Zen

Bridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.

10K+

18 Tools

Packaged by

Requires Secrets

Add to Docker Desktop

Version 4.43 or later needs to be installed to add the server automatically

Overview Tools (18)Config

Docker Hub⁠Github repository⁠

Use cases

Performs comprehensive code analysis with systematic investigation and expert validation. Use for architecture, performance, maintainability, and pattern analysis. Guides through structured code review and strategic planning.

Use this tool automatically when you need current API/SDK documentation, latest version info, breaking changes, deprecations, migration guides, or official release notes. This tool searches authoritative sources (official docs, GitHub, package registries) to ensure up-to-date accuracy.

Prevents reflexive agreement by forcing critical thinking and reasoned analysis when a statement is challenged. Trigger automatically when a user critically questions, disagrees or appears to push back on earlier answers, and use it manually to sanity-check contentious claims.

General chat and collaborative thinking partner for brainstorming, development discussion, getting second opinions, and exploring ideas. Use for ideas, validations, questions, and thoughtful explanations.

Link a request to an external AI CLI (Gemini CLI, Qwen CLI, etc.) through PAL MCP to reuse their capabilities inside existing workflows.

Performs systematic, step-by-step code review with expert validation. Use for comprehensive analysis covering quality, security, performance, and architecture. Guides through structured investigation to ensure thoroughness.

Builds multi-model consensus through systematic analysis and structured debate. Use for complex decisions, architectural choices, feature proposals, and technology evaluations. Consults multiple models with different stances to synthesize comprehensive recommendations.

Performs systematic debugging and root cause analysis for any type of issue. Use for complex bugs, mysterious errors, performance issues, race conditions, memory leaks, and integration problems. Guides through structured investigation with hypothesis testing and expert analysis.

Generates comprehensive code documentation with systematic analysis of functions, classes, and complexity. Use for documentation generation, code analysis, complexity assessment, and API documentation. Analyzes code structure and patterns to create thorough documentation.

Shows which AI model providers are configured, available model names, their aliases and capabilities.

View all

About

Zen MCP Server

Bridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.

What is an MCP Server?⁠

MCP Info

Attribute	Details
Docker Image	mcp/zen⁠
Author	BeehiveInnovations⁠
Repository	https://github.com/beehiveinnovations/zen-mcp-server⁠

Image Building Info

Attribute	Details
Dockerfile	https://github.com/beehiveinnovations/zen-mcp-server/blob/7afc7c1cc96e23992c8f105f960132c657883bb1/Dockerfile⁠
Commit	`7afc7c1cc96e23992c8f105f960132c657883bb1`
Docker Image built by	Docker Inc.
Docker Scout Health Score
Verify Signature	`COSIGN_REPOSITORY=mcp/signatures cosign verify mcp/zen --key https://raw.githubusercontent.com/docker/keyring/refs/heads/main/public/mcp/latest.pub`
Licence	Other

Available Tools (18)

Tools provided by this Server	Short Description
`analyze`	Performs comprehensive code analysis with systematic investigation and expert validation.
`apilookup`	Use this tool automatically when you need current API/SDK documentation, latest version info, breaking changes, deprecations, migration guides, or official release notes.
`challenge`	Prevents reflexive agreement by forcing critical thinking and reasoned analysis when a statement is challenged.
`chat`	General chat and collaborative thinking partner for brainstorming, development discussion, getting second opinions, and exploring ideas.
`clink`	Link a request to an external AI CLI (Gemini CLI, Qwen CLI, etc.) through PAL MCP to reuse their capabilities inside existing workflows.
`codereview`	Performs systematic, step-by-step code review with expert validation.
`consensus`	Builds multi-model consensus through systematic analysis and structured debate.
`debug`	Performs systematic debugging and root cause analysis for any type of issue.
`docgen`	Generates comprehensive code documentation with systematic analysis of functions, classes, and complexity.
`listmodels`	Shows which AI model providers are configured, available model names, their aliases and capabilities.
`planner`	Breaks down complex tasks through interactive, sequential planning with revision and branching capabilities.
`precommit`	Validates git changes and repository state before committing with systematic analysis.
`refactor`	Analyzes code for refactoring opportunities with systematic investigation.
`secaudit`	Performs comprehensive security audit with systematic vulnerability assessment.
`testgen`	Creates comprehensive test suites with edge case coverage for specific functions, classes, or modules.
`thinkdeep`	Performs multi-stage investigation and reasoning for complex problem analysis.
`tracer`	Performs systematic code tracing with modes for execution flow or dependency mapping.
`version`	Get server version, configuration details, and list of available tools.

Tools Details

Tool: `analyze`

Parameters	Type	Description
`findings`	`string`	Summary of discoveries from this step, including architectural patterns, tech stack assessment, scalability characteristics, performance implications, maintainability factors, and strategic improvement opportunities. IMPORTANT: Document both strengths (good patterns, solid architecture) and concerns (tech debt, overengineering, unnecessary complexity). In later steps, confirm or update past findings with additional evidence.
`model`	`string`	Currently in auto model selection mode. CRITICAL: When the user names a model, you MUST use that exact name unless the server rejects it. If no model is provided, you may use the `listmodels` tool to review options and select an appropriate match. Top models: gpt-5.2 (score 100, 400K ctx, thinking, code-gen); gpt-5.1-codex (score 100, 400K ctx, thinking, code-gen); gemini-2.5-pro (score 100, 1.0M ctx, thinking, code-gen); gemini-3-pro-preview (score 100, 1.0M ctx, thinking, code-gen); gpt-5.2-pro (score 100, 400K ctx, thinking, code-gen); +26 more via `listmodels`.
`next_step_required`	`boolean`	Set to true if you plan to continue the investigation with another step. False means you believe the analysis is complete and ready for expert validation.
`step`	`string`	The analysis plan. Step 1: State your strategy, including how you will map the codebase structure, understand business logic, and assess code quality, performance implications, and architectural patterns. Later steps: Report findings and adapt the approach as new insights emerge.
`step_number`	`integer`	The index of the current step in the analysis sequence, beginning at 1. Each step should build upon or revise the previous one.
`total_steps`	`integer`	Your current estimate for how many steps will be needed to complete the analysis. Adjust as new findings emerge.
`analysis_type`	`string`optional	Type of analysis to perform (architecture, performance, security, quality, general)
`confidence`	`string`optional	Your confidence in the analysis: exploring, low, medium, high, very_high, almost_certain, or certain. 'certain' indicates the analysis is complete and ready for validation.
`continuation_id`	`string`optional	Unique thread continuation ID for multi-turn conversations. Works across different tools. ALWAYS reuse the last continuation_id you were given—this preserves full conversation context, files, and findings so the agent can resume seamlessly.
`files_checked`	`array`optional	List all files examined (absolute paths). Include even ruled-out files to track exploration path.
`images`	`array`optional	Optional absolute paths to architecture diagrams or visual references that help with analysis context.
`issues_found`	`array`optional	Issues or concerns identified during analysis, each with severity level (critical, high, medium, low)
`output_format`	`string`optional	How to format the output (summary, detailed, actionable)
`relevant_context`	`array`optional	Methods/functions identified as involved in the issue
`relevant_files`	`array`optional	Subset of files_checked directly relevant to analysis findings (absolute paths). Include files with significant patterns, architectural decisions, or strategic improvement opportunities.
`temperature`	`number`optional	0 = deterministic · 1 = creative.
`thinking_mode`	`string`optional	Reasoning depth: minimal, low, medium, high, or max.
`use_assistant_model`	`boolean`optional	Use assistant model for expert analysis after workflow steps. False skips expert analysis, relies solely on your personal investigation. Defaults to True for comprehensive validation.

This tool is read-only. It does not modify its environment.

Tool: `apilookup`

Parameters	Type	Description
`prompt`	`string`	The API, SDK, library, framework, or technology you need current documentation, version info, breaking changes, or migration guidance for.

This tool is read-only. It does not modify its environment.

Tool: `challenge`

Parameters	Type	Description
`prompt`	`string`	Statement to scrutinize. If you invoke `challenge` manually, strip the word 'challenge' and pass just the statement. Automatic invocations send the full user message as-is; do not modify it.

This tool is read-only. It does not modify its environment.

Tool: `chat`

Parameters	Type	Description
`model`	`string`	Currently in auto model selection mode. CRITICAL: When the user names a model, you MUST use that exact name unless the server rejects it. If no model is provided, you may use the `listmodels` tool to review options and select an appropriate match. Top models: gpt-5.2 (score 100, 400K ctx, thinking, code-gen); gpt-5.1-codex (score 100, 400K ctx, thinking, code-gen); gemini-2.5-pro (score 100, 1.0M ctx, thinking, code-gen); gemini-3-pro-preview (score 100, 1.0M ctx, thinking, code-gen); gpt-5.2-pro (score 100, 400K ctx, thinking, code-gen); +26 more via `listmodels`.
`prompt`	`string`	Your question or idea for collaborative thinking to be sent to the external model. Provide detailed context, including your goal, what you've tried, and any specific challenges. WARNING: Large inline code must NOT be shared in prompt. Provide full-path to files on disk as separate parameter.
`working_directory_absolute_path`	`string`	Absolute path to an existing directory where generated code artifacts can be saved.
`absolute_file_paths`	`array`optional	Full, absolute file paths to relevant code in order to share with external model
`continuation_id`	`string`optional	Unique thread continuation ID for multi-turn conversations. Works across different tools. ALWAYS reuse the last continuation_id you were given—this preserves full conversation context, files, and findings so the agent can resume seamlessly.
`images`	`array`optional	Image paths (absolute) or base64 strings for optional visual context.
`temperature`	`number`optional	0 = deterministic · 1 = creative.
`thinking_mode`	`string`optional	Reasoning depth: minimal, low, medium, high, or max.

Tool: `clink`

Link a request to an external AI CLI (Gemini CLI, Qwen CLI, etc.) through PAL MCP to reuse their capabilities inside existing workflows.

Parameters	Type	Description
`cli_name`	`string`	Configured CLI client name (from conf/cli_clients). Available: claude, codex, gemini
`prompt`	`string`	User request forwarded to the CLI (conversation context is pre-applied).
`absolute_file_paths`	`array`optional	Full paths to relevant code
`continuation_id`	`string`optional	Unique thread continuation ID for multi-turn conversations. Works across different tools. ALWAYS reuse the last continuation_id you were given—this preserves full conversation context, files, and findings so the agent can resume seamlessly.
`images`	`array`optional	Optional absolute image paths or base64 blobs for visual context.
`role`	`string`optional	Optional role preset defined for the selected CLI (defaults to 'default'). Roles per CLI: claude: codereviewer, default, planner; codex: codereviewer, default, planner; gemini: codereviewer, default, planner

This tool is read-only. It does not modify its environment.

Tool: `codereview`

Parameters	Type	Description
`findings`	`string`	Capture findings (positive and negative) across quality, security, performance, and architecture; update each step.
`model`	`string`	Currently in auto model selection mode. CRITICAL: When the user names a model, you MUST use that exact name unless the server rejects it. If no model is provided, you may use the `listmodels` tool to review options and select an appropriate match. Top models: gpt-5.2 (score 100, 400K ctx, thinking, code-gen); gpt-5.1-codex (score 100, 400K ctx, thinking, code-gen); gemini-2.5-pro (score 100, 1.0M ctx, thinking, code-gen); gemini-3-pro-preview (score 100, 1.0M ctx, thinking, code-gen); gpt-5.2-pro (score 100, 400K ctx, thinking, code-gen); +26 more via `listmodels`.
`next_step_required`	`boolean`	True when another review step follows. External validation: step 1 → True, step 2 → False. Internal validation: set False immediately. Apply the same rule on continuation flows.
`step`	`string`	Review narrative. Step 1: outline the review strategy. Later steps: report findings. MUST cover quality, security, performance, and architecture. Reference code via `relevant_files`; avoid dumping large snippets.
`step_number`	`integer`	Current review step (starts at 1) – each step should build on the last.
`total_steps`	`integer`	Number of review steps planned. External validation: two steps (analysis + summary). Internal validation: one step. Use the same limits when continuing an existing review via continuation_id.
`confidence`	`string`optional	Confidence level: exploring (just starting), low (early investigation), medium (some evidence), high (strong evidence), very_high (comprehensive understanding), almost_certain (near complete confidence), certain (100% confidence locally - no external validation needed)
`continuation_id`	`string`optional	Unique thread continuation ID for multi-turn conversations. Works across different tools. ALWAYS reuse the last continuation_id you were given—this preserves full conversation context, files, and findings so the agent can resume seamlessly.
`files_checked`	`array`optional	Absolute paths of every file reviewed, including those ruled out.
`focus_on`	`string`optional	Optional note on areas to emphasise (e.g. 'threading', 'auth flow').
`hypothesis`	`string`optional	Current theory about issue/goal based on work
`images`	`array`optional	Optional diagram or screenshot paths that clarify review context.
`issues_found`	`array`optional	Issues with severity (critical/high/medium/low) and descriptions.
`relevant_context`	`array`optional	Methods/functions identified as involved in the issue
`relevant_files`	`array`optional	Step 1: list all files/dirs under review. Must be absolute full non-abbreviated paths. Final step: narrow to files tied to key findings.
`review_type`	`string`optional	Review focus: full, security, performance, or quick.
`review_validation_type`	`string`optional	Set 'external' (default) for expert follow-up or 'internal' for local-only review.
`severity_filter`	`string`optional	Lowest severity to include when reporting issues (critical/high/medium/low/all).
`standards`	`string`optional	Coding standards or style guides to enforce.
`temperature`	`number`optional	0 = deterministic · 1 = creative.
`thinking_mode`	`string`optional	Reasoning depth: minimal, low, medium, high, or max.
`use_assistant_model`	`boolean`optional	Use assistant model for expert analysis after workflow steps. False skips expert analysis, relies solely on your personal investigation. Defaults to True for comprehensive validation.

This tool is read-only. It does not modify its environment.

Tool: `consensus`

Parameters	Type	Description
`findings`	`string`	Step 1: your independent analysis for later synthesis (not shared with other models). Steps 2+: summarize the newest model response.
`next_step_required`	`boolean`	True if more model consultations remain; set false when ready to synthesize.
`step`	`string`	Consensus prompt. Step 1: write the exact proposal/question every model will see (use 'Evaluate…', not meta commentary). Steps 2+: capture internal notes about the latest model response—these notes are NOT sent to other models.
`step_number`	`integer`	Current step index (starts at 1). Step 1 is your analysis; steps 2+ handle each model response.
`total_steps`	`integer`	Total steps = number of models consulted plus the final synthesis step.
`continuation_id`	`string`optional	Unique thread continuation ID for multi-turn conversations. Works across different tools. ALWAYS reuse the last continuation_id you were given—this preserves full conversation context, files, and findings so the agent can resume seamlessly.
`current_model_index`	`integer`optional	0-based index of the next model to consult (managed internally).
`images`	`array`optional	Optional absolute image paths or base64 references that add helpful visual context.
`model_responses`	`array`optional	Internal log of responses gathered so far.
`models`	`array`optional	User-specified roster of models to consult (provide at least two entries). User-specified list of models to consult (provide at least two entries). Each entry may include model, stance (for/against/neutral), and stance_prompt. Each (model, stance) pair must be unique, e.g. [{'model':'gpt5','stance':'for'}, {'model':'pro','stance':'against'}]. When the user names a model, you MUST use that exact value or report the provider error—never swap in another option. Use the `listmodels` tool for the full roster. Top models: gpt-5.2 (score 100, 400K ctx, thinking, code-gen); gpt-5.1-codex (score 100, 400K ctx, thinking, code-gen); gemini-2.5-pro (score 100, 1.0M ctx, thinking, code-gen); gemini-3-pro-preview (score 100, 1.0M ctx, thinking, code-gen); gpt-5.2-pro (score 100, 400K ctx, thinking, code-gen); +26 more via `listmodels`.
`relevant_files`	`array`optional	Optional supporting files that help the consensus analysis. Must be absolute full, non-abbreviated paths.
`use_assistant_model`	`boolean`optional	Use assistant model for expert analysis after workflow steps. False skips expert analysis, relies solely on your personal investigation. Defaults to True for comprehensive validation.

This tool is read-only. It does not modify its environment.

Tool: `debug`

Parameters	Type	Description
`findings`	`string`	Discoveries: clues, code/log evidence, disproven theories. Be specific. If no bug found, document clearly as valid.
`model`	`string`	Currently in auto model selection mode. CRITICAL: When the user names a model, you MUST use that exact name unless the server rejects it. If no model is provided, you may use the `listmodels` tool to review options and select an appropriate match. Top models: gpt-5.2 (score 100, 400K ctx, thinking, code-gen); gpt-5.1-codex (score 100, 400K ctx, thinking, code-gen); gemini-2.5-pro (score 100, 1.0M ctx, thinking, code-gen); gemini-3-pro-preview (score 100, 1.0M ctx, thinking, code-gen); gpt-5.2-pro (score 100, 400K ctx, thinking, code-gen); +26 more via `listmodels`.
`next_step_required`	`boolean`	True if you plan to continue the investigation with another step. False means root cause is known or investigation is complete. IMPORTANT: When continuation_id is provided (continuing a previous conversation), set this to False to immediately proceed with expert analysis.
`step`	`string`	Investigation step. Step 1: State issue+direction. Symptoms misleading; 'no bug' valid. Trace dependencies, verify hypotheses. Use relevant_files for code; this for text only.
`step_number`	`integer`	Current step index (starts at 1). Build upon previous steps.
`total_steps`	`integer`	Estimated total steps needed to complete the investigation. Adjust as new findings emerge. IMPORTANT: When continuation_id is provided (continuing a previous conversation), set this to 1 as we're not starting a new multi-step investigation.
`confidence`	`string`optional	Your confidence in the hypothesis: exploring (starting out), low (early idea), medium (some evidence), high (strong evidence), very_high (very strong evidence), almost_certain (nearly confirmed), certain (100% confidence - root cause and fix are both confirmed locally with no need for external validation). WARNING: Do NOT use 'certain' unless the issue can be fully resolved with a fix, use 'very_high' or 'almost_certain' instead when not 100% sure. Using 'certain' means you have ABSOLUTE confidence locally and PREVENTS external model validation.
`continuation_id`	`string`optional	Unique thread continuation ID for multi-turn conversations. Works across different tools. ALWAYS reuse the last continuation_id you were given—this preserves full conversation context, files, and findings so the agent can resume seamlessly.
`files_checked`	`array`optional	All examined files (absolute paths), including ruled-out ones.
`hypothesis`	`string`optional	Concrete root cause theory from evidence. Can revise. Valid: 'No bug found - user misunderstanding' or 'Symptoms unrelated to code' if supported.
`images`	`array`optional	Optional screenshots/visuals clarifying issue (absolute paths).
`issues_found`	`array`optional	Issues identified with severity levels during work
`relevant_context`	`array`optional	Methods/functions identified as involved in the issue
`relevant_files`	`array`optional	Files directly relevant to issue (absolute paths). Cause, trigger, or manifestation locations.
`temperature`	`number`optional	0 = deterministic · 1 = creative.
`thinking_mode`	`string`optional	Reasoning depth: minimal, low, medium, high, or max.
`use_assistant_model`	`boolean`optional	Use assistant model for expert analysis after workflow steps. False skips expert analysis, relies solely on your personal investigation. Defaults to True for comprehensive validation.

This tool is read-only. It does not modify its environment.

Tool: `docgen`

Parameters	Type	Description
`comments_on_complex_logic`	`boolean`	True (default) to add inline comments around non-obvious logic.
`document_complexity`	`boolean`	Include algorithmic complexity (Big O) analysis when True (default).
`document_flow`	`boolean`	Include call flow/dependency notes when True (default).
`findings`	`string`	Important findings, evidence and insights discovered in this step
`next_step_required`	`boolean`	Whether another work step is needed. When false, aim to reduce total_steps to match step_number to avoid mismatch.
`num_files_documented`	`integer`	Count of files finished so far. Increment only when a file is fully documented.
`step`	`string`	Current work step content and findings from your overall work
`step_number`	`integer`	Current step number in work sequence (starts at 1)
`total_files_to_document`	`integer`	Total files identified in discovery; completion requires matching this count.
`total_steps`	`integer`	Estimated total steps needed to complete work
`update_existing`	`boolean`	True (default) to polish inaccurate or outdated docs instead of leaving them untouched.
`continuation_id`	`string`optional	Unique thread continuation ID for multi-turn conversations. Works across different tools. ALWAYS reuse the last continuation_id you were given—this preserves full conversation context, files, and findings so the agent can resume seamlessly.
`issues_found`	`array`optional	Issues identified with severity levels during work
`relevant_context`	`array`optional	Methods/functions identified as involved in the issue
`relevant_files`	`array`optional	Files identified as relevant to issue/goal (FULL absolute paths to real files/folders - DO NOT SHORTEN)
`use_assistant_model`	`boolean`optional	Use assistant model for expert analysis after workflow steps. False skips expert analysis, relies solely on your personal investigation. Defaults to True for comprehensive validation.

This tool is read-only. It does not modify its environment.

Tool: `listmodels`

Shows which AI model providers are configured, available model names, their aliases and capabilities.

Tool: `planner`

Breaks down complex tasks through interactive, sequential planning with revision and branching capabilities. Use for complex project planning, system design, migration strategies, and architectural decisions. Builds plans incrementally with deep reflection for complex scenarios.

Parameters	Type	Description
`model`	`string`	Currently in auto model selection mode. CRITICAL: When the user names a model, you MUST use that exact name unless the server rejects it. If no model is provided, you may use the `listmodels` tool to review options and select an appropriate match. Top models: gpt-5.2 (score 100, 400K ctx, thinking, code-gen); gpt-5.1-codex (score 100, 400K ctx, thinking, code-gen); gemini-2.5-pro (score 100, 1.0M ctx, thinking, code-gen); gemini-3-pro-preview (score 100, 1.0M ctx, thinking, code-gen); gpt-5.2-pro (score 100, 400K ctx, thinking, code-gen); +26 more via `listmodels`.
`next_step_required`	`boolean`	Whether another work step is needed. When false, aim to reduce total_steps to match step_number to avoid mismatch.
`step`	`string`	Planning content for this step. Step 1: describe the task, problem and scope. Later steps: capture updates, revisions, branches, or open questions that shape the plan.
`step_number`	`integer`	Current step number in work sequence (starts at 1)
`total_steps`	`integer`	Estimated total steps needed to complete work
`branch_from_step`	`integer`optional	If branching, the step number that this branch starts from.
`branch_id`	`string`optional	Name for this branch (e.g. 'approach-A', 'migration-path').
`continuation_id`	`string`optional	Unique thread continuation ID for multi-turn conversations. Works across different tools. ALWAYS reuse the last continuation_id you were given—this preserves full conversation context, files, and findings so the agent can resume seamlessly.
`is_branch_point`	`boolean`optional	True when this step creates a new branch to explore an alternative path.
`is_step_revision`	`boolean`optional	Set true when you are replacing a previously recorded step.
`more_steps_needed`	`boolean`optional	True when you now expect to add additional steps beyond the prior estimate.
`revises_step_number`	`integer`optional	Step number being replaced when revising.
`use_assistant_model`	`boolean`optional	Use assistant model for expert analysis after workflow steps. False skips expert analysis, relies solely on your personal investigation. Defaults to True for comprehensive validation.

This tool is read-only. It does not modify its environment.

Tool: `precommit`

Validates git changes and repository state before committing with systematic analysis. Use for multi-repository validation, security review, change impact assessment, and completeness verification. Guides through structured investigation with expert analysis.

Parameters	Type	Description
`findings`	`string`	Record git diff insights, risks, missing tests, security concerns, and positives; update previous notes as you go.
`model`	`string`	Currently in auto model selection mode. CRITICAL: When the user names a model, you MUST use that exact name unless the server rejects it. If no model is provided, you may use the `listmodels` tool to review options and select an appropriate match. Top models: gpt-5.2 (score 100, 400K ctx, thinking, code-gen); gpt-5.1-codex (score 100, 400K ctx, thinking, code-gen); gemini-2.5-pro (score 100, 1.0M ctx, thinking, code-gen); gemini-3-pro-preview (score 100, 1.0M ctx, thinking, code-gen); gpt-5.2-pro (score 100, 400K ctx, thinking, code-gen); +26 more via `listmodels`.
`next_step_required`	`boolean`	True to continue with another step, False when validation is complete. CRITICAL: If total_steps>=3 or when `precommit_type = external`, set to True until the final step. When continuation_id is provided: Follow the same validation rules based on precommit_type.
`step`	`string`	Step 1: outline how you'll validate the git changes. Later steps: report findings. Review diffs and impacts, use `relevant_files`, and avoid pasting large snippets.
`step_number`	`integer`	Current pre-commit step number (starts at 1).
`total_steps`	`integer`	Planned number of validation steps. External validation: use at most three (analysis → follow-ups → summary). Internal validation: a single step. Honour these limits when resuming via continuation_id.
`compare_to`	`string`optional	Optional git ref (branch/tag/commit) to diff against; falls back to staged/unstaged changes.
`confidence`	`string`optional	Confidence level: exploring (just starting), low (early investigation), medium (some evidence), high (strong evidence), very_high (comprehensive understanding), almost_certain (near complete confidence), certain (100% confidence locally - no external validation needed)
`continuation_id`	`string`optional	Unique thread continuation ID for multi-turn conversations. Works across different tools. ALWAYS reuse the last continuation_id you were given—this preserves full conversation context, files, and findings so the agent can resume seamlessly.
`files_checked`	`array`optional	Absolute paths for every file examined, including ruled-out candidates.
`focus_on`	`string`optional	Optional emphasis areas such as security, performance, or test coverage.
`hypothesis`	`string`optional	Current theory about issue/goal based on work
`images`	`array`optional	Optional absolute paths to screenshots or diagrams that aid validation.
`include_staged`	`boolean`optional	Whether to inspect staged changes (ignored when `compare_to` is set).
`include_unstaged`	`boolean`optional	Whether to inspect unstaged changes (ignored when `compare_to` is set).
`issues_found`	`array`optional	List issues with severity (critical/high/medium/low) plus descriptions (bugs, security, performance, coverage).
`path`	`string`optional	Absolute path to the repository root. Required in step 1.
`precommit_type`	`string`optional	'external' (default, triggers expert model) or 'internal' (local-only validation).
`relevant_context`	`array`optional	Methods/functions identified as involved in the issue
`relevant_files`	`array`optional	Absolute paths of files involved in the change or validation (code, configs, tests, docs). Must be absolute full non-abbreviated paths.
`severity_filter`	`string`optional	Lowest severity to include when reporting issues.
`temperature`	`number`optional	0 = deterministic · 1 = creative.
`thinking_mode`	`string`optional	Reasoning depth: minimal, low, medium, high, or max.
`use_assistant_model`	`boolean`optional	Use assistant model for expert analysis after workflow steps. False skips expert analysis, relies solely on your personal investigation. Defaults to True for comprehensive validation.

This tool is read-only. It does not modify its environment.

Tool: `refactor`

Analyzes code for refactoring opportunities with systematic investigation. Use for code smell detection, decomposition planning, modernization, and maintainability improvements. Guides through structured analysis with expert validation.

Parameters	Type	Description
`findings`	`string`	Summary of discoveries from this step, including code smells and opportunities for decomposition, modernization, or organization. Document both strengths and weaknesses. In later steps, confirm or update past findings.
`model`	`string`	Currently in auto model selection mode. CRITICAL: When the user names a model, you MUST use that exact name unless the server rejects it. If no model is provided, you may use the `listmodels` tool to review options and select an appropriate match. Top models: gpt-5.2 (score 100, 400K ctx, thinking, code-gen); gpt-5.1-codex (score 100, 400K ctx, thinking, code-gen); gemini-2.5-pro (score 100, 1.0M ctx, thinking, code-gen); gemini-3-pro-preview (score 100, 1.0M ctx, thinking, code-gen); gpt-5.2-pro (score 100, 400K ctx, thinking, code-gen); +26 more via `listmodels`.
`next_step_required`	`boolean`	Set to true if you plan to continue the investigation with another step. False means you believe the refactoring analysis is complete and ready for expert validation.
`step`	`string`	The refactoring plan. Step 1: State strategy. Later steps: Report findings. CRITICAL: Examine code for smells, and opportunities for decomposition, modernization, and organization. Use 'relevant_files' for code. FORBIDDEN: Large code snippets.
`step_number`	`integer`	The index of the current step in the refactoring investigation sequence, beginning at 1. Each step should build upon or revise the previous one.
`total_steps`	`integer`	Your current estimate for how many steps will be needed to complete the refactoring investigation. Adjust as new opportunities emerge.
`confidence`	`string`optional	Your confidence in refactoring analysis: exploring (starting), incomplete (significant work remaining), partial (some opportunities found, more analysis needed), complete (comprehensive analysis finished, all major opportunities identified). WARNING: Use 'complete' ONLY when fully analyzed and can provide recommendations without expert help. 'complete' PREVENTS expert validation. Use 'partial' for large files or uncertain analysis.
`continuation_id`	`string`optional	Unique thread continuation ID for multi-turn conversations. Works across different tools. ALWAYS reuse the last continuation_id you were given—this preserves full conversation context, files, and findings so the agent can resume seamlessly.
`files_checked`	`array`optional	List all files examined (absolute paths). Include even ruled-out files to track exploration path.
`focus_areas`	`array`optional	Specific areas to focus on (e.g., 'performance', 'readability', 'maintainability', 'security')
`hypothesis`	`string`optional	Current theory about issue/goal based on work
`images`	`array`optional	Optional list of absolute paths to architecture diagrams, UI mockups, design documents, or visual references that help with refactoring context. Only include if they materially assist understanding or assessment.
`issues_found`	`array`optional	Refactoring opportunities as dictionaries with 'severity' (critical/high/medium/low), 'type' (codesmells/decompose/modernize/organization), and 'description'. Include all improvement opportunities found.
`refactor_type`	`string`optional	Type of refactoring analysis to perform (codesmells, decompose, modernize, organization)
`relevant_context`	`array`optional	Methods/functions identified as involved in the issue
`relevant_files`	`array`optional	Subset of files_checked with code requiring refactoring (absolute paths). Include files with code smells, decomposition needs, or improvement opportunities.
`style_guide_examples`	`array`optional	Optional existing code files to use as style/pattern reference (must be FULL absolute paths to real files / folders - DO NOT SHORTEN). These files represent the target coding style and patterns for the project.
`temperature`	`number`optional	0 = deterministic · 1 = creative.
`thinking_mode`	`string`optional	Reasoning depth: minimal, low, medium, high, or max.
`use_assistant_model`	`boolean`optional	Use assistant model for expert analysis after workflow steps. False skips expert analysis, relies solely on your personal investigation. Defaults to True for comprehensive validation.

This tool is read-only. It does not modify its environment.

Tool: `secaudit`

Performs comprehensive security audit with systematic vulnerability assessment. Use for OWASP Top 10 analysis, compliance evaluation, threat modeling, and security architecture review. Guides through structured security investigation with expert validation.

Parameters	Type	Description
`findings`	`string`	Summarize vulnerabilities, auth issues, validation gaps, compliance notes, and positives; update prior findings as needed.
`model`	`string`	Currently in auto model selection mode. CRITICAL: When the user names a model, you MUST use that exact name unless the server rejects it. If no model is provided, you may use the `listmodels` tool to review options and select an appropriate match. Top models: gpt-5.2 (score 100, 400K ctx, thinking, code-gen); gpt-5.1-codex (score 100, 400K ctx, thinking, code-gen); gemini-2.5-pro (score 100, 1.0M ctx, thinking, code-gen); gemini-3-pro-preview (score 100, 1.0M ctx, thinking, code-gen); gpt-5.2-pro (score 100, 400K ctx, thinking, code-gen); +26 more via `listmodels`.
`next_step_required`	`boolean`	True while additional threat analysis remains; set False once you are ready to hand off for validation.
`step`	`string`	Step 1: outline the audit strategy (OWASP Top 10, auth, validation, etc.). Later steps: report findings. MANDATORY: use `relevant_files` for code references and avoid large snippets.
`step_number`	`integer`	Current security-audit step number (starts at 1).
`total_steps`	`integer`	Expected number of audit steps; adjust as new risks surface.
`audit_focus`	`string`optional	Primary focus area: owasp, compliance, infrastructure, dependencies, or comprehensive.
`compliance_requirements`	`array`optional	Applicable compliance frameworks or standards (SOC2, PCI DSS, HIPAA, GDPR, ISO 27001, NIST, etc.).
`confidence`	`string`optional	exploring/low/medium/high/very_high/almost_certain/certain. 'certain' blocks external validation—use only when fully complete.
`continuation_id`	`string`optional	Unique thread continuation ID for multi-turn conversations. Works across different tools. ALWAYS reuse the last continuation_id you were given—this preserves full conversation context, files, and findings so the agent can resume seamlessly.
`files_checked`	`array`optional	Absolute paths for every file inspected, including rejected candidates.
`hypothesis`	`string`optional	Current theory about issue/goal based on work
`images`	`array`optional	Optional absolute paths to diagrams or threat models that inform the audit.
`issues_found`	`array`optional	Security issues with severity (critical/high/medium/low) and descriptions (vulns, auth flaws, injection, crypto, config).
`relevant_context`	`array`optional	Methods/functions identified as involved in the issue
`relevant_files`	`array`optional	Absolute paths for security-relevant files (auth modules, configs, sensitive code).
`security_scope`	`string`optional	Security context (web, mobile, API, cloud, etc.) including stack, user types, data sensitivity, and threat landscape.
`severity_filter`	`string`optional	Minimum severity to include when reporting security issues.
`temperature`	`number`optional	0 = deterministic · 1 = creative.
`thinking_mode`	`string`optional	Reasoning depth: minimal, low, medium, high, or max.
`threat_level`	`string`optional	Assess the threat level: low (internal/low-risk), medium (customer-facing/business data), high (regulated or sensitive), critical (financial/healthcare/PII).
`use_assistant_model`	`boolean`optional	Use assistant model for expert analysis after workflow steps. False skips expert analysis, relies solely on your personal investigation. Defaults to True for comprehensive validation.

This tool is read-only. It does not modify its environment.

Tool: `testgen`

Creates comprehensive test suites with edge case coverage for specific functions, classes, or modules. Analyzes code paths, identifies failure modes, and generates framework-specific tests. Be specific about scope - target particular components rather than testing everything.

Parameters	Type	Description
`findings`	`string`	Summarise functionality, critical paths, edge cases, boundary conditions, error handling, and existing test patterns. Cover both happy and failure paths.
`model`	`string`	Currently in auto model selection mode. CRITICAL: When the user names a model, you MUST use that exact name unless the server rejects it. If no model is provided, you may use the `listmodels` tool to review options and select an appropriate match. Top models: gpt-5.2 (score 100, 400K ctx, thinking, code-gen); gpt-5.1-codex (score 100, 400K ctx, thinking, code-gen); gemini-2.5-pro (score 100, 1.0M ctx, thinking, code-gen); gemini-3-pro-preview (score 100, 1.0M ctx, thinking, code-gen); gpt-5.2-pro (score 100, 400K ctx, thinking, code-gen); +26 more via `listmodels`.
`next_step_required`	`boolean`	True while more investigation or planning remains; set False when test planning is ready for expert validation.
`step`	`string`	Test plan for this step. Step 1: outline how you'll analyse structure, business logic, critical paths, and edge cases. Later steps: record findings and new scenarios as they emerge.
`step_number`	`integer`	Current test-generation step (starts at 1) — each step should build on prior work.
`total_steps`	`integer`	Estimated number of steps needed for test planning; adjust as new scenarios appear.
`confidence`	`string`optional	Indicate your current confidence in the test generation assessment. Use: 'exploring' (starting analysis), 'low' (early investigation), 'medium' (some patterns identified), 'high' (strong understanding), 'very_high' (very strong understanding), 'almost_certain' (nearly complete test plan), 'certain' (100% confidence - test plan is thoroughly complete and all test scenarios are identified with no need for external model validation). Do NOT use 'certain' unless the test generation analysis is comprehensively complete, use 'very_high' or 'almost_certain' instead if not 100% sure. Using 'certain' means you have complete confidence locally and prevents external model validation.
`continuation_id`	`string`optional	Unique thread continuation ID for multi-turn conversations. Works across different tools. ALWAYS reuse the last continuation_id you were given—this preserves full conversation context, files, and findings so the agent can resume seamlessly.
`files_checked`	`array`optional	Absolute paths of every file examined, including those ruled out.
`hypothesis`	`string`optional	Current theory about issue/goal based on work
`images`	`array`optional	Optional absolute paths to diagrams or visuals that clarify the system under test.
`issues_found`	`array`optional	Issues identified with severity levels during work
`relevant_context`	`array`optional	Methods/functions identified as involved in the issue
`relevant_files`	`array`optional	Absolute paths of code that requires new or updated tests (implementation, dependencies, existing test fixtures).
`temperature`	`number`optional	0 = deterministic · 1 = creative.
`thinking_mode`	`string`optional	Reasoning depth: minimal, low, medium, high, or max.
`use_assistant_model`	`boolean`optional	Use assistant model for expert analysis after workflow steps. False skips expert analysis, relies solely on your personal investigation. Defaults to True for comprehensive validation.

This tool is read-only. It does not modify its environment.

Tool: `thinkdeep`

Performs multi-stage investigation and reasoning for complex problem analysis. Use for architecture decisions, complex bugs, performance challenges, and security analysis. Provides systematic hypothesis testing, evidence-based investigation, and expert validation.

Parameters	Type	Description
`findings`	`string`	Important findings, evidence and insights discovered in this step
`model`	`string`	Currently in auto model selection mode. CRITICAL: When the user names a model, you MUST use that exact name unless the server rejects it. If no model is provided, you may use the `listmodels` tool to review options and select an appropriate match. Top models: gpt-5.2 (score 100, 400K ctx, thinking, code-gen); gpt-5.1-codex (score 100, 400K ctx, thinking, code-gen); gemini-2.5-pro (score 100, 1.0M ctx, thinking, code-gen); gemini-3-pro-preview (score 100, 1.0M ctx, thinking, code-gen); gpt-5.2-pro (score 100, 400K ctx, thinking, code-gen); +26 more via `listmodels`.
`next_step_required`	`boolean`	Whether another work step is needed. When false, aim to reduce total_steps to match step_number to avoid mismatch.
`step`	`string`	Current work step content and findings from your overall work
`step_number`	`integer`	Current step number in work sequence (starts at 1)
`total_steps`	`integer`	Estimated total steps needed to complete work
`confidence`	`string`optional	Confidence level: exploring (just starting), low (early investigation), medium (some evidence), high (strong evidence), very_high (comprehensive understanding), almost_certain (near complete confidence), certain (100% confidence locally - no external validation needed)
`continuation_id`	`string`optional	Unique thread continuation ID for multi-turn conversations. Works across different tools. ALWAYS reuse the last continuation_id you were given—this preserves full conversation context, files, and findings so the agent can resume seamlessly.
`files_checked`	`array`optional	List of files examined during this work step
`focus_areas`	`array`optional	Focus aspects (architecture, performance, security, etc.)
`hypothesis`	`string`optional	Current theory about issue/goal based on work
`images`	`array`optional	Optional absolute image paths or base64 blobs for visual context.
`issues_found`	`array`optional	Issues identified with severity levels during work
`problem_context`	`string`optional	Additional context about problem/goal. Be expressive.
`relevant_context`	`array`optional	Methods/functions identified as involved in the issue
`relevant_files`	`array`optional	Files identified as relevant to issue/goal (FULL absolute paths to real files/folders - DO NOT SHORTEN)
`temperature`	`number`optional	0 = deterministic · 1 = creative.
`thinking_mode`	`string`optional	Reasoning depth: minimal, low, medium, high, or max.
`use_assistant_model`	`boolean`optional	Use assistant model for expert analysis after workflow steps. False skips expert analysis, relies solely on your personal investigation. Defaults to True for comprehensive validation.

This tool is read-only. It does not modify its environment.

Tool: `tracer`

Performs systematic code tracing with modes for execution flow or dependency mapping. Use for method execution analysis, call chain tracing, dependency mapping, and architectural understanding. Supports precision mode (execution flow) and dependencies mode (structural relationships).

Parameters	Type	Description
`findings`	`string`	Important findings, evidence and insights discovered in this step
`model`	`string`	Currently in auto model selection mode. CRITICAL: When the user names a model, you MUST use that exact name unless the server rejects it. If no model is provided, you may use the `listmodels` tool to review options and select an appropriate match. Top models: gpt-5.2 (score 100, 400K ctx, thinking, code-gen); gpt-5.1-codex (score 100, 400K ctx, thinking, code-gen); gemini-2.5-pro (score 100, 1.0M ctx, thinking, code-gen); gemini-3-pro-preview (score 100, 1.0M ctx, thinking, code-gen); gpt-5.2-pro (score 100, 400K ctx, thinking, code-gen); +26 more via `listmodels`.
`next_step_required`	`boolean`	Whether another work step is needed. When false, aim to reduce total_steps to match step_number to avoid mismatch.
`step`	`string`	Current work step content and findings from your overall work
`step_number`	`integer`	Current step number in work sequence (starts at 1)
`target_description`	`string`	Description of what to trace and WHY. Include context about what you're trying to understand or analyze.
`total_steps`	`integer`	Estimated total steps needed to complete work
`trace_mode`	`string`	Type of tracing: 'ask' (default - prompts user to choose mode), 'precision' (execution flow) or 'dependencies' (structural relationships)
`confidence`	`string`optional	Confidence level: exploring (just starting), low (early investigation), medium (some evidence), high (strong evidence), very_high (comprehensive understanding), almost_certain (near complete confidence), certain (100% confidence locally - no external validation needed)
`continuation_id`	`string`optional	Unique thread continuation ID for multi-turn conversations. Works across different tools. ALWAYS reuse the last continuation_id you were given—this preserves full conversation context, files, and findings so the agent can resume seamlessly.
`files_checked`	`array`optional	List of files examined during this work step
`images`	`array`optional	Optional paths to architecture diagrams or flow charts that help understand the tracing context.
`relevant_context`	`array`optional	Methods/functions identified as involved in the issue
`relevant_files`	`array`optional	Files identified as relevant to issue/goal (FULL absolute paths to real files/folders - DO NOT SHORTEN)
`use_assistant_model`	`boolean`optional	Use assistant model for expert analysis after workflow steps. False skips expert analysis, relies solely on your personal investigation. Defaults to True for comprehensive validation.

This tool is read-only. It does not modify its environment.

Tool: `version`

Get server version, configuration details, and list of available tools.

Use this MCP Server

{
  "mcpServers": {
    "zen": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "OPENROUTER_API_KEY",
        "-e",
        "GEMINI_API_KEY",
        "-e",
        "OPENAI_API_KEY",
        "-e",
        "XAI_API_KEY",
        "mcp/zen"
      ],
      "env": {
        "OPENROUTER_API_KEY": "sk-or-v1-****",
        "GEMINI_API_KEY": "AIza****",
        "OPENAI_API_KEY": "sk-proj-****",
        "XAI_API_KEY": "xai-****"
      }
    }
  }
}

Why is it safer to run MCP Servers with Docker?⁠

Zen

Zen MCP Server

MCP Info

Image Building Info

Available Tools (18)

Tools Details

Tool: `analyze`

Tool: `apilookup`

Tool: `challenge`

Tool: `chat`

Tool: `clink`

Tool: `codereview`

Tool: `consensus`

Tool: `debug`

Tool: `docgen`

Tool: `listmodels`

Tool: `planner`

Tool: `precommit`

Tool: `refactor`

Tool: `secaudit`

Tool: `testgen`

Tool: `thinkdeep`

Tool: `tracer`

Tool: `version`

Use this MCP Server

Related servers

AWS Core

Desktop Commander

Docker Hub

GitHub Official

Zen

Zen MCP Server

MCP Info

Image Building Info

Available Tools (18)

Tools Details

Tool: analyze

Tool: apilookup

Tool: challenge

Tool: chat

Tool: clink

Tool: codereview

Tool: consensus

Tool: debug

Tool: docgen

Tool: listmodels

Tool: planner

Tool: precommit

Tool: refactor

Tool: secaudit

Tool: testgen

Tool: thinkdeep

Tool: tracer

Tool: version

Use this MCP Server

Related servers

AWS Core

Desktop Commander

Docker Hub

GitHub Official

Tool: `analyze`

Tool: `apilookup`

Tool: `challenge`

Tool: `chat`

Tool: `clink`

Tool: `codereview`

Tool: `consensus`

Tool: `debug`

Tool: `docgen`

Tool: `listmodels`

Tool: `planner`

Tool: `precommit`

Tool: `refactor`

Tool: `secaudit`

Tool: `testgen`

Tool: `thinkdeep`

Tool: `tracer`

Tool: `version`