The Official Model Context Protocol (MCP) server for Kagi search & other tools.
2.4K
2 Tools
Version 4.43 or later needs to be installed to add the server automatically
Use cases
About
The Official Model Context Protocol (MCP) server for Kagi search & other tools.
Attribute | Details |
---|---|
Docker Image | mcp/kagisearch |
Author | kagisearch |
Repository | https://github.com/kagisearch/kagimcp |
Dockerfile | https://github.com/kagisearch/kagimcp/blob/main/Dockerfile |
Docker Image built by | Docker Inc. |
Docker Scout Health Score | |
Verify Signature | COSIGN_REPOSITORY=mcp/signatures cosign verify mcp/kagisearch --key https://raw.githubusercontent.com/docker/keyring/refs/heads/main/public/mcp/latest.pub |
Licence | MIT License |
Tools provided by this Server | Short Description |
---|---|
kagi_search_fetch | Fetch web results based on one or more queries using the Kagi Search API. |
kagi_summarizer | Summarize content from a URL using the Kagi Summarizer API. |
kagi_search_fetch
Fetch web results based on one or more queries using the Kagi Search API. Use for general search and when the user explicitly tells you to 'fetch' results/information. Results are from all queries given. They are numbered continuously, so that a user may be able to refer to a result by a specific number.
Parameters | Type | Description |
---|---|---|
queries | array | One or more concise, keyword-focused search queries. Include essential context within each query for standalone use. |
kagi_summarizer
Summarize content from a URL using the Kagi Summarizer API. The Summarizer can summarize any document type (text webpage, video, audio, etc.)
Parameters | Type | Description |
---|---|---|
url | string | A URL to a document to summarize. |
summary_type | string optional | Type of summary to produce. Options are 'summary' for paragraph prose and 'takeaway' for a bulleted list of key points. |
target_language | string optional | Desired output language using language codes (e.g., 'EN' for English). If not specified, the document's original language influences the output. |
{
"mcpServers": {
"kagisearch": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"KAGI_SUMMARIZER_ENGINE",
"-e",
"KAGI_API_KEY",
"mcp/kagisearch"
],
"env": {
"KAGI_SUMMARIZER_ENGINE": "cecil",
"KAGI_API_KEY": "YOUR_API_KEY_HERE"
}
}
}
}
Manual installation
You can install the MCP server using:
Installation for