Program Integrity Alliance

Program Integrity Alliance MCP Server

An MCP server to help make U.S. Government open datasets AI-friendly.

What is an MCP Server?⁠

MCP Info

Image Building Info

Attribute	Details
Dockerfile	https://github.com/Program-Integrity-Alliance/pia-mcp-local/blob/f10cab6874a341c79aedbcba9bab6df7e1313069/Dockerfile⁠
Commit	f10cab6874a341c79aedbcba9bab6df7e1313069
Docker Image built by	Docker Inc.
Docker Scout Health Score
Verify Signature	COSIGN_REPOSITORY=mcp/signatures cosign verify mcp/pia --key https://raw.githubusercontent.com/docker/keyring/refs/heads/main/public/mcp/latest.pub
Licence	MIT License

Available Tools (2)

Tools Details

Tool: pia_oversight_recommendations

Search oversight recommendations (Open Recommendations dataset) with facets enabled by default. Today's date is 2026-06-25. This dataset contains recommendations from GAO and Oversight.gov only — SourceDocumentDataSource filters for any other source will be ignored. Do NOT filter by SourceDocumentDataSet — this tool already targets the 'Open Recommendations' dataset automatically. IMPORTANT: When a text query is provided, do NOT add a referenced_agencies filter — the query handles relevance matching. Only use referenced_agencies when the query is empty (pure filter/facet lookups). total_count is the number of OPEN recommendations matching the query and all applied filters — report it as that count. The results are a representative sample to summarize, and facets break the set down by status, priority, agency, and theme. Counts from free-text queries are approximate (semantic matching); pure filter or agency lookups are exact. Recommendations have no per-document citations, so it is very important to always include the govquery_url for the full set in Rec Spotlight rather than citing individual rows.

AVAILABLE FIELDS: • SourceDocumentDataSource: Data source/agency that published the document. Major sources (>1k documents): 'Department of Justice', 'Congress.gov', 'Oversight.gov', 'CRS', 'GAO', 'Federal Register' • SourceDocumentDataSet: Dataset or collection the document belongs to. Values include: 'reports', 'federal-reports', 'press-releases', 'executive orders', 'Open Recommendations'. Note: the value is 'Open Recommendations' (not 'recommendations'). Values: 'press-releases', 'bills-and-laws', 'reports', 'federal-reports', 'executive orders', 'state-and-local-reports', 'annual-financial-reports', 'congressional-justification-reports', 'performance-and-accountability-reports' • SourceDocumentTitle: Document title - use contains, eq for text matching • SourceDocumentPublishDate: Publication date - ISO 8601 format YYYY-MM-DD (e.g., '2023-01-01'). Use ge/le for ranges • RecStatus: Recommendation status • RecPriorityFlag: Priority flag for recommendations • SourceDocumentIsRecDoc: Whether the document contains recommendations. Values: 'No', 'Yes' • RecFraudRiskManagementThemePIA: Fraud risk management theme classification • RecMatterForCongressPIA: Whether the matter is for Congressional attention • RecRecommendation: Recommendation text - use contains, eq for text matching • RecAgencyComments: Agency comments on recommendations - use contains, eq for text matching • referenced_agencies: Agencies referenced by documents (collection field). IMPORTANT: Only use this filter when the query is empty (pure filter/facet lookups). Do NOT combine with a text query — the query already handles relevance matching. Example: (referenced_agencies/any(a: a eq 'Department of Defense (DOD)') or referenced_agencies/any(a: a eq 'Department of Justice (DOJ)')) - for single agency omit outer parentheses and 'or'. Get all values via pia_search with facets_only=true.

OPERATORS: • Text: contains, eq, ne, startswith, endswith • Exact: eq (equals), ne (not equals), in (in list) • Date: ge (greater/equal), le (less/equal), eq (equals) • Logic: and, or, not, parentheses for grouping

EXAMPLES: • "SourceDocumentDataSource eq 'GAO'" • "SourceDocumentDataSource eq 'GAO' and RecStatus ne 'Closed'" • "(SourceDocumentDataSource eq 'GAO' or SourceDocumentDataSource eq 'OIG') and RecStatus eq 'Open'" • "SourceDocumentPublishDate ge '2020-01-01' and SourceDocumentPublishDate le '2024-12-31'"

TIP: Use pia_search with facets_only=true to get the most current available values.

COMMON AGENCY NAMES (use EXACT spelling for referenced_agencies): Department of Defense (DOD), Department of Health and Human Services (HHS), Department of Homeland Security (DHS), Department of Justice (DOJ), Department of Education (ED), Department of Veterans Affairs (VA), Department of the Treasury, Department of Agriculture (USDA), Department of the Interior (DOI), Department of Transportation (DOT), Department of Energy (DOE), Department of State, Department of Labor (DOL), Department of Commerce (DOC), Department of Housing and Urban Development (HUD), Environmental Protection Agency (EPA), National Aeronautics and Space Administration (NASA), Social Security Administration (SSA), Small Business Administration (SBA), Office of Personnel Management (OPM), General Services Administration (GSA) include_facets|booleanoptional|Include facets in results (default: true) limit|integeroptional|Maximum results limit page|integeroptional|Page number (default: 1) page_size|integeroptional|Results per page (default: 100) search_mode|stringoptional|Search mode (default: content)

Tool: pia_search

Search the Program Integrity Alliance (PIA) database of government oversight reports, recommendations, executive orders, legislation, and integrity data (GAO, OIG/Oversight.gov, CRS, DOJ, Congress.gov, Federal Register). One tool for all document search: scope by source/dataset/agency/date via filter, choose content vs titles via search_mode, sweep every source with wide, or discover filter values with facets_only. WHAT THE COUNTS MEAN: in 'content' mode (default) total_count and facet counts are TEXT CHUNKS / EXCERPTS — a single document is split into many chunks, so these counts are much larger than the number of documents and must NOT be reported as a document/report/article count. In 'titles' mode the counts are whole DOCUMENTS / ARTICLES. Use search_mode='titles' whenever the user asks how many documents, reports, or articles there are. Citations are very important to PIA users, so it is strongly expected that your answer: (1) gives every factual claim at least one clickable inline citation in the form [1]⁠, numbered sequentially from 1; (2) ends with a References section listing every source you cited, each reference on its own line (never multiple references on one line) — omit this section only for a pure count or summary with nothing specific to cite; and (3) includes a Find Out More section with the govquery_url so the user can open the full result set. Please do not present findings from these results without their inline citations and References section. Counts from free-text queries are approximate, because semantic search matches variations of the search terms.

Use this MCP Server

{
  "mcpServers": {
    "pia": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "PIA_API_KEY",
        "mcp/pia"
      ],
      "env": {
        "PIA_API_KEY": "pia_5cFd9jtG3zbY4VpREewTP17uzdfnvMt8_3m778O2dv8"
      }
    }
  }
}

Why is it safer to run MCP Servers with Docker?⁠