fetch
ChatGPTRetrieve the full contents of a specific document from the PIA database using its unique identifier. This endpoint is one of the supported for OpenAI's MCP spec when integrating ChatGPT Connectors.
Productivity
Overview
GovQuery is a powerful search engine that makes U.S. government reports and data easier to explore, locate, and understand. Built by the Program Integrity Alliance, GovQuery processes over 300,000 articles, reports, and oversight recommendations to make them more digestible for AI platforms — offering deeper, more targeted search than general-purpose engines. Every result links to the exact page where content appears, and you can filter by granular categories unavailable on the source platforms. Data sources currently include: - Reports from the Government Accountability Office (GAO), federal inspectors general (Oversight.gov), and the Congressional Research Service (CRS) - Department of Justice press releases - Executive orders (last six presidents) - Annual federal CJ/AFR/PAR agency reports (since 2019 for Chief Financial Officers (CFO) Act of 1990) GovQuery also includes all open oversight recommendations from the GAO and federal inspectors general (Oversight.gov), with tools to analyze them by category and track trends over time. New data sources are added regularly. You can register for a free account at: https://www.programintegrity.org (click on the person icon top-right) For more information on GovQuery data, please see our FAQ (https://www.programintegrity.org/faq).
Tools
fetch
ChatGPTRetrieve the full contents of a specific document from the PIA database using its unique identifier. This endpoint is one of the supported for OpenAI's MCP spec when integrating ChatGPT Connectors.
pia_oversight_recommendations
ChatGPTSearch oversight recommendations (Open Recommendations dataset) with facets enabled by default. Today's date is 2026-06-22. 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). IMPORTANT — your response MUST: 1) Cite
total_count as the number of OPEN recommendations matching the query AND every filter clause. 2) Summarize the recommendations in results; you MAY break the set down using facets (status, priority, agency, theme, …). 3) Caveat totals from TEXT queries: semantic matching is approximate; pure filter/agency lookups are exact. 4) ALWAYS include a Find Out More section linking the govquery_url so the user can open the full set in Rec Spotlight. Recommendations have NO per-document citations — do NOT fabricate [[N]](url) citations or a References section; direct users to Rec Spotlight via govquery_url.pia_oversight_recommendations
ChatGPTSearch oversight recommendations (Open Recommendations dataset) with facets enabled by default. Today's date is 2026-06-22. 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). IMPORTANT — your response MUST: 1) Cite
total_count as the number of OPEN recommendations matching the query AND every filter clause. 2) Summarize the recommendations in results; you MAY break the set down using facets (status, priority, agency, theme, …). 3) Caveat totals from TEXT queries: semantic matching is approximate; pure filter/agency lookups are exact. 4) ALWAYS include a Find Out More section linking the govquery_url so the user can open the full set in Rec Spotlight. Recommendations have NO per-document citations — do NOT fabricate [[N]](url) citations or a References section; direct users to Rec Spotlight via govquery_url.pia_search
ChatGPTSearch 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. IMPORTANT — your response MUST include: 1) Every factual claim MUST have at least one clickable inline citation [[1]](url) — renumber sequentially from 1. 2) A References section (each ref on its OWN line) for every item you cited — omit ONLY for rec count/summary questions. 3) A Find Out More section with the
govquery_url so the user can view results directly. 4) Caveat any totals from text queries: semantic search matches variations, so counts are approximate. Do NOT omit the Find Out More link. Do NOT put multiple references on one line.pia_search
ChatGPTSearch 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. IMPORTANT — your response MUST include: 1) Every factual claim MUST have at least one clickable inline citation [[1]](url) — renumber sequentially from 1. 2) A References section (each ref on its OWN line) for every item you cited — omit ONLY for rec count/summary questions. 3) A Find Out More section with the
govquery_url so the user can view results directly. 4) Caveat any totals from text queries: semantic search matches variations, so counts are approximate. Do NOT omit the Find Out More link. Do NOT put multiple references on one line.search
ChatGPTSearch the Program Integrity Alliance (PIA) database and return a list of potentially relevant search results with titles, snippets, and URLs for citation. This endpoint is one of the supported for OpenAI's MCP spec when integrating ChatGPT Connectors.
search
ChatGPTSearch the Program Integrity Alliance (PIA) database and return a list of potentially relevant search results with titles, snippets, and URLs for citation. This endpoint is one of the supported for OpenAI's MCP spec when integrating ChatGPT Connectors.
Capabilities
Retrievable
Links
App Stats
8
Tools
ChatGPT
Platforms
Category
Knowledge LookupWorks with
ChatGPT
Similar Apps
Data refreshed daily