Skip to content

Conversation

@dividor
Copy link
Contributor

@dividor dividor commented Aug 20, 2025

Description

The Program Integrity Alliance (PIA) aims to make working with U.S. Government datasets easier and AI-friendly. We have ingested hundreds of thousands of documents and articles across a range of sources, and this list is growing. This MCP server enables AIs to search this data at a more detailed level than on most source websites, for example, searching within PDF reports to find the exact pages where text and images appear.

Full attribution is given to the amazing open federal data sources, and all links in the data provided by PIA will always direct back to the original source.

Currently, the list of datasets includes:

  • U.S. Government Accountability Office (GAO) - 10k Federal Reports since 2010 and 5.5k Open Oversight Recommendations
  • Oversight.gov - 28k OIG Federal Reports since 2010, and 29k Open Oversight Recommendations
  • U.S. Congress - Bill texts for sessions 118 and 119
    Department of Justice (DOJ) - 195k Press Releases since 2000
  • Federal Agency annual reports - Congressional Justification, Financial Report, Performance Report - 139 reports across 10 priority agencies, with best coverage in 2024.

This data is updated weekly, and we will be adding more datasets and tools soon.

Server Details

  • Server: filesystem connecting to hosted

Motivation and Context

PIA ingests, combines and augments U.S. Open datasets, with the aim of making them easier to use for AI.

How Has This Been Tested?

The MCP server is live and already in use, is also reviewed and available on Docker MCP Catalog. See also testing in repo.

Breaking Changes

Will users need to update their MCP client configurations?
No, this is a new server, only mentiopned in README.

Types of changes

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to change)
  • Documentation update

Checklist

  • I have read the MCP Protocol Documentation
  • My changes follows MCP security best practices
  • I have updated the server's README accordingly
  • I have tested this with an LLM client
  • My code follows the repository's style guidelines
  • New and existing tests pass locally
  • I have added appropriate error handling
  • I have documented all environment variables and configuration options

Additional context

This is a submission of a new approved MCP server

@olaservo olaservo merged commit 5326822 into modelcontextprotocol:main Aug 22, 2025
19 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants