University AI Policy Tracker

Open, evidence-backed AI policy records for public reuse.

API docsGitHub repo

MCP alpha

Read-only agent access design

The first MCP surface is intentionally read-only. It should help agents answer citation-backed questions from public records, but it must not mutate records, write the production database, publish canonical claims, push main, operate OpenClaw, or bypass review state.

MCP manifest

Machine-readable manifest for the alpha MCP design.

Read-only tools

Allowed tool shapes map directly to existing public JSON endpoints.

uapt.get_api_index

Read public endpoint, trust page, limitation, and citation metadata.

MethodGETPath/api/public/v1/index.json

uapt.list_universities

Read the public university record list. Client-side filtering is expected in the alpha design.

MethodGETPath/api/public/v1/universities.json

uapt.get_university_policy

Read one citation-ready university record with claims, evidence, source URLs, review states, and caveats.

MethodGETPath/api/public/v1/universities/{slug}.json

uapt.get_recent_changes

Read recent public source checks and changed institution records.

MethodGETPath/api/public/v1/recent-changes.json

uapt.get_dataset_release

Read the latest dataset release manifest, artifacts, checksums, and citation fields.

MethodGETPath/api/public/v1/datasets/latest.json

Prohibited actions

The MCP layer must keep publication authority inside the reviewed dataset workflow.

  • No writes to the production database.
  • No publishing canonical claims or changing review state.
  • No pushing to `main` or bypassing pull request review.
  • No OpenClaw operation, crawling, login bypass, paywall bypass, or robots bypass.
  • No legal advice or academic integrity advice.
  • No write tools for institution corrections or course submissions in the alpha MCP surface.

Example agent queries

These examples define the intended retrieval behavior for future MCP implementation.

  • Find universities whose public AI policy records mention approved AI tools, and include review state and source URL for each answer.
  • Summarize the latest checked record for Massachusetts Institute of Technology, but separate reviewed claims from needs-review claims.
  • List recent university AI policy records that changed this month and provide canonical page URLs plus public JSON URLs.
  • Compare Harvard and Stanford policy metadata, using only source-backed public claims and preserving original evidence language.
  • Generate a citation for the latest dataset release and include the release manifest URL.

Response requirements

Every MCP answer should be usable as a citation trail.

  • Return canonical page URLs and public JSON URLs with answers.
  • Return review state next to any summarized claim.
  • Return source URLs and source snapshot hashes for claim evidence.
  • Preserve source-language evidence as canonical evidence.
  • Label candidate or needs-review records clearly.