{
  "markdown": "# @pipeworx/committee-releases\n\nDocuments congressional committees publish on their **own** websites — press releases, oversight letters, staff reports, released interview transcripts and investigation files. Keyless.\n\nPart of [Pipeworx](https://pipeworx.io) — an MCP gateway connecting AI agents to 1476+ live data sources.\n\n## Tools\n\n- `search_committee_documents(...)` — find documents by headline across seven committees, filtered by `committee`, `doc_type` and (where dates exist) `since`.\n- `get_committee_document(...)` — a document page's headline, publication date, published text and attached PDFs with URLs and sizes.\n- `list_committee_document_types(...)` — which committees are covered and what each publishes.\n\n## Auth\n\nNone.\n\n## Why this exists\n\n`congressional-documents` covers GovInfo — the official printed record, which lags the event by months and never receives the ad-hoc material a committee posts to its own site. This covers that gap, within hours of publication.\n\n## Committees covered\n\n| Committee | Chamber | Shape | Dates |\n|---|---|---|---|\n| `house-oversight` | House | typed | yes |\n| `hsgac` | Senate | typed | yes |\n| `senate-commerce` | Senate | typed | yes |\n| `senate-judiciary` | Senate | flat | **no** |\n| `senate-foreign-relations` | Senate | flat | **no** |\n| `senate-help` | Senate | flat | **no** |\n| `senate-aging` | Senate | flat | **no** |\n\n~40,600 documents indexed. All 30 major House and Senate committees were surveyed on 2026-07-30: **most House committees publish no sitemap at all**, so they cannot be added without a new adapter.\n\n**`flat` committees publish a sitemap with no dates.** Their results carry `last_updated: null`, sort alphabetically rather than by recency, and **refuse `since`** instead of applying it to undated rows — which would return pre-cutoff documents as though they had passed the filter. The response says so via `dates_unavailable`.\n\nNot every committee publishes every type. A `doc_type` a committee does not publish returns an explicit `unavailable_types` and a note, never an empty list that would read as \"nothing on the subject\".\n\n## Coverage and limits\n\n- **Search matches the document headline/slug, not body or PDF text.** Searching 40,000 pages of body text needs full-text indexing. A null result means no headline matched — not that the subject is absent.\n- **PDF text is not extracted.** Attachments come back as url + filename + bytes. Quote the page text and cite the attachment as a link; do not represent a PDF as having been read.\n- Some pages are pure file wrappers with no prose of their own; those return empty text plus a `no_prose_note` rather than the site footer.\n- `get_committee_document` fetches a caller-supplied URL, so it is **host-allowlisted** to the seven committee domains.\n\n## A deliberate omission\n\nNo person→mentions tool, for the reasons set out in `congressional-documents`: a name is not an identifier, and being named in a committee document is not an allegation.\n\n## Data sources\n\nEach committee's Yoast sitemap index or `sitemap.xml`, e.g.:\n\n- `https://oversight.house.gov/sitemap_index.xml`\n- `https://www.hsgac.senate.gov/sitemap_index.xml`\n- `https://www.judiciary.senate.gov/sitemap.xml`\n\nAll are served under a `robots.txt` with an empty `Disallow:` — crawling explicitly permitted.\n\n## Quick Start\n\nAdd to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):\n\n```json\n{\n  \"mcpServers\": {\n    \"committee-releases\": {\n      \"url\": \"https://gateway.pipeworx.io/committee-releases/mcp\"\n    }\n  }\n}\n```\n\n### What this endpoint actually serves\n\n`tools/list` at `https://gateway.pipeworx.io/committee-releases/mcp` returns the tools in the table\nabove **plus the shared Pipeworx meta-tools** — `ask_pipeworx`,\n`discover_tools`, `search_within`, `remember`/`recall` and the rest of the\ngateway-wide set. So the tool count you see is larger than this table: a\nsingle-pack endpoint currently lists roughly 30 shared tools alongside the\npack's own. The connection's `initialize` response states its exact scope, and\nis the authoritative answer for a given day.\n\nThis is deliberate, not multiplexing by accident. The meta-tools are what let a\nscoped connection answer a question this pack does not cover — via\n`ask_pipeworx`, which routes across the whole catalog — without you adding a\nsecond MCP server. There is currently no way to mount a pack endpoint without\nthem; if the extra schemas cost you more context than the routing is worth,\nconnect to the full gateway once rather than to several pack endpoints.\n\nOr connect to the full Pipeworx gateway to get every pack's tools listed\ndirectly, instead of just this one's:\n\n```json\n{\n  \"mcpServers\": {\n    \"pipeworx\": {\n      \"url\": \"https://gateway.pipeworx.io/mcp\"\n    }\n  }\n}\n```\n\nBoth URLs reach the same gateway and the same 1476+ data sources. The\nonly difference is which pack's tools are listed **directly**; `ask_pipeworx`\nreaches all of them from either one.\n\n## Using with ask_pipeworx\n\nInstead of calling tools directly, you can ask questions in plain English —\nthis works on the pack endpoint above as well as on the full gateway:\n\n```\nask_pipeworx({ question: \"your question about Committee Releases data\" })\n```\n\nThe gateway picks the right tool and fills the arguments automatically.\n\n## More\n\n- [Docs and guides](https://pipeworx.io/docs)\n- [pipeworx.io](https://pipeworx.io)\n\n## License\n\nMIT\n",
  "bytes": 5385,
  "sha": "29563e6fb5d72132248e9437aebd3e45cd69276c85e114367c28538479e09c68",
  "repo_slug": "pipeworx-io/mcp-committee-releases",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_pipeworx_io_committee_releases_97ea19d8/readme"
}