io.github.cyanheads/congressgov-mcp-server

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Access U.S. congressional data (bills, votes, members, committees) via MCP.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "congressgov-mcp-server": {
      "url": "https://congressgov.caseyjhand.com/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (10)

• congressgov_bill_lookup read-only

  Browse and retrieve U.S. legislative bill data from Congress.gov. Discover bills by filtering on congress, bill type, and date range — there is no keyword search. Use 'list' to browse (requires congress, defaults to most-recently-updated first), 'get' for full bill detail (sponsor, policy area, CBO estimates, law info), or drill into a specific bill with 'actions', 'amendments', 'cosponsors', 'committees', 'subjects', 'summaries', 'text', 'titles', or 'related' (each requires congress + billType + billNumber). 'text' lists the published versions and their format URLs; 'content' then reads one version's actual text, a bounded character window at a time. 'summaries' takes an optional versionCode selector and returns each row's text a bounded character window at a time — a row past the window carries textTotalCharacters/textTruncated/textNextOffset, and characterOffset reads on from there.

  Parameters:

  • operation (required) — string — Which data to retrieve.
  • congress (required) — integer — Congress number (e.g., 118, 119).
  • limit — integer — Results per page (1-250).
  • order — string — Sort order for 'list' (sorts by update date). 'recent' (default) is newest first; 'oldest' is ascending. Ignored by other operations.
  • format — string — Document format for 'content'. 'text' is GPO's Formatted Text — plain, pre-formatted print output, published for every document checked. 'xml' prefers United States Legislative Markup and falls back to Formatted XML; it exists on some bill text versions and on no committee report or Congressional Record article. PDF is not retrieved — read one at the format URLs 'text'/'articles' return.
  • offset — integer — Pagination offset.
  • billType — string — Bill type code. Required for get and sub-resource operations.
  • billNumber — Bill number. Required for get and sub-resource operations. Accepts the digit-string form list rows carry (e.g. "9479") as well as a number.
  • toDateTime — string — End of date range filter (ISO 8601). Same field semantics as fromDateTime.
  • versionCode — string — Which summary version 'summaries' returns — the versionCode a summary row carries ('00' introduced, '49' public law). Selection runs over the bill's whole summary list, which Congress.gov publishes no filter for, and limit/offset then page the matching rows. Omit to return every version. Ignored by other operations.
  • fromDateTime — string — Start of date range filter (ISO 8601). Filters by the bill's update date — when Congress.gov last touched the record — not by the bill's latest legislative action.
  • characterLimit — integer — Maximum characters to return (1-100000) — for the document window on 'content', and for each row's summary text on 'summaries'. Legislative documents run past a million characters and an enacted bill's summary past two hundred thousand, so either takes several windows.
  • characterOffset — integer — First character to return, 0-based — of the document on 'content', and of every returned row's summary text on 'summaries'. Offsets are exact and are never snapped to a section or paragraph break, so feeding back the response's nextOffset (or a summary row's textNextOffset) walks the whole text with every character returned exactly once.
  • textVersionIndex — integer — Which text version 'content' reads, 0-based against the same order 'text' returns — 0 is the most recent version. Ignored by other operations.

  Hints: read-only yes · destructive not declared · idempotent yes · open-world yes

• congressgov_enacted_laws read-only

  Browse enacted public and private laws from Congress.gov by congress and law type ('pub' for public laws, 'priv' for private). 'list' filters by enactment status and law type — the discovery path 'bill_lookup' does not offer. 'get' returns the origin bill record (sponsor, actions, summaries, text), with the public/private law citation on the bill's 'laws' array (e.g. {"number":"118-2","type":"Public Law"}).

  Parameters:

  • operation (required) — string — Which data to retrieve.
  • congress (required) — integer — Congress number.
  • limit — integer — Results per page (1-250).
  • offset — integer — Pagination offset.
  • lawType — string — Law type — 'pub' (public laws, general application, most common) or 'priv' (private laws, specific individuals or entities). Required for 'get'.
  • lawNumber — Law number, as carried by a 'list' row's `laws[].number` — either the full citation ('118-90', rendered as 'Public Law 118-90') or the portion after the hyphen ('90'); the prefix is the congress and must match `congress`. Not the row's own `number`, which is the origin bill. Required for 'get'.

  Hints: read-only yes · destructive not declared · idempotent yes · open-world yes

• congressgov_member_lookup read-only

  Discover congressional members and their legislative activity. No name search. For 'list', filter by stateCode (optionally with district), by congress, or by both together (e.g., 118th Congress + CA, or CA district 12 in the 118th). Add currentMember=true to restrict to currently serving members. Once you have a bioguideId, use 'get' for full profile or 'sponsored'/'cosponsored' for their legislative portfolio.

  Parameters:

  • operation (required) — string — Which data to retrieve.
  • limit — integer — Results per page (1-250).
  • offset — integer — Pagination offset.
  • congress — integer — Congress number to filter by.
  • district — integer — Congressional district number. Requires stateCode. Use 0 for at-large.
  • stateCode — string — Two-letter state code (e.g., 'CA', 'TX').
  • bioguideId — string — Unique member identifier (e.g., 'P000197'). Required for get/sponsored/cosponsored.
  • currentMember — boolean — Filter to currently serving members. Omit to include both current and former members.

  Hints: read-only yes · destructive not declared · idempotent yes · open-world yes

• congressgov_committee_lookup read-only

  Browse congressional committees and their legislation, reports, and nominations. Committee codes follow the pattern chamber-prefix (h/s/j) + abbreviation + 2-digit number — use 'list' (with optional 'filter' for name→code resolution) to discover codes, then 'get' or drill into 'bills', 'reports', or 'nominations' ('nominations' is Senate-only). 'get' and sub-resources only need committeeCode (chamber is inferred from the prefix); pass chamber explicitly to override. The 'bills' sub-resource defaults to 'recent' order (newest update-date first); pass order='oldest' for ascending update-date order. Upstream omits bill titles from the 'bills' sub-resource — rows carry only {congress, billType, billNumber, actionDate, relationshipType, url}; chain 'congressgov_bill_lookup get' per row to retrieve titles and policy area.

  Parameters:

  • operation (required) — string — Which data to retrieve.
  • limit — integer — Results per page (1-250).
  • order — string — Sort order for the 'bills' sub-resource. 'recent' (default) returns newest update-date first; 'oldest' returns ascending update-date order. Ignored by other operations.
  • filter — string — Filter committee-list results by name (e.g., 'transportation', 'armed services'). Only meaningful for 'list'; fuzzy-matched rows are labeled approximate.
  • offset — integer — Pagination offset.
  • chamber — string — Chamber filter for 'list', or override for 'get' and sub-resources (otherwise inferred from committeeCode prefix).
  • congress — integer — Congress number.
  • committeeCode — string — Committee system code, e.g. 'hsju00'. Required for 'get' and sub-resources. Codes are letters + a 2-digit suffix and are matched case-insensitively. Any other non-blank value is treated as a committee name and resolved automatically — single-word names ('Judiciary') included — or use operation:'list' with filter to browse.

  Hints: read-only yes · destructive not declared · idempotent yes · open-world yes

• congressgov_roll_votes read-only

  Retrieve U.S. congressional roll call votes and individual member voting positions for either chamber. Set 'chamber' to 'house' (default, from the Congress.gov API) or 'senate' (from the Senate's official LIS feed). Use 'list' to find votes by congress and session (newest first by default), 'get' for vote details (question, result, tallies, party breakdown, associated bill/nomination/amendment), or 'members' for how each member voted.

  Parameters:

  • operation (required) — string — Which data to retrieve.
  • congress (required) — integer — Congress number.
  • session (required) — integer — Session number (1 or 2). Odd years are session 1, even years session 2.
  • limit — integer — Results per page (1-250).
  • order — string — Sort order for 'list'. 'recent' (default) returns newest first; 'oldest' returns ascending. House sorts by vote update date (with 'recent', offset=0 always returns the strictly newest page); Senate sorts by roll call number. Ignored by 'get' and 'members'.
  • offset — integer — Pagination offset.
  • chamber — string — Chamber whose votes to query. 'house' (default) draws from the Congress.gov API; 'senate' draws from the Senate's official LIS roll-call feed. Roll call numbers reset each session and are specific to one chamber.
  • voteNumber — integer — Roll call vote number. Required for 'get' and 'members'.

  Hints: read-only yes · destructive not declared · idempotent yes · open-world yes

• congressgov_senate_nominations read-only

  Browse presidential nominations to federal positions and track the Senate confirmation process. Use 'list' to browse, 'get' for nomination detail, 'actions'/'committees'/'hearings' for confirmation pipeline data, or 'nominees' to retrieve individual appointees in a multi-nominee batch. Nominations use 'PN' (Presidential Nomination) numbering. Most nominations carry confirmation activity on the parent (e.g., PN1000); multi-part parents (e.g., PN851) carry no activity of their own — their actions, committees, hearings, and nominees live on partitioned children (PN851-1, PN851-2, …). 'get' on a parent that has no `nominees` array signals the partitioned form is needed for everything below it.

  Parameters:

  • operation (required) — string — Which data to retrieve.
  • congress (required) — integer — Congress number.
  • limit — integer — Results per page (1-250).
  • offset — integer — Pagination offset.
  • ordinal — integer — Batch ordinal within a multi-nominee nomination. Each ordinal addresses a group of nominees; the 'nominees' operation returns every individual in that batch. Use 'get' first to see available ordinals on the nomination's `nominees` array (multi-part parents have no nominees array — use a partitioned form like '851-1' instead).
  • nominationNumber — string — Nomination number. Use the bare form (e.g. '1000') for nominations whose activity sits on the parent; use the partitioned form (e.g. '851-1') for sub-resources of a multi-part nomination. Required for detail operations.

  Hints: read-only yes · destructive not declared · idempotent yes · open-world yes

• congressgov_bill_summaries read-only

  Browse recent CRS (Congressional Research Service) bill summaries — plain-language summaries of bills at each legislative stage, useful for answering "what's happening in Congress?". The fromDateTime/toDateTime filters apply to the summary's update time, not the bill's action date, so results include recently rewritten summaries of older bills. Defaults to summaries updated in the last 7 days. Each item shows both the bill's action date and the summary update date. A page stops adding rows once it reaches a fixed response-character budget, and a summary longer than the per-row window arrives as an exact character window carrying textTotalCharacters/textTruncated/textNextOffset; pagination.nextOffset continues the page and a row's textNextOffset continues its text. For summaries of one specific bill — and to read a windowed summary to the end — use congressgov_bill_lookup with operation='summaries' instead.

  Parameters:

  • limit — integer — Results per page (1-250).
  • offset — integer — Pagination offset.
  • billType — string — Bill type filter. Requires 'congress'.
  • congress — integer — Congress number. Optional — omit for summaries across all congresses.
  • toDateTime — string — End of date range (ISO 8601), filtered on the summary update time. Defaults to now.
  • fromDateTime — string — Start of date range (ISO 8601), filtered on the summary update time. Defaults to 7 days ago if neither date param is set.

  Hints: read-only yes · destructive not declared · idempotent yes · open-world yes

• congressgov_crs_reports read-only

  Browse and retrieve CRS (Congressional Research Service) reports — nonpartisan policy analyses by subject-matter experts at the Library of Congress, covering policy areas, legislative proposals, and legal questions. Report IDs use letter-number codes (e.g., R40097, RL33612, IF12345). Use 'list' to browse available reports or 'get' for full detail (authors, topics, summary, download formats).

  Parameters:

  • operation (required) — string — Which data to retrieve.
  • limit — integer — Results per page (1-250).
  • offset — integer — Pagination offset.
  • reportNumber — string — CRS report ID (e.g., 'R40097'). Required for 'get'.

  Hints: read-only yes · destructive not declared · idempotent yes · open-world yes

• congressgov_committee_reports read-only

  Browse and retrieve committee reports from Congress.gov — reports accompany legislation reported out of committee and explain the bill's purpose, committee amendments, dissenting views, and the committee vote. Report types are 'hrpt' (House), 'srpt' (Senate), and 'erpt' (Executive). 'text' lists the published format URLs; 'content' then reads the report's actual text, a bounded character window at a time.

  Parameters:

  • operation (required) — string — Which data to retrieve.
  • congress (required) — integer — Congress number.
  • limit — integer — Results per page (1-250).
  • format — string — Document format for 'content'. 'text' is GPO's Formatted Text — plain, pre-formatted print output, published for every document checked. 'xml' prefers United States Legislative Markup and falls back to Formatted XML; it exists on some bill text versions and on no committee report or Congressional Record article. PDF is not retrieved — read one at the format URLs 'text'/'articles' return.
  • offset — integer — Pagination offset.
  • reportType — string — Report type. Required for get, text, and content operations.
  • reportNumber — integer — Committee report number. Required for get, text, and content operations.
  • characterLimit — integer — Maximum characters to return for 'content' (1-100000). Legislative documents run past a million characters, so a full bill takes several windows.
  • characterOffset — integer — First character to return for 'content', 0-based. Offsets are exact and are never snapped to a section or paragraph break, so feeding the response's nextOffset back walks the whole document with every character returned exactly once.

  Hints: read-only yes · destructive not declared · idempotent yes · open-world yes

• congressgov_daily_record read-only

  Browse the daily Congressional Record — floor speeches, debates, and legislative text published each day Congress is in session. Navigation is hierarchical: volumes (via 'list') → issues (via 'issues') → articles (via 'articles'). Use 'list' to find recent volumes, 'issues' to see what's in a volume, and 'articles' to access individual speeches and debate sections. 'articles' lists each article and its format URLs; 'content' then reads one article's actual text, a bounded character window at a time.

  Parameters:

  • operation (required) — string — Which data to retrieve.
  • limit — integer — Results per page (1-250).
  • format — string — Document format for 'content'. 'text' is GPO's Formatted Text — plain, pre-formatted print output, published for every document checked. 'xml' prefers United States Legislative Markup and falls back to Formatted XML; it exists on some bill text versions and on no committee report or Congressional Record article. PDF is not retrieved — read one at the format URLs 'text'/'articles' return.
  • offset — integer — Pagination offset.
  • issueNumber — Issue number within a volume. Required for 'articles' and 'content'. List rows carry this as a string (e.g. "109") — both forms are accepted.
  • articleIndex — integer — Which article 'content' reads, 0-based against the issue's whole article sequence — the same absolute position 'articles' pages through with offset. Ignored by other operations.
  • volumeNumber — Volume number. Required for 'issues', 'articles', and 'content'. Accepts a number or the digit-string form list rows carry.
  • characterLimit — integer — Maximum characters to return for 'content' (1-100000). Legislative documents run past a million characters, so a full bill takes several windows.
  • characterOffset — integer — First character to return for 'content', 0-based. Offsets are exact and are never snapped to a section or paragraph break, so feeding the response's nextOffset back walks the whole document with every character returned exactly once.

  Hints: read-only yes · destructive not declared · idempotent yes · open-world yes

Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.