Comprehensive Model Context Protocol server for managing Home Assistant through AI assistants.
Legislation is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
U.S. bills, roll-call votes, legislators and 2026 elections for all 50 states, D.C. and Congress.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http legislation-mcp https://mcp.delilahusa.com/
# 2 — ask your agent for something these tools do
# search_bills, semantic_search_bills, get_bill and 33 more
Legislation costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http legislation-mcp https://mcp.delilahusa.com/Reconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
36 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Search or list legislation with structured filters (GET /v1/bills). Use this when you know the jurisdiction, sponsor, topic, or status you want. Every filter is optional and they combine with AND. A bill number typed into q (e.g. 'HB 1', 'SB0002') matches that bill directly. Returns bill summaries plus pagination; call get_bill for the full record. Corpus is 2026-forward only. status_id values: 1=
No parameter schema on file.
Vector search over the full text of every bill (GET /v1/search/semantic): describe what you want in plain English — 'protecting kids from social media', 'limits on rent increases' — and get the closest bills with a match_score. Prefer this over search_bills for questions and topics; prefer search_bills for a known bill number, sponsor, or status filter, and keyword_search_bills for exact terms tha
No parameter schema on file.
Fetch a single bill by its numeric bill_id (GET /v1/bills/{bill_id}), optionally merging in sub-resources: votes (roll calls with tallies), sponsors, history (action timeline), texts (version metadata), amendments, subjects, analyses (staff analyses), calendar (scheduled events), citations (statutes the bill touches), referrals (committee referrals), sast (same-as / similar-to companion bills in t
No parameter schema on file.
Compare two versions of a bill's text (GET /v1/bills/{bill_id}/diff): a unified diff plus similarity, added/removed line and character counts, and changed-section highlights. Get the two version ids from get_bill with include:['texts'] — each text row's text_id. Pass them as from (the earlier version) and to (the later version). Diffs are precomputed, so only bills that have more than one te
No parameter schema on file.
Keyword search where EVERY term must appear (GET /v1/search/bills). Use when the user gives specific words that all have to be present, e.g. ['short-term rental', 'tax']. Prefer semantic_search_bills for questions and search_bills for structured filters. Up to 10 terms. Returns bill summaries plus pagination. Corpus is 2026-forward only.
No parameter schema on file.
The cleaned plain text of one bill-text version (GET /v1/texts/{text_id}), entities decoded, ready to quote or summarize. Get text_id from get_bill with include:['texts'] (each version has a date and type). Texts longer than 40,000 characters are clipped with a '[truncated]' marker.
No parameter schema on file.
Timeline of all computed diffs between successive text versions of one bill (GET /v1/bills/{bill_id}/changes): what changed, when, and how much. Use get_bill_diff for one specific pair of versions. Get bill_id from search_bills or semantic_search_bills.
No parameter schema on file.
Search or list legislators (GET /v1/legislators) by jurisdiction, chamber, party, district, or name. This is how you turn a name into the people_id that get_legislator needs. Filters combine with AND.
No parameter schema on file.
Fetch a legislator's profile by people_id (GET /v1/legislators/{people_id}), optionally merging in votes (every roll call they are recorded on, newest first, with their individual position: 1=Yea, 2=Nay, 3=Not Voting, 4=Absent) and bills (legislation they sponsor, with sponsor_type_id 1=primary, 2=cosponsor). Find a people_id with list_legislators or from a bill's sponsors. Corpus is 2026-forward
No parameter schema on file.
Fetch a roll call by roll_call_id (GET /v1/votes/{roll_call_id}): the motion, chamber, date and yea/nay/absent tallies. Add include:['details'] to also pull how every individual member voted (vote_id 1=Yea, 2=Nay, 3=Not Voting, 4=Absent) — this is the tool for 'how did each legislator vote on this'. Get a roll_call_id from get_bill with include:['votes'].
No parameter schema on file.
One-call voting and sponsorship profile for a legislator (GET /v1/legislators/{people_id}/scorecard): participation, party-line alignment, bills sponsored and passed, notable votes. This is the tool for 'how does X vote' or 'is X effective'. Get people_id from list_legislators (q=name).
No parameter schema on file.
List legislative committees (GET /v1/committees), filterable by jurisdiction, chamber, or name search. Returns the committee_id values that get_committee needs.
No parameter schema on file.
Fetch a committee by committee_id (GET /v1/committees/{committee_id}), optionally merging in members (its roster, with roles) and hearings (its scheduled meetings). Find a committee_id with list_committees.
No parameter schema on file.
Scheduled committee hearings across committees (GET /v1/hearings), filterable by jurisdiction and start date. Use this to answer 'what is being heard this week' or to track when a committee next meets. For hearings on one specific committee use get_committee with include:['hearings']; for one specific bill use get_bill with include:['calendar'].
No parameter schema on file.
Near-real-time feed of what changed (GET /v1/changes). Poll with since=<ISO timestamp> to get everything newer than your cursor; with no since it defaults to the last hour. Reason types include NewBill, StatusChange, Text, Vote and Amendment. Use this for monitoring and incremental sync — 'what moved in Florida since yesterday' — rather than re-scanning search_bills.
No parameter schema on file.
The canonical topic taxonomy with per-topic bill counts (GET /v1/topics). Call this first to find the right slug for the topic filter on search_bills, instead of guessing one. Pass a slug to get that topic's detail and a sample of the raw subject names folded into it (GET /v1/topics/{slug}); to get the topic's actual bills, use search_bills with topic=<slug>.
No parameter schema on file.
The raw subject taxonomy with per-subject bill counts (GET /v1/subjects). Subjects are the fine-grained categories the legislatures themselves assign to bills — narrower and more numerous than the curated topic slugs from list_topics. Use this to find a subject_id to filter search_bills by, or to gauge what a jurisdiction is legislating on. Scope with state and narrow with q.
No parameter schema on file.
Legislative sessions (GET /v1/sessions): regular and special sessions with their years, start/sine-die dates and a session_id. Use this to resolve which session a bill belongs to, to find the current session for a state, or to pass session_id as a filter to search_bills. Omit state to list every jurisdiction's sessions. Corpus is 2026-forward only.
No parameter schema on file.
Headline counts for one legislative session (GET /v1/sessions/{id}/dashboard): bills filed, passed, signed, vetoed, roll calls, active legislators. Start here for 'how is the 2026 Florida session going'. Get session_id from list_sessions.
No parameter schema on file.
Legislators ranked by bills sponsored and passed in one session (GET /v1/sessions/{id}/sponsor-stats). Each row has bills_sponsored, bills_primary, bills_passed, bills_primary_passed and pass_rate (passed = status 4, 5 or 8). This is the one call for 'who is most active or effective this session' and 'which senator passed the most bills': set chamber and sort:'passed' (or 'primary_passed' to count
No parameter schema on file.
How many roll calls each legislator voted in versus missed during one session (GET /v1/sessions/{id}/vote-participation). Use for attendance questions. Get session_id from list_sessions.
No parameter schema on file.
Every legislator who served in one session (GET /v1/sessions/{id}/legislators), with people_id. Use list_legislators for the current roster by state; use this for a specific past or special session. Get session_id from list_sessions.
No parameter schema on file.
Bill count per status (by:'status', on the status_id ladder) or per subject (by:'subject') for one session (GET /v1/sessions/{id}/status-counts or /subject-counts). Get session_id from list_sessions. status_id values: 1=Introduced, 2=In Committee, 3=Passed One Chamber, 4=Passed Both Chambers, 5=Signed into Law, 6=Vetoed, 7=Failed/Dead, 8=Chaptered. Aggregate buckets: passed={4,5,8}, failed={6,7},
No parameter schema on file.
The jurisdiction directory (GET /v1/states): the 50 states, D.C. and the U.S. Congress with their state_id, 2-letter code and full name. Returns the full list (52 rows) so you can resolve a name to a code or enumerate everything the corpus covers. For how COMPLETE each jurisdiction's data is, use get_coverage instead.
No parameter schema on file.
Per-state depth snapshot (GET /v1/coverage): how COMPLETE each jurisdiction's data is — bill counts, the share of bills holding at least one vote, text or sponsor, and whether the legislature is currently in session. Use it before drawing conclusions from a thin result set, to tell 'no such bills' apart from 'this state is thinly covered'. Read the completeness ratios rather than the raw percentag
No parameter schema on file.
Bills with the most news coverage in the window (GET /v1/trending), optionally for one state. Use for 'what's in the news' or 'hot bills right now'. Returns bill summaries with mention counts; call get_bill for detail.
No parameter schema on file.
Bills whose LATEST action in the window falls in a stage (GET /v1/bills-by-stage): introduced, committee, passed, executive (with the governor, signed, or vetoed), amendments, other. Fleet-wide across all jurisdictions — there is no state filter, so filter the rows by state_id or state_name yourself. Classified from the action text, not status_id. Use for 'what passed this week' or 'what reached t
No parameter schema on file.
One row per stage with the number of bills whose latest action landed there in the window (GET /v1/bills-weekly-breakdown). All jurisdictions combined. Use for a national 'how much moved this week' number; use get_session_dashboard for one state.
No parameter schema on file.
Search the election-candidate directory (GET /v1/candidates): people running for office. Filters combine with AND. Roughly a third carry an FEC filer id and sitting members of Congress carry a Bioguide id; both are null otherwise. Rows also carry people_id where the person has a legislative voting record — pass it to get_legislator / get_legislator_scorecard to go from candidate to voting history
No parameter schema on file.
Fetch one election candidate by id (GET /v1/candidates/{id}): their party, office, district and cycle, plus an FEC filer id where the campaign has filed and a Bioguide id for sitting members of Congress. When people_id is set, the candidate has a legislative voting record — pass it to get_legislator or get_legislator_scorecard to go from candidate to voting history in one hop. Get an id from list_
No parameter schema on file.
The election slate for 2026-11-03 (GET /v1/midterms): races, candidates and ballot measures per state, with official results where available. All data is official state election-office and FEC content collected by Delilah — no third-party attribution is required. live_results carries ONE ENTRY PER CONTEST, each with contest (e.g. primary:DEM, runoff:REP) and party: a closed primary returns eac
No parameter schema on file.
Ballot measures (GET /v1/measures): the list for a state, or one measure by its number (e.g. 'Amendment 1') with full text, summary and official source URL. Use for 'what's on the ballot in X' and 'what does Amendment N do'.
No parameter schema on file.
District metadata by state and type (GET /v1/districts): congressional, state senate, state house. Pass district_id with boundary:true to get the polygon as GeoJSON (GET /v1/districts/{id}/boundary) — it is large, so set simplify (degrees, e.g. 0.01) to shrink it. Match districts NUMERICALLY (district_number), never by label text.
No parameter schema on file.
The URL of a candidate's official portrait (GET /v1/photos/{candidate_id} returns the image bytes). Sources are official state-legislature and congressional portraits, public-domain and licensed images only — never a third party's photo library — and each carries a license and attribution string that MUST be shown when the license requires it (Wikimedia CC BY). Returns null when the candidate has
No parameter schema on file.
The current key's tier, monthly cap, requests used and remaining, and when the period resets (GET /v1/_meta/usage). Call this when a request is rate-limited (HTTP 429) or the user asks about their plan.
No parameter schema on file.
Manage the key's webhook subscriptions (/v1/webhooks). action:'list' is read-only. 'create' REGISTERS a URL that Delilah will POST to on the chosen events — it changes the account, so it requires confirm:true and the user's explicit go-ahead. 'test' queues a sample delivery to an existing subscription. 'delete' removes one (confirm:true). Events: bill_introduced, status_change, vote_recorded, text
No parameter schema on file.
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Legislation or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
This listing is an address its publisher runs, and you connect to it directly — this marketplace is not in the path. The scanner reads packages and public source, and an address is neither. So there is no grade — not a withheld one, an unmeasured one.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 0.7.2.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish Legislation can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.