Officials MCP server

• politics_alignmentFree

  Compare an official's stated positions against their actual roll-call votes, per topic — what they SAY vs how they VOTED, both source-linked. Does NOT label agreement/contradiction (you judge and cite); surfaces the juxtaposition no unsigned source can. Use official id.

• politics_billFree

  Details of a US bill or resolution: vote breakdown, sponsors, cosponsors, status, and origin proof. Returns metadata, a short text excerpt, and a text index by default; full legislative text is omitted because omnibus bills exceed typical token caps. The include_text parameter controls whether the complete text is returned in a single response.

• politics_bill_textFree

  One signed, bounded slice of a bill's full legislative text, addressed by part number or section label. Each response carries part and total_parts, next_part, the slice's part_sha256, and the whole-bill content_hash. Parts 1 through total_parts concatenated in order hash to content_hash, so a bill too large to return in a single response remains verifiable as complete and unaltered.

• politics_bill_tocFree

  Section index for a bill: every "SEC. N" heading with its character offset and length, plus the whole-bill origin hash (content_hash) and total text length. A small response that describes the structure of a large bill.

• politics_bills_searchFree

  Search bills by topic, sponsor, status, or congress. Returns bill metadata and whether full text is available.

• politics_bridge_compareFree

  Compare multiple politicians side-by-side on a bridge page — positions, party, office, campaign finance. Optionally filter to a specific topic.

• politics_bridge_createwrite actionFree

  Create a citizen bridge page — a personalized workspace for tracking representatives, comparing positions, and taking action (write letters, log calls). Returns a shareable URL that any AI agent can collaborate on. Optionally auto-populates with the citizen's state representatives.

• politics_bridge_letterFree

  Draft a letter to a politician on the citizen's bridge page. The letter gets an origin hash for proof of content. Returns delivery options (email, web form, USPS, phone).

• politics_bridge_sessionFree

  Current state of a citizen bridge workspace: tracked officials, saved comparisons, drafted actions, and messages.

• politics_by_stateFree

  Get all current officials for a US state — federal senators and representatives, state legislators, and any indexed local officials. Organized by government level.

• politics_candidate_feedFree

  Get a candidate's Campaign Data Standard (CDS) feed: a single machine-readable record of who they are, the offices they hold and seek, their positions in their own words (each source-linked), their voting record by reference, and declared data gaps. This is the standardized, signed feed an AI or reporter uses to grab a candidate's positions and verify they are genuine. Every MCP response is signed; the standalone signed feed is also at /official/{id}/candidate.json. Tier is "rootz-compiled" until the campaign claims and signs it ("candidate-signed").

• politics_candidatesFree

  Registered federal candidates for the 2026 election cycle, filterable by state, office (senate, house, president), party, or presence of a campaign URL. Returns campaign website, social media links, FEC data, and position and speech counts.

• politics_changesFree

  Get recent changes detected across all politicians — position shifts, website updates, new data. Each change links to the before/after snapshots with origin proof.

• politics_coverageFree

  Coverage map: per-state, per-dataset completeness (officials by level, positions, finance, state-legislative votes). Shows WHERE the data is deep (federal — complete) vs sparse (local). Use it to know whether silence means "no data captured" rather than "nothing there".

• politics_create_watchlistwrite actionFree

  Creates a Just the Facts watchlist bound to an email address, covering any combination of specific officials, issue topics, and a town with state for local meetings, agendas, and minutes. Sends a double-opt-in confirmation email and returns the bridge workspace URL.

• politics_methodologyFree

  Get the full transparency methodology — how we collect, assess, extract, sign, and verify political data. Includes quality assessment algorithm (signals + weights), trust levels, data sources, cron schedule, and what we can and cannot prove. Open and auditable.

• politics_municipalitiesFree

  Search US municipalities (cities, towns, villages, counties). Every incorporated place in the US with coordinates. Filter by state, name, or type. Returns website, platform, meeting calendar, and board/commission info where available.

• politics_officialFree

  Get full details for a specific official by ID — biography, party, office, policy positions, committee assignments, campaign finance, social media, and contact info. All data includes source URLs for verification.

• politics_originFree

  Get origin archive statistics — total snapshots, changes detected, origin proofs recorded, unique URLs tracked. Shows the depth of the political wayback machine.

• politics_pollFree

  Get one poll in full: pollster, sponsor, field dates, population, sample size, margin of error, mode, the VERBATIM question(s) asked, per-option toplines, the first-party source_url, and the signature (poll_proof) that binds the exact wording and numbers. This is the ground truth to check any claim about a poll against.

• politics_pollsFree

  Search the SIGNED public-poll archive. Unlike aggregators, every poll keeps the EXACT question wording, population base (LV/RV/adults), sample size, margin of error, mode, and per-option toplines — first-party sourced, snapshot-hashed, and cryptographically signed (verifiable). Filter by race_key, state, subject (e.g. "approval", "Senate"), pollster, or since (ISO date). Returns a list; call politics_poll {id} for full detail + signature. Use this when a question hinges on what a poll ACTUALLY asked vs how it was reported.

• politics_positionsFree

  Policy positions across officials by topic, covering who supports or opposes issues such as crypto, stablecoins, AI, healthcare, and guns. Each position carries a source URL and origin hash. Returns compact records by default (id, name, party, state, stance, summary, source) with a total count; the compact parameter controls row detail and offset controls paging.

• politics_provenanceFree

  Get the complete origin proof chain for an official — every data source, content hash, quality assessment, snapshot history, and verification instructions. Proves where every piece of data came from.

• politics_representFree

  Representation lookup for a US ZIP code: both U.S. Senators, the U.S. House member for that ZIP's congressional district, and the state's statewide executives (governor, attorney general, and similar). Every official carries source_url (the capture origin) and source_link (a public page).

• politics_resolveFree

  Resolve a messy name string (e.g. "Rep. Johnson", "cornyn") to a canonical official — returns the best match with a 0-1 confidence score and ranked alternatives. Use this first when you have a name but not an ID; then call politics_official with best.id. Add state to disambiguate.

• politics_searchFree

  Search for politicians and elected officials across all levels of US government — federal, state, county, municipal. Filter by name, state, party, level, chamber, or office title. Returns officials with their current office, party, and contact info.

• politics_speechesFree

  Search Congressional Record floor speeches by official, topic, date range, or keyword. Returns verbatim text from the official government record with origin proof hash. Every speech is directly citable with a GPO source URL.

• politics_state_votesFree

  Search state legislature votes across 26+ US states. Filter by state, topic, or date. Returns bill title, vote result, yes/no counts.

• politics_statsFree

  Get summary statistics for the politics.rootz.global database — total officials, breakdown by level, party, state, and chamber. Shows coverage completeness.

• politics_timelineFree

  Get the full origin timeline for a politician — every page snapshot, every position change, every data source with hash proof. The political wayback machine. Shows what changed, when, and where the data came from.

• –Code scanremote-only server, no package to scann/a
• Live reliabilityremote reachable in 1019ms20/20
• Tool poisoning30 tool descriptions checked15/15
• Auth qualityopen endpoint exposes 2 write-action tools with no auth3/15
• Maintenancerepository archived0/15
• Maintainer identitynamespace and repository owner differ; GitHub account older than a year; website matches verified namespace8/10

Safety score

61/100

higher than 16% of 48,255 servers

Tools

30

the typical server has 7

Tools that change things

7%

typical: 0%. Fewer write tools means less an agent can break

Uptime

100%

of our recent checks; the typical remote server answers 100%

Response time

427 ms

faster than 34% of 30,031 servers

Grade history

• 2026-10-09restoreF → Cscore 61: Write-action tools reachable without authentication; Repository is archived
• 2026-10-02revokeC → Fscore 22: Remote endpoint did not respond; Repository is archived

Officials: common questions

Is Officials MCP server safe?

With care: it is graded C, so read the findings first (61/100). Read the Officials safety report

How do I install Officials?

It runs remotely at politics.rootz.global. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.

Does Officials need an API key?

Not as far as the registry entry and our scan can tell: no credentials are declared or required.

Is Officials maintained?

The last commit was 103 days ago (2026-07-24). The latest release is v0.3.0.

Is Officials up?

100% of our last 28 checks got an answer. We check remote servers about four times a day.

How does Officials compare with other MCP servers?

safety score 61/100 (higher than 16% of 48,255 servers); tools 30 (the typical server has 7); tools that change things 7% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.