ElectionsMCP

Model and map any 2028 U.S.

Community: Submitted by a user or imported; check the owner before granting accessOnlineAPI key requiredGlobalFreeRead-only

What it can do

    What data it sees

    Do you need an account

    An API key from the service settings is required

    Model and map any 2028 U.S. race down to the precinct: scenarios, swing, turnout, and roll-ups.

    How to connect

    How to connect ElectionsMCP to Claude

    The server address to paste into Claude settings:

    https://www.electionsmcp.com/mcp

    1. Open Claude (claude.ai or the desktop app).
    2. Go to Settings → Connectors.
    3. Click Add custom connector.
    4. Paste the server address copied below into Remote MCP server URL and click Add.
    5. In a chat, click + → Connectors and switch the new connector on.

    Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

    Authorization

    After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

    How to connect ElectionsMCP to ChatGPT

    The server address to paste into ChatGPT settings:

    https://www.electionsmcp.com/mcp

    1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
    2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
    3. Open Settings → Connectors and click Create.
    4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
    5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
    6. In a new chat open + → Apps/Connectors and enable the connector.

    OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

    Authorization

    On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

    How to connect ElectionsMCP to Cursor

    The server address to paste into Cursor settings:

    https://www.electionsmcp.com/mcp

    Fastest: click Open in Cursor below and confirm the prompt.

    Manually:

    1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
    2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
    3. Save the file. The server appears in the MCP list; authorize it there if asked.

    Authorization

    If the service needs sign-in, an authorize button appears next to the server in the MCP list.

    Server tool list (41)

    Raw names from tools/list. Only developers need these.

    resolve_geographyTurn a place name or shorthand into its canonical geo_id — resolve natural-language or structured location input. Handles "CA-03"/"NC-4" (congressional districts), bare state names/abbreviations, "<County> County…
    resolve_candidateWHO holds or runs for WHAT — turn a candidate/officeholder name into their seat + next race. Given a name (full, last-name, or a registry alias — "Lauren Boebert", "Boebert"), returns the person(s) who match with their…
    search_candidatesBROWSE the canonical candidate registry WITHOUT a name — the nameless companion to resolve_candidate (which requires a name). Filter the registry of canonical people by party, office, and/or a name substring:…
    lookup_addressResolve a US street address, ZIP, state, or U.S. House district and show workspace campaigns covering the result. Street addresses return a geocoded point and containing districts, with a precinct when coverage exists.…
    list_contestsDiscover contests for a geography and election cycle. Filter general, primary (dem_primary/rep_primary), or all stages; count describes the returned top-level rows. National presidential primaries are discoverable in…
    election_calendarThe election planning calendar. National form ({cycle}) returns federal contests, governors and by_state office lists; state form ({state,cycle}) returns a four-year horizon. Other statewide executive offices use the…
    set_performanceSet a candidate's vote share, such as the Democratic candidate to 54%, in one specific county, district, state, or precinct (the general-election override). Routes a county/state/district geo_id to a feature override…
    target_precinctsReturn structured precinct model rows: precinct_id, name, county, county_fips, baseline_share, modeled_share, ballots_est, overridden, and gap_to_goal. The response does not include demographic columns or demographic…
    create_scenarioCreate a new Scenario (a modeled path) — optionally inside a Race and seeded from a contest_id or an existing scenario (import_from). Seeds an immutable baseline version (v1). Returns scenario_id + version_id. (A…
    get_viewRead the exact map/view state the application renders for a canonical scenario: headline totals, selected geography, modeled feature colors, annotations, primary-calendar playhead, candidate roster, presence, and a…
    render_viewA headless server-rendered IMAGE of the map — the rendered view a viewer sees, as SVG or PNG, WITHOUT a browser (tk_0b6d3501 P2). For a scenario + level (president | senate | house | governor | the execs) it draws the…
    render_chartshare_comparison compares candidate shares for two saved versions of one model or two same-contest statewide general-election models. Returns canonical integer candidate votes, all-ballot shares, D-minus-R margins,…
    set_viewSet the active scenario view and selected map context: race stage, calendar playhead, geography grain, result source, selected feature, camera, map theme, and rail. The same persisted view state and deep link are used…
    get_scenarioA Scenario at its latest version (or a specified version_id): metadata (incl. latest_hash) + the version's top_line (margin / EC / viability) + its content hash/prev_hash. EM-119: pass a version_id (or…
    commit_versionSave the scenario's current state as a new immutable, hash-stamped version in the append-only chain. Records a diff vs the parent version and the recomputed top_line, and returns a content `hash` (+ `prev_hash`…
    list_scenariosPage saved scenarios/simulations in this workspace by updated_at descending and scenario_id ascending, without version blobs. Returns scenario_id, name, level, cycle, contest_id, race_id, tags, durable_id, published…
    diff_versionsStructured diff between two immutable versions. Raw before/after remain stored override patches (null means no saved override). Precinct cells also include effective_before/effective_after shares with their…
    billing_statusBILLING — your subscription state: {billing_enabled, logged_in, plan (personal|team|null), status, active, renews, can_save}. billing_enabled is false until the server is configured with Stripe; while it is false,…
    connection_statusWHO AM I — how THIS session is authenticated and which workspace this request resolved to. Returns authentication fields plus workspace {workspace_id, role, selection_source}. Modern MCP clients select a workspace with…
    set_candidatesReplace the entire candidate roster for a simulation+level in one call (add / edit / remove / reorder). Each candidate: {id?, name, party, color?, incumbent?}; ids auto-assigned if omitted. Use this to set the real…
    set_turnoutSet the turnout (mobilization) model. PRESIDENT (default, unchanged): each dial is a percentage-point boost toward toward_candidate_id in counties over an ACS threshold (college = >20% BA share, immig = >15%…
    add_map_commentLeave a Google-Docs-style COMMENT on the scenario map — a threaded, resolvable discussion anchored to a place. CAMPAIGN ISOLATION: when working inside a campaign, pass campaign_id; the scenario must be filed under it…
    list_map_commentsList one campaign's map comments on a scenario (oldest-first), each with its campaign_id, anchor, author, body, @mentions, parent_id, and resolved state. Pass campaign_id inside a campaign; only that exact campaign is…
    apply_uniform_swingApply an incremental swing in points toward one candidate at the requested office. A saved race_scope restricts writes to that state or district and refuses a different office or unresolved geography. Unscoped and…
    get_tallyCompute the current per-candidate tally for a simulation+level. For President: state-aggregated EVs. For others: feature counts. For level:"senate" the default is the 50-state per-candidate race scoreboard; pass…
    list_simulationsList saved simulations in this workspace (id, name, level, cycle, mode, contest_id, last-modified; rows stamped with an identity also carry created_by/updated_by member user_ids). Optional filters narrow a large…
    get_simulationRead the canonical simulation/scenario state, including candidates, race scope, geography overrides, active version identity, provenance, and optional summary or selected dot-path fields.
    list_flippedList baseline-to-model winner changes. Defaults to state for statewide offices, county for president, and district for house/state legislature. Explicit grain:county|precinct uses canonical integer local votes for a…
    compare_simulationsCompare two simulations. Without grain, returns the existing chamber/feature comparison. With grain:county|precinct and one state, compares exact saved canonical vote rows: margin(B)-margin(A), winners, flips, ballots…
    share_simulationMint a public, read-only link to the exact canonical scenario/version. Authenticate for durable workspace ownership; revoke_share disables the link.
    roll_up_raceRoll up precincts to a race outcome under the current simulation. Sums baseline votes for all precincts inside the district boundary, applying overrides in precedence order: a per-precinct override wins, else…
    apply_swing_to_queryApply a uniform swing or an explicit per-precinct weights vector to a filtered cohort in one atomic call. Weights select only their named IDs, support canonical statewide mechanisms, and optionally rescale a persuasion…
    get_campaign_onboardingCAMPAIGN ONBOARDING — guide a campaign manager or joining staff member through setup in their connected AI. Read one step or the complete guide: connection, campaign identity, team access, optional data imports, first…
    helpOrient an AI client to campaign onboarding through get_campaign_onboarding, user-controlled election modeling, candidate and presidential-primary workflows, supported geography, scenario versions, contextual War Room…
    get_catalogDISCOVERY — browse workflow/category groups, search tool names and descriptions, or fetch one complete schema and AI guide with tool. No arguments returns a compact counted index of the authorized inventory. Core…
    list_primary_calendarRead the 2028 primary calendar with source dates, schedule certainty, modeled delegate coverage, missing jurisdictions, and threshold basis. New calendars include the six DNC-approved early dates; other unverified…
    set_primary_sharesSet a party's presidential-primary vote shares — one state, or MANY states in a single call. SINGLE STATE: pass `state` + `shares` (unchanged behavior; echoes the full running roll_up). BATCH: pass `states` = { "SC":…
    roll_up_primaryThe running delegate count — OR, for a race-scoped downballot sim, that race's own share rollup. DOWNBALLOT (tk_2110d54c1d0871): when the scenario is race-scoped to a non-presidential office (set_race_scope…
    primary_batch_editATOMIC batch-edit transaction for a PRIMARY scenario — validate, preview, apply, and roll back a whole SET of candidate / share / calendar edits as ONE transaction. Pass edits:[{op, ...}, …] where each entry carries…
    set_race_scopeBind the canonical scenario to one race/campaign so its map, tally, candidates, War Room context, operations, outputs, and MCP actions share the same race identity.
    call_toolRun any other tool you are authorized for that is not in this list. Find it and its exact input schema with get_catalog (search, a workflow, or {tool: name}), then call call_tool({ name, arguments }). The named tool…