Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@civic-awareness-mcp Show me recent bills on healthcare in Congress"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Two MCP servers for US civic data — one for Congress + federal campaign finance, one for 50-state legislatures.
Server | Source | Jurisdictions | Package |
| Congress.gov + OpenFEC | US federal |
|
| OpenStates | 50 states + DC |
|
Each server reads/writes-through to a local SQLite store as a TTL cache. Every response includes a sources: { name, url }[] array for provenance. No tool synthesizes summaries — that is the LLM's job.
Related MCP server: LegiScan MCP Server
Tool | Kind | What it answers |
| feed | Bills introduced or acted on in the last N days (Congress.gov) |
| feed | Roll-call votes in the last N days, yea/nay/present tallies |
| feed | Federal campaign contributions in a date window (OpenFEC) |
| search | Title search across cached federal bills, votes, contributions |
| entity | Name search across Members of Congress + FEC candidates/committees |
| entity | Entity detail + role history + recent documents |
| entity | Disambiguate a name into one or more Person entity IDs |
| entity | Co-occurrence graph via bills, votes, contributions (depth 1–2) |
| detail | Full roll-call vote with per-legislator positions |
Tool | Kind | What it answers |
| feed | Bills by jurisdiction; filters for sponsor, subject, classification, session, dates |
| feed | Roll-call votes in the last N days, chamber + tally (OpenStates, per jurisdiction) |
| detail | Full bill detail: actions, versions, sponsors, subjects |
| search | Title search across cached state bills |
| entity | Name search across state legislators (OpenStates) |
| entity | Entity detail + role history + recent documents |
| entity | Disambiguate a name into one or more Person entity IDs |
| entity | Co-occurrence graph via shared sponsored bills (depth 1–2) |
Node.js ≥ 22
API keys: api.data.gov (covers Congress.gov + OpenFEC), OpenStates — all free tier
npm install
npm run build
# federal server
npm run bootstrap:federal
npm run start:federal
# state server
npm run bootstrap:state
npm run start:stateFor development (no build step):
npm run dev:federal
npm run dev:stateThe server fetches data automatically on cache miss. For bulk pre-population:
# federal
npm run refresh:federal -- --source=congress --max-pages=1
npm run refresh:federal -- --source=openfec --max-pages=1
# state (one jurisdiction)
npm run refresh:state -- --source=openstates --jurisdictions=tx --max-pages=1To prune stale fetch-log rows (recommended monthly):
npm run evict-fetch-lognpm test # mocked unit + integration suite (MSW)
npm run test:watch # rerun on change
npm run test:drift # live-API drift tests (requires .env.local)
npm run typecheck # tsc --noEmit
npm run lint # eslint
npm run format # prettier --writeTo run both servers locally, add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"civic-federal-mcp": {
"command": "node",
"args": ["/absolute/path/to/civic-awareness-mcp/dist/federal/index.js"],
"env": {
"API_DATA_GOV_KEY": "your-key",
"CIVIC_FEDERAL_DB_PATH": "/absolute/path/to/federal.db"
}
},
"civic-state-mcp": {
"command": "node",
"args": ["/absolute/path/to/civic-awareness-mcp/dist/state/index.js"],
"env": {
"OPENSTATES_API_KEY": "your-key",
"CIVIC_STATE_DB_PATH": "/absolute/path/to/state.db"
}
}
}
}Variable | Server | Description |
| federal | api.data.gov key (Congress.gov + OpenFEC) |
| state | OpenStates v3 API key |
| federal | SQLite path (default |
| state | SQLite path (default |
| both | Optional daily API spend cap (unused by default) |
| both |
|
Four workflows in .github/workflows/:
ci.yml — format, lint, typecheck, tests, build, MCP stdio smoke. Matrix on Node 22/24. Runs on push to main and on every PR.
codeql.yml — CodeQL static analysis. Runs on push/PR/weekly.
scorecard.yml — OpenSSF Scorecard. Runs on push/weekly.
nightly-drift.yml — live-API shape checks against OpenStates, Congress.gov, OpenFEC. Runs daily at 09:00 UTC and on-demand via workflow_dispatch.
The drift workflow requires repo secrets OPENSTATES_API_KEY and API_DATA_GOV_KEY (separate from user keys — those are configured locally via .env.local).
See SECURITY.md. Highlights:
Never writes to upstream APIs
All sources are sanctioned free-tier APIs with documented rate limits
Rate-limited fetch with per-host token bucket; Retry-After honoured
Zod-validated inputs; parameterized SQLite queries
No contributor PII in responses
MIT — see LICENSE.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Search bills and speaker-attributed hearing transcripts across all 50 US state legislatures.
Access FEC campaign finance data. Query data about candidates, money trails, and election filings.
Search bills, legislators, committees, and events across all 50 US states, DC, and 5 US territories.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/julianken/civic-awareness-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server