Documentation

How to connect your AI agent to KeyVex and query the 38 tools. No account, no API key, no OAuth flow — point your MCP client at the endpoint and go. Last updated 2026-05-22.

What is KeyVex

KeyVex is a remote Model Context Protocol (MCP) server that exposes US public financial and government disclosures as agent-native tools. Your AI agent (Claude Desktop, Cursor, or any MCP client) connects once and can query 38 tools across dozens of official US government sources — SEC filings, congressional trades, FEC campaign finance, federal contracts and grants, lobbying, regulatory enforcement, sanctions, macroeconomic indicators, and more.

All data is public-record information sourced directly from US government agencies. KeyVex normalizes and indexes it; KeyVex does not provide investment advice, derived signals, or trading recommendations.

Quickstart

1. There's no signup

KeyVex's MCP endpoint is publicly accessible. No account, no API key, no consent flow. Point your client at the URL below and start calling tools.

2. Configure your MCP client

The KeyVex MCP endpoint is:

https://mcp.keyvex.com

For Claude Desktop, add this to your claude_desktop_config.json:

{
  "mcpServers": {
    "keyvex": {
      "url": "https://mcp.keyvex.com",
      "transport": "http"
    }
  }
}

For Cursor or any other MCP client, follow your client's instructions for adding a remote MCP server URL. KeyVex supports the standard Streamable HTTP transport. No authentication headers are required.

3. Make a query

Ask your agent something that touches KeyVex data:

"Show me the largest congressional trades in the past 30 days
 with party and committee context."

The agent will pick the right tools (get_congressional_trades and get_member_profile), run them in parallel, and synthesize an answer.

4. Verify with curl (optional)

You can hit the endpoint directly without any client. Health check:

curl https://mcp.keyvex.com/

Returns server version, tool count, and the full tool list as JSON. List all tools via MCP:

curl -X POST https://mcp.keyvex.com/ \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'

No Authorization header is needed. The response is a JSON-RPC envelope containing the full schema of every tool.

Authentication

The reason: every tool serves data already public by federal mandate (SEC filings, USAspending records, congressional disclosures, etc.). There's nothing user-specific to gate on. Removing the auth layer also removes a setup step for the agent developer.

Abuse prevention. Because the endpoint is open, two mechanisms protect it from runaway use:

• A per-IP rate limit caps each calling IP at 60 requests per 60-second sliding window. Exceed it and the endpoint returns HTTP 429 with a Retry-After header.
• A Cloud Run instance cap bounds the worst-case server load even under a coordinated flood.

Future paid tiers (when they ship). Paid tiers — with higher quotas, priority routing, and dedicated support — will live on a separate URL (e.g., a /v2 path or sibling subdomain) and will use per-customer Bearer keys we issue at signup. The public endpoint at mcp.keyvex.com will remain authless and free.

Tool reference

KeyVex exposes 38 tools. All are read-only. Every tool's full schema (parameters, filters, response shape) is returned by the MCP tools/list method. The table below is a one-line summary.

SEC filings & market structure

Congressional activity

Campaign finance & influence

Federal awards

Regulatory & compliance

Macroeconomic & markets

unified_search

unified_search is the cross-source meta-tool. Pass one or more identifiers (ticker, company_name, cusip, company_cik, bioguide_id, recipient_uei) and it fans out across every applicable tool in parallel, returning a unified envelope.

Useful when you want a full picture of an entity without manually calling 10 tools:

{
  "method": "tools/call",
  "params": {
    "name": "unified_search",
    "arguments": { "ticker": "NVDA" }
  }
}

The fan-out hits insider transactions, congressional trades, institutional holdings, activist stakes, federal contracts, material events, fundamentals, and more — whichever tools match the identifier you passed. get_lobbying_filings is the one collection deliberately excluded from the fan-out (substring scans on 51K+ filings are too slow to parallelize); call it directly for lobbying queries.

Rate limits

The public endpoint is open but rate-limited per IP to prevent abuse and protect hosting cost:

• 60 requests per 60-second sliding window per IP. If you exceed this, the endpoint returns HTTP 429 with a Retry-After header indicating how long to wait.
• Server-side concurrent instance cap further bounds worst-case load under coordinated traffic. You should never see this unless you're actively trying to flood the server.

For most agent workflows (a few tool calls per user question, occasional batch catch-up) you will never see the rate limit. If your use case legitimately requires sustained higher volume, email contact@keyvex.com — we can discuss a paid tier on a separate URL when those ship.

Data freshness

KeyVex caches normalized data in Firestore. Refresh cadence per source:

• SEC filings (most types): hourly
• SEC Form 4: every 30 minutes
• 13F: every 4 hours
• Congressional trades: daily, 6 AM ET
• FEC contributions, federal contracts, lobbying: daily
• Bills, votes, member profiles: daily
• XBRL fundamentals: weekly
• FARA, OFAC, screening lists, recalls: daily
• Economic indicators: daily

Each tool response includes a scraped_at or last_modified_date field so you can see exactly when the source was last polled.

Troubleshooting

Support

For privacy, terms, and data-handling questions, see the privacy policy. For status and version, see the public health check at https://mcp.keyvex.com/ (returns server version and current tool list as JSON, no authentication required).