Catalyst Edge MCP Server
Enables AI agents to access audited SEC intelligence, including scored catalyst picks and track record data, via the Model Context Protocol.
README
Catalyst Edge MCP Server
Audited SEC catalyst intelligence for AI agents, over the Model Context Protocol. Every US-market SEC filing with market-moving potential is fetched from EDGAR, scored by 500+ data engines, and ranked before the market opens — and unlike most signal products, the track record is public: every past call is published with its outcome at catalystedgescanner.com/receipts.
Use the hosted server (no install)
A hosted instance is live. Point any MCP-capable client at it, or POST JSON-RPC directly:
curl -s https://catalystedgescanner.com/mcp/ \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'
Call a tool (no key needed for the free tier):
curl -s https://catalystedgescanner.com/mcp/ \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"get_convergence_picks","arguments":{"limit":3}}}'
Paid tiers use a Bearer token: Authorization: Bearer <your-key>.
Tools
| Tool | Tier | Returns |
|---|---|---|
get_convergence_picks |
free | today's scored catalyst picks (free: top 3) |
get_track_record |
free | historical hit-rate / alpha of published picks |
get_ticker_signal |
intelligence | full per-ticker signal-layer breakdown |
get_thesis |
intelligence | plain-language thesis (catalysts, risks, bear case) |
get_sector_lean |
intelligence | directional sector lean |
free — evaluation tier, no key required. intelligence — all tools, full depth; keys via catalystedgescanner.com/pricing or catalystedgepro@gmail.com.
Claude Desktop / Cursor config (stdio, self-hosted)
{
"mcpServers": {
"catalyst-edge": {
"command": "python3",
"args": ["/path/to/catalyst_mcp.py"],
"env": { "CATALYST_MCP_KEY": "optional-key" }
}
}
}
Stdlib Python only — no dependencies. HTTP mode: CATALYST_MCP_HTTP=1 python3 catalyst_mcp.py (binds 127.0.0.1:8848; front with TLS for public use — see catalyst-mcp.service). Key→tier mapping lives in mcp_keys.json (see mcp_keys.json.example).
Verify
python3 smoke_test.py # exit 0 = handshake + all tools OK
Data & disclaimers
Sources: SEC EDGAR (filings, XBRL, insider activity), US government open data, delayed market prices. Nothing here is financial advice; signals are research with a published, audited track record — hits and misses both. Machine-readable site map: catalystedgescanner.com/llms.txt · OpenAPI: /openapi.json.
MIT licensed.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.