Catalyst Edge Research runs on your own machine — the client starts it, so there is no endpoint to ping. 223 installs a week from pypi. Last commit 6 Oct 2026.
Source-linked market intelligence for AI agents researching public-company tickers.
Today is the operative word: we check Catalyst Edge Research every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add catalyst-edge-mcp -e 'CATALYST_EDGE_SEC_USER_AGENT=<CATALYST_EDGE_SEC_USER_AGENT>' -- uvx catalyst-edge-mcp
{
"mcpServers": {
"catalyst-edge-mcp": {
"command": "uvx",
"args": [
"catalyst-edge-mcp"
],
"env": {
"CATALYST_EDGE_SEC_USER_AGENT": "<CATALYST_EDGE_SEC_USER_AGENT>"
}
}
}
}
[mcp_servers.catalyst-edge-mcp]
command = "uvx"
args = ["catalyst-edge-mcp"]
env = { CATALYST_EDGE_SEC_USER_AGENT = "<CATALYST_EDGE_SEC_USER_AGENT>" }
{
"mcpServers": {
"catalyst-edge-mcp": {
"command": "uvx",
"args": [
"catalyst-edge-mcp"
],
"env": {
"CATALYST_EDGE_SEC_USER_AGENT": "<CATALYST_EDGE_SEC_USER_AGENT>"
}
}
}
}
{
"servers": {
"catalyst-edge-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"catalyst-edge-mcp"
],
"env": {
"CATALYST_EDGE_SEC_USER_AGENT": "<CATALYST_EDGE_SEC_USER_AGENT>"
}
}
}
}
Put your own value in place of
<CATALYST_EDGE_SEC_USER_AGENT> (Required SEC-compliant identity in Company [email protected] form for live evidence collection).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
CATALYST_EDGE_EVIDENCE_STORE (Optional local SQLite evidence-store path), CATALYST_EDGE_GDELT (Rights-cleared attributed discovery metadata defaults to enabled; set to disabled to opt out), CATALYST_EDGE_BLUESKY (Optional explicit opt-in: set to enabled for forward-only partial public attention; defaults to disabled).
Market research and competitive intelligence for startup ideas - every finding source-linked.
Pharma intelligence: source-linked drug, trial, result, patent, company and deal research.
x402-paid analytics, market intelligence, research, and LLM inference for AI agents.
Pay-per-call trading intelligence for AI agents: live market regime, trading signals, composite conv
Paid NOVA research, company intelligence, and output recovery for agents.
Public source-linked memories for AI agents: search, read, cite, reply, and share findings.
Equity trend, relative-strength, expected-return, market-context, and research resources for agents.
The Google for AI agents — company intel, competitor tracking, market research via MCP. JSON output
Answers built from our own checks of this server.