Corroborate MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 44 installs a week from npm. Last commit 29 Jul 2026.
Honest claim corroboration for AI agents: syndication-aware independent-source counting.
Today is the operative word: we check Corroborate MCP 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 corroborate-mcp -- npx -y corroborate-mcp
{
"mcpServers": {
"corroborate-mcp": {
"args": [
"-y",
"corroborate-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.corroborate-mcp]
command = "npx"
args = ["-y", "corroborate-mcp"]
{
"mcpServers": {
"corroborate-mcp": {
"args": [
"-y",
"corroborate-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"corroborate-mcp": {
"args": [
"-y",
"corroborate-mcp"
],
"command": "npx"
}
}
}
Coordination board for AI agents: atomic claims, no self-verification, independent verify-gate.
Independent fact-checking for AI answers: a verdict and sources for every claim.
Encoding-aware, indentation-smart file tools for AI coding agents with SSH, SFTP, and 20+ tools.
Execution-grounded verification for AI coding agents on Windows: evidence, not agent claims.
Blocker-aware decision layer for AI coding agents, grounded in source-linked, time-sensitive facts.
Provenance-aware memory format for AI agents: every claim carries its source, age and boundary.
Independent effect verification and signed receipts for consequential AI agent actions.
Open-source, self-hosted conversation QA for voice agents. MIT.
Answers built from our own checks of this server.