Corroborate MCP server
io.github.chefcohen/corroborate-mcp·v0.1.3·1 starsHonest claim corroboration for AI agents: syndication-aware independent-source counting.
1 stars79 downloads/wk
Reviews
Write oneNobody has reviewed Corroborate yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Corroborate tools (2)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
corroborate_claimGiven a factual/news claim, returns how INDEPENDENTLY it is being reported. Use before
find_sourcesMulti-engine news/source search (Google News, GDELT, Hacker News) for a query: a deduped list of
Public scan report
scanner v0.1.10 · 2026-10-31 · same rubric, same numbers if you re-run it
- Code scan5 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 94 days ago8/15
- Maintainer identityregistry namespace matches repository owner6/10
How Corroborate compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 78/100
- higher than 57% of 48,255 servers
- Tools
- 2
- the typical server has 7
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- GitHub stars
- 1
- more than 65% of 28,688 servers
- Downloads a week
- 79
- more than 57% of 12,191 servers with a package
What its tools let an agent do: 2 read
Install Corroborate in Claude Code, Cursor or VS Code
Runs npx -y corroborate-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add corroborate-mcp -- npx -y corroborate-mcp
What the publisher says
From the Corroborate repository's README, as published. We do not edit it. Read it on GitHub
corroborate-mcp
The honest corroboration layer for AI agents. Hand it a claim; it tells you how independently that claim is actually being reported — and shows its work.
An AP story echoed by 40 outlets is one origin, not 40 citations. Other verifiers count citations; Corroborate counts independent origins — syndication-aware — then publishes its own error rates and discloses coverage gaps. That's the judgment layer raw search and citation-checkers skip.
corroborate_claim("NASA delayed the Artemis III landing") → CONFIRMED 4 independent origins · conf 0.9
corroborate_claim("Zorblatt Corp acquired Portugal") → UNCORROBORATED 0 origins · conf 0.05When an agent should call this
- Before relying on a current-event / news claim — is it independently reported, or one source echoed everywhere?
- To rank or filter sources by genuine independence, with a confidence score.
- When you need a verdict you can defend — every answer ships its evidence, its confidence, and its own caveats.
Not a web search engine (use Exa/Tavily/Brave for that) and not a human fact-checking network. It's the narrow, honest primitive in between: how independently is this reported?
Why it's trustworthy — by design
What it measures — and what it doesn't
Reporting corroboration, not truth. A claim every outlet syndicated from one wire story comes back SINGLE_SOURCE. A claim nobody covers comes back UNCORROBORATED even if true. The verdict states exactly what was measured, flags its weaknesses in notes, and sets coverage:"degraded" when an engine was down — so absence of evidence is never quietly sold as evidence of absence.
Quickstart
Requires Node ≥ 18. No keys, no config.
Claude Code
claude mcp add corroborate -- npx -y corroborate-mcpClaude Desktop / Cursor / any MCP client (claudedesktopconfig.json, .cursor/mcp.json, …)
{ "mcpServers": { "corroborate": { "command": "npx", "args": ["-y", "corroborate-mcp"] } } }Try it with no MCP client
npx corroborate-mcp # starts the stdio server (silent = healthy)
# or from a checkout: node cli.js "The Federal Reserve held interest rates steady"Tools
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Grade history
- 2026-10-31downgradeA → Bscore 78
Corroborate: common questions
- Is Corroborate MCP server safe?
- Mostly: it is graded B (78/100). Read the Corroborate safety report
- How do I install Corroborate?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Corroborate need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Corroborate maintained?
- The last commit was 98 days ago (2026-07-29). The latest release is v0.1.3.
- How does Corroborate compare with other MCP servers?
- safety score 78/100 (higher than 57% of 48,255 servers); tools 2 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.