eleata Claim Verifier MCP server
Grounding/hallucination guard: verify a claim against evidence (Supported/Refuted/NEE).
1 stars38 downloads/wk
Reviews
Write oneNobody has reviewed eleata Claim Verifier yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
eleata Claim Verifier tools (3)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
check_groundednessHallucination guard for RAG / agent answers. Pass the model's generated answer and the retrieved
verify_claimFact-check a claim against a piece of evidence using natural-language inference.
verify_strictSame as verify_claim but with a raised abstention threshold — abstains more readily. Use when a wrong
Public scan report
scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it
- Code scan2 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 qualitystatic API keys via environment variables6/15
- Maintenancelast push 88 days ago12/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How eleata Claim Verifier 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
- 3
- 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
- 38
- more than 29% of 12,191 servers with a package
What its tools let an agent do: 3 read
Install eleata Claim Verifier in Claude Code, Cursor or VS Code
Runs npx -y eleata-verify-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add eleata-verify-mcp -- npx -y eleata-verify-mcp
What the publisher says
From the eleata Claim Verifier repository's README, as published. We do not edit it. Read it on GitHub
eleata Claim Verifier — MCP server
A grounding / hallucination guardrail for AI agents. Give it a claim and supporting evidence; it returns whether the evidence Supports / Refutes / gives Not Enough Evidence for the claim (natural-language inference), with a confidence and an abstained flag for low-confidence cases. Wraps the hosted eleata Claim Verifier.
Use it as a fact-check / RAG hallucination guard: before an agent trusts or repeats a
statement, check it against its source. Treat abstained=true (or any verdict other than
Supported) as "do not rely".
Tools
Setup
{
"mcpServers": {
"eleata-verify": {
"command": "npx",
"args": ["-y", "eleata-verify-mcp"],
"env": { "EVERIFY_API_KEY": "your_key" }
}
}
}Get a key at (paid channel, sent as Authorization: Bearer). For the RapidAPI marketplace channel, set EVERIFYRAPIDAPI=1 and EVERIFYAPI_BASE to the RapidAPI host (the key is then sent as X-RapidAPI-Key).
Notes
Confidence is uncalibrated on the public channels (not a probability) — rely on the verdict and the abstained flag, not the raw number. The engine is a multilingual NLI model (mDeBERTa-v3-mnli-xnli). verify sends your claim + evidence to the hosted API; see .
MIT licensed.
Nothing above is checked by us. What we check is on the safety report.
eleata Claim Verifier: common questions
- Is eleata Claim Verifier MCP server safe?
- Mostly: it is graded B (78/100). Read the eleata Claim Verifier safety report
- How do I install eleata Claim Verifier?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does eleata Claim Verifier need an API key?
- Yes. The registry entry asks for
EVERIFY_API_KEY. - Is eleata Claim Verifier maintained?
- The last commit was 127 days ago (2026-06-30). The latest release is v0.1.1.
- How does eleata Claim Verifier compare with other MCP servers?
- safety score 78/100 (higher than 57% of 48,255 servers); tools 3 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.