mcpField
E

Eleata Verify Mcp

Local
github.com/hernaninversoAI & Agents1Updated 17w ago
Repository

About Eleata Verify Mcp

Eleata Verify Mcp is an MCP server that checks claims against supplied evidence through the hosted eleata Claim Verifier. It returns a verdict, confidence, and an abstention flag for use in agent fact-checking and RAG grounding checks.

Key features

  1. 01Checks claims against evidence
  2. 02Returns support, refutation, or insufficient evidence
  3. 03Provides confidence and abstention status
  4. 04Checks answers against retrieved context
  5. 05Offers a stricter verification mode

Use cases

  1. 01Fact-check an agent's claim against its source
  2. 02Check whether a RAG answer is grounded in context
  3. 03Apply stricter checks in compliance or legal workflows

MCP support

Exposes `verify_claim`, `check_groundedness`, and `verify_strict` tools to MCP clients. Verification is performed through the hosted eleata service.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "eleata-verify": {
      "command": "npx",
      "args": [
        "-y",
        "eleata-verify-mcp"
      ],
      "env": {
        "EVERIFY_API_KEY": "<EVERIFY_API_KEY>"
      }
    }
  }
}
Run commandnpx -y eleata-verify-mcp
Environment variables to set
EVERIFY_API_KEYSecretAPI key for the eleata Claim Verifier (paid Bearer or RapidAPI key)

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmeleata-verify-mcp0.1.1

Tools

3

Saved tool list · updated 3w ago

ParameterTypeRequiredDescription
claimstringYesThe statement to check.
evidencestringYesThe source text the claim should be supported by.

Details

From the project README

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

ToolWhat it does
verify_claim(claim, evidence)Is the claim supported by the evidence? Verdict + confidence + abstained.
check_groundedness(answer, context)RAG guard: is the model's answer grounded in the retrieved context?
verify_strict(claim, evidence)Same, with a higher abstention threshold — for compliance/legal where a wrong "Supported" is costly.

Setup

{
  "mcpServers": {
    "eleata-verify": {
      "command": "npx",
      "args": ["-y", "eleata-verify-mcp"],
      "env": { "EVERIFY_API_KEY": "your_key" }
    }
  }
}

Get a key at https://eleata.io/checkout?p=verifypro (paid channel, sent as Authorization: Bearer). For the RapidAPI marketplace channel, set EVERIFY_RAPIDAPI=1 and EVERIFY_API_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 https://eleata.io/privacy/.

MIT licensed.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.