eleata Claim Verifier

io.github.hernaninversoPublished by GitHub account hernaninversov0.1.1Updated Oct 24, 2026

Grounding/hallucination guard: verify a claim against evidence (Supported/Refuted/NEE).

VerifiedSTDIODesktop onlyKnowledge & MemoryAI & ML

Overview

AI-generated overview

Checks whether a claim is supported by given evidence, returning Supported, Refuted, or Not Enough Evidence.

What you can do
A grounding and hallucination guardrail that wraps a hosted natural-language inference service. Its verify_claim tool takes a claim and evidence and returns a verdict, a confidence value, and an abstained flag for low-confidence cases. check_groundedness checks whether a model answer is grounded in retrieved context, and verify_strict applies a higher abstention threshold for compliance or legal use.
When to use it
Use it before an agent trusts or repeats a statement, or as a RAG hallucination guard that checks an answer against its source. The strict variant suits compliance or legal settings where a wrong Supported verdict is costly.
Requirements
Runs locally as an npm package via npx, so Node.js is needed. It requires a paid API key supplied in the EVERIFY_API_KEY environment variable, and network access to the hosted API. The RapidAPI channel additionally needs EVERIFY_RAPIDAPI and EVERIFY_API_BASE.
Before you install
The claim and evidence are sent to a hosted third-party API, so do not submit confidential text. A paid key is required. Confidence is uncalibrated on public channels, so rely on the verdict and the abstained flag rather than the raw number, and treat anything other than Supported as do-not-rely.

Installation

In SourceWeft

  1. Open eleata Claim Verifier in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

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

json
{  "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.

Source: README.md at commit 2963a42

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.1LatestSep 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.