Skip to main content
Glama
Sign In
eleata-verify-mcp

eleata-verify-mcp

by eleata
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

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

Tool

What 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.

Related MCP server: Fact-Checker MCP Server

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.

Available Tools

3 tools
check_groundednessA

Hallucination guard for RAG / agent answers. Pass the model's generated answer and the retrieved context; returns whether the answer is grounded in the context. Treat any verdict other than 'Supported', or abstained=true, as 'ungrounded / likely hallucination' and have the agent retract or re-retrieve.

Inputs: answer (required), context (required).

verify_claimA

Fact-check a claim against a piece of evidence using natural-language inference. Returns a grounded verdict — Supported, Refuted, or Not Enough Evidence — with a confidence (0..1) and an abstained flag. Use it to check whether a statement is actually backed by a source before trusting or repeating it. If abstained is true, treat the result as 'cannot verify — do not rely'.

Inputs: claim (required), evidence (required).

verify_strictA

Same as verify_claim but with a raised abstention threshold — abstains more readily. Use when a wrong 'Supported' is costly (compliance, legal, medical-adjacent) and the agent must not over-assert.

Inputs: claim (required), evidence (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A3.7/5.0

    Scored across 3 tools

    Disambiguation2/5

    verify_claim and verify_strict are nearly identical except for an abstention threshold, making it unclear which to choose. check_groundedness overlaps in purpose (checking support in context/evidence). Agents will struggle to differentiate without additional heuristics.

    Naming Consistency3/5

    Two tools use 'verify_' (one with noun 'claim', one with adjective 'strict'), and one uses 'check_groundedness'. The verbs 'check' and 'verify' are synonymous but break pattern consistency. The mix of noun and adjective styles is acceptable but not uniform.

    Tool Count4/5

    With 3 tools, the count is slightly low but appropriate for a narrowly scoped verification server. Each tool serves a distinct mode (normal, strict, groundedness), so no tool feels superfluous.

    Completeness3/5

    Covers the core verification operations but lacks any tool for evidence retrieval, source management, or batch verification. The strict version adds nuance but also indicates incomplete coverage of confidence levels. Agents may need to work around missing functionality.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Resources

    Related MCP Connectors

    Related MCP Servers

    • tru8-mcp

      SamYatesSmith
      A
      license
      A
      quality
      C
      maintenance
      MCP server for Tru8 Evidence Research that enables AI agents to submit claims or URLs and receive source-traced evidence organized by tier and type with element decomposition and relationship mapping.
      3
      68 PyPI
      MIT

    • corroborate-mcp

      chefcohen
      A
      license
      A
      quality
      C
      maintenance
      An MCP server that evaluates claims by counting independent story origins, giving AI agents a verdict on reporting corroboration rather than truth.
      2
      67 npm
      1
      MIT

    • mcp-citation-checker

      ethanchand
      A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server that verifies whether a claim is actually supported by the source text at a given citation — independent of what the calling LLM asserts.
      MIT