Skip to main content
Glama

Zetesis

Scientific due diligence on a claim, from inside Claude, Copilot, or any MCP host.

Zetesis takes a high-dimensional scientific or technical claim and grades it dimension by dimension against public literature, clinical trials, and filings. It returns an overall reading, cites every source by id, and, for a full evaluation, translates the science into what a commitment to the claim turns on and seals the result in an attestation anyone can re-check.

This package is a thin MCP client. It holds no keys and runs no model. Every call is proxied to the hosted engine at https://api.zetesis.science with your token.

Get a token

Free, no card, at https://api.zetesis.science/signup. The free plan gives you a handful of screening evaluations each month.

Related MCP server: biopharma-catalyst-mcp

Connect it

Claude Code:

claude mcp add zetesis --env ZETESIS_TOKEN=zk_... -- uvx --from zetesis zetesis-client

Claude Desktop (claude_desktop_config.json):

{
  "mcpServers": {
    "zetesis": {
      "command": "uvx",
      "args": ["--from", "zetesis", "zetesis-client"],
      "env": { "ZETESIS_TOKEN": "zk_..." }
    }
  }
}

Tools

  • evaluate_claim — grade a claim. depth="screen" returns the verdict directly (free tier); depth="deep" runs the full signed dossier in the background. mode="research" is science only; mode="diligence" adds the capital reading.

  • check_evaluation — get the verdict and the rendered dossier link for a deep run.

  • verify_attestation — re-check any Zetesis attestation. No account needed.

  • account_status — your plan and remaining evaluations or credits.

How it grades

It grades only what the evidence supports, cites sources by hard id (PMID, DOI, NCT, NIH grant, SEC filing), and flags gaps rather than filling them. It never invents citations. Claim text is not logged; only metadata (the routed domain, depth, counts) is kept.

Configuration

  • ZETESIS_TOKEN — your token (required for evaluations; verify works without one)

  • ZETESIS_API — override the API base (default https://api.zetesis.science)

MIT licensed. The hosted engine is a separate service.


mcp-name: io.github.reutavidan/zetesis

Install Server
A
license - permissive license
A
quality
C
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • F
    license
    -
    quality
    -
    maintenance
    A bounded evidence review engine that ingests documents, extracts evidence for a given claim, detects contradictions, and produces auditable evidence packets without hallucinations or open-web research.
  • A
    license
    A
    quality
    D
    maintenance
    Enables biopharma catalyst research by aggregating signals from ClinicalTrials.gov, PubMed, SEC EDGAR, openFDA, and Yahoo Finance, with a single tool to audit a ticker/drug combination and return a forensic verdict.
    10
    23
    4
    ISC
  • F
    license
    -
    quality
    D
    maintenance
    High-strategic intelligence platform for life sciences that enables real-time clinical trial audits, competitive landscape mapping, regulatory cross-referencing, and financial milestone correlation using the Model Context Protocol.
  • A
    license
    -
    quality
    B
    maintenance
    Enables per-claim citation verification for AI-generated text by fetching cited sources and judging whether they support the claim, with verdicts and evidence quotes.
    75
    MIT

View all related MCP servers

Related MCP Connectors

  • Verify claims with verdict, confidence & cited sources; batch verify, source checks, daily brief.

  • Fact-check claims against independent sources — fast verdict or deep multi-step investigation.

  • Citation-backed regulatory intelligence tools for explicit multi-jurisdiction packs

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/reutavidan/zetesis'

If you have feedback or need assistance with the MCP directory API, please join our Discord server