MCP Servers

Tools your AI can call, and check.

Five open-source Model Context Protocol servers for evidence-grounded work in pharma and healthcare: live literature and drug labels, a privacy boundary for clinical text, and deterministic checks that an answer is actually supported by its source.

  • 5 servers, all open source
  • Listed in Anthropic’s MCP Directory
  • Published to the official MCP Registry
  • No LLM-as-judge in any check
The servers

Install one, or all five.

Each runs locally over stdio with npx. They work with Claude Desktop, Claude Code, Cursor and any other MCP client.

Redacta

Privacy

A privacy boundary for clinical text.

Pseudonymises patient identifiers before the model sees them. The reversal map stays inside the server process, so the agent you’re protecting the data from never sees it. Output can be checked for identifiers that reappeared, so the boundary is verified rather than assumed.

  • protect
  • release_to_file
  • check_output
  • discard_session
npx -y redacta-mcp
OverviewGitHubnpm

PubCrawl

Evidence

Real papers. Real labels. Real citations.

Live access to PubMed, Europe PMC, US and UK drug labelling and ClinicalTrials.gov. Fourteen tools, no model in any of them, and every result carries its PMID, NCT ID or DOI. compare_labels pairs US and UK label sections so market differences are visible, not assumed.

  • search_pubmed
  • get_full_text
  • search_trials
  • get_uspi
  • get_smpc
  • compare_labels
  • +8 more
npx -y @pharmatools/pubcrawl
OverviewGitHubnpm

StudyDiff

Evidence

Why do two studies disagree?

Extracts each study’s design, shows which methodological dimensions differ and which are identical (so ruled out), and grounds every value in a verbatim quote from the source. It never picks a winner. Fields it can’t ground come back as not reported, never guessed.

  • compare_studies
  • compare_example
  • list_examples
npx -y studydiff-mcp
Live demoGitHubnpm

OpenGATE

Verification

Let an agent check its own answer before it replies.

One tool, check_grounding, backed by OpenGATE’s deterministic grounding check. Required facts must appear, every number must trace to the context, and unanswerable questions must be declined, not fabricated. Reproducible verdicts with no LLM-as-judge.

  • check_grounding
npx -y @pharmatools/opengate-mcp
OverviewGitHubnpm

Groundwork

Deployment

Is this document-QA system ready to ship?

Runs Groundwork’s deployment-readiness gate from inside a conversation: check a whole repo, a single answer for grounding, or a single extracted record against its schema, or scaffold the evaluation harness. A strong floor, not a safety certificate, and it says so.

  • check_readiness
  • check_answer_grounding
  • check_extraction
  • scaffold_harness
  • cost_summary
npx -y @pharmatools/groundwork mcp
OverviewGitHubnpm
Quick install

All five in one config.

Paste into claude_desktop_config.json, .mcp.json or your client’s equivalent. StudyDiff needs an ANTHROPIC_API_KEY for live comparisons; its cached examples run without one.

mcp.json
{
  "mcpServers": {
    "redacta":    { "command": "npx", "args": ["-y", "redacta-mcp"] },
    "pubcrawl":   { "command": "npx", "args": ["-y", "@pharmatools/pubcrawl"] },
    "studydiff":  { "command": "npx", "args": ["-y", "studydiff-mcp"] },
    "opengate":   { "command": "npx", "args": ["-y", "@pharmatools/opengate-mcp"] },
    "groundwork": { "command": "npx", "args": ["-y", "@pharmatools/groundwork", "mcp"] }
  }
}

Claude Code: claude mcp add pubcrawl -- npx -y @pharmatools/pubcrawl, and the same pattern for the others.

How they’re built

Built to be checked, not trusted.

Sources, not memory

Results come from the primary source at call time and carry the identifier you need to verify them: PMID, NCT ID, DOI or a verbatim quote.

Deterministic checks

Grounding and readiness verdicts come from rule-based checks, not another model’s opinion, so the same input gives the same answer every time.

A human stays in the loop

These are decision support for regulated work. Outputs are designed to be reviewed by a qualified person before anyone relies on them.

If you’re an AI agent

The machine-readable version of this page, with directives, tool schemas and a manifest, is at /agents. There’s a plain-text summary at /llms.txt.