MCP Servers

Tools your AI can call, and check

Six open-source Model Context Protocol servers. Five 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. And one for the water and energy cost of AI itself.

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

One question, one real answer.

Each example below is genuine output from the server, captured in October 2026 and trimmed for length. Pick a server.

You ask

“Summarise this clinic note, but protect the patient’s details first.”

Claude calls
redacta.protect(text: "Patient: Margaret Ellison, DOB 14/03/1952, NHS number 943 476 5919. Seen by Dr Patel… Lives at OX7 5QA, tel 07700 900123…")

The model only ever sees the tokens. The map that reverses them stays inside the server. The clinician’s name is kept, because it isn’t a patient identifier. (Fictional patient.)

Returns

Patient: [PATIENT_NAME_1], DOB [DATE_OF_BIRTH_1], NHS number [NHS_NUMBER_1]. Seen by Dr Patel at the respiratory clinic. Lives at [POSTCODE_1], tel [PHONE_1]. Ongoing COPD; started ensifentrine 3 mg nebulised twice daily.

5identifiers replaced
0left over (self-check)
0map entries returned
The servers

Install one, or all six.

Five run locally over stdio with npx. AI Footprint is hosted: connect by URL, with nothing to install. All six 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
API key
None
Network calls
NoneEverything stays in the server process
npx -y redacta-mcp

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
API key
NoneOptional free NCBI key for higher PubMed limits
Network calls
Public sources onlyPubMed, Europe PMC, DailyMed, emc, ClinicalTrials.gov
npx -y @pharmatools/pubcrawl

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
API key
AnthropicLive comparisons only; built-in examples need none
Network calls
PubMed and AnthropicBuilt-in examples run offline
npx -y studydiff-mcp

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
API key
None
Network calls
NoneDeterministic, runs in the server process
npx -y @pharmatools/opengate-mcp

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
API key
NoneFor the checks themselves
Network calls
None of its ownThe readiness gate calls your system via its adapter
npx -y @pharmatools/groundwork mcp

AI Footprint

Sustainability

How much water and energy does AI use?

Four tools built on the calculator’s published methodology: energy first from 2025–26 vendor disclosures, water derived from it, onsite or comprehensive boundary. Estimate chat use, put any volume of water in context, or estimate an agent session from its token counts. Pure arithmetic, no model in any tool, and tests keep it identical to the page.

  • estimate_ai_footprint
  • get_methodology
  • compare_water_use
  • estimate_session_footprint
API key
None
Transport
Remote, streamable HTTPRead-only, rate-limited, inputs not logged
https://footprint.pharmatools.ai/mcp

Not an MCP client? The same tools are plain GET endpoints: try one.

Install

Pick your client.

The five npx servers need Node.js 20 or later. AI Footprint needs nothing installed. Restart your client after adding them.

Settings → Developer → Edit Config, then paste into claude_desktop_config.json. Redacta can also be added in one click from Anthropic’s directory.

claude_desktop_config.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"] }
  }
}

AI Footprint is a remote server, so it goes in through Settings → Connectors → Add custom connector instead. Paste https://footprint.pharmatools.ai/mcp.

In your environment

Or run it inside your own cloud.

For teams that need tools inside their own cloud project, behind their own sign-in, rather than installed on laptops. PubCrawl ships as a container that serves MCP over HTTP, and the steps below were run end to end on Google Cloud in November 2026.

  1. Build it anywhere

    A non-root image with a health check that shuts down cleanly when the platform stops it. CI builds and tests it on every push.

    terminal
    git clone https://github.com/nickjlamb/pubcrawl && cd pubcrawl
    docker build -t pubcrawl . && docker run -p 8080:8080 pubcrawl
  2. Put your sign-in in front

    Deployed to Cloud Run with authentication required, requests without a Google identity are refused before they reach the server. PubCrawl holds no credentials of its own.

    terminal
    gcloud beta run deploy pubcrawl --source . \
      --project=PROJECT_ID --region=REGION \
      --no-allow-unauthenticated --functional-type=mcp-server
  3. Register it for your agents

    Agent Registry can’t read tools from a server that requires sign-in, so PubCrawl ships a tool spec generated from its own code, and a test fails if the two drift apart.

    terminal
    gcloud agent-registry services create pubcrawl-mcp \
      --project=PROJECT_ID --location=REGION \
      --mcp-server-spec-type=tool-spec \
      --mcp-server-spec-content=deploy/agent-registry/toolspec.json \
      --interfaces=url=SERVICE_URL/mcp,protocolBinding=jsonrpc

PubCrawl is the first of the six packaged this way. Redacta’s privacy gateway also runs self-hosted, on Kubernetes.

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.