Atlas / MCP servers / pascalwhoop / Medical APIs

Medical APIsSAFE

mcp/pascalwhoop/medical-apis

A collection of MCP tools for AI agents to interact with major biomedical databases

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
1 1r · 0w · 0d
Transport
streamable-http
License
MIT
Stars
23
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

[](https://pypi.org/project/medical-mcps/) [](https://www.python.org/downloads/) [](https://opensource.org/licenses/MIT) [](https://github.com/pascalwhoop/medical-mcps/actions/workflows/release.yml)

MCP server that integrates multiple biological and medical databases for research purposes.

Quick Start

Connect to Production Server

The easiest way to use this MCP server is to connect to the production deployment. All APIs are available through a unified endpoint that gives you access to all tools in one place.

Production URL: https://mcp.cloud.curiloo.com/tools/unified/mcp

Configure in Cursor (or other MCP client)

Add this to your .cursor/mcp.json (or equivalent MCP client configuration):

{
"mcpServers": {
"medical-apis": {
"url": "https://mcp.cloud.curiloo.com/tools/unified/mcp"
}
}
}

What You Get

Once connected, you'll have access to 100+ tools across 14 biological and medical APIs:

  • Pathways: Reactome, KEGG, Pathway Commons
  • Genes & Proteins: UniProt, MyGene.info, Node Normalization
  • Targets & Associations: OpenTargets Platform
  • Variants: MyVariant.info, GWAS Catalog
  • Diseases: OMIM, MyDisease.info
  • Drugs: ChEMBL, MyChem.info, OpenFDA
  • Literature: PubMed/PubTator3
  • Trials: ClinicalTrials.gov, NCI Clinical Trials
  • Knowledge Graphs: Every Cure Matrix Knowledge Graph

Example: Search for a Gene

{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "mygene_get_gene",
"arguments": {
"gene_id_or_symbol": "TP53"
}
}
}

Individual

Read from source at commit 0af78e15110bOBSERVED · 2026-10-09
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code
claude mcp add medical-mcps --env NCI_API_KEY=${NCI_API_KEY} --env OMIM_API_KEY=${OMIM_API_KEY} -- uvx medical-mcps
claude-desktop
{
  "mcpServers": {
    "medical-mcps": {
      "command": "uvx",
      "args": [
        "medical-mcps"
      ],
      "env": {
        "NCI_API_KEY": "${NCI_API_KEY}",
        "OMIM_API_KEY": "${OMIM_API_KEY}"
      }
    }
  }
}
03

Exposed tools (1)

1 read · 0 write · 0 destructive.

ToolRiskDescription
existing_toolreadreturn {
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codeWARN
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (1 observation(s))
Network
declared (7 observation(s))
Shell
none-observed
Dependencies
pinned
Secrets in source
found

Findings (3)

MEDIUMHard-coded secrets · secret.generic · CWE-798, CWE-321
tests/README.md:171
api_key: "your-real-omim-api-key"
LOWInventory / provenance · inv.hidden_file · CWE-1104
.pre-commit-config.yaml
.pre-commit-config.yaml
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWCode injection · code.deserialize · CWE-78, CWE-94, CWE-95
tests/test_response_sizes.py:36
content = yaml.load(f, Loader=SafeLoaderIgnoreUnknown)
Why it matters. deserialises untrusted bytes into live objects
Fix. use json or yaml.safe_load

Gates applied: no_behavioural_pass.

Audited 2026-10-09 · audit v0.4.1 · source sha 0af78e15110bfull audit observations/trust-audit/mcp-server/pascalwhoop__medical-apis.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-090af78e15110bSAFEB89first audit
06

Questions

What is the Medical APIs MCP server?

A collection of MCP tools for AI agents to interact with major biomedical databases

What tools does Medical APIs expose?

1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is Medical APIs safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does Medical APIs need?

It reads NCI_API_KEY and OMIM_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How does Medical APIs run?

It speaks streamable-http, so it runs as a service you connect to over the network. It is published on PyPI as medical-mcps.

How current is this page?

The grade is for one exact copy of the source (0af78e15110b), read on 2026-10-09. The repository is watched and re-audited when it changes.

Advertisement