Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add zamushwani/biomedical-ai-skills --skill biomedical-mcpgit clone --depth 1 https://github.com/zamushwani/biomedical-ai-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zamushwani/biomedical-ai-skills/biomedical-mcp)<a href="https://agentmods.dev/skills/zamushwani/biomedical-ai-skills/biomedical-mcp"><img src="https://agentmods.dev/badge/skills/zamushwani/biomedical-ai-skills/biomedical-mcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zamushwani/biomedical-ai-skills/biomedical-mcp"><img src="https://agentmods.dev/badge/skills/zamushwani/biomedical-ai-skills/biomedical-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.08186 |
| Opus 5 | $0.00000 | $0.04093 |
| Sonnet 5 | $0.00000 | $0.01637 |
| Haiku 4.5 | $0.00000 | $0.00819 |
Grade B, and why
biomedical-mcp scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
r = httpx.post("https://civicdb.org/api/graphql", json={"query": q}, timeout=30) Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
import httpx, urllib.parse How it starts
The opening of the file, as written. The whole thing — 664 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Biomedical MCP Servers
Building Model Context Protocol servers that give AI agents structured, tested access to biomedical databases. Covers MCP server design, the GDC REST API behind TCGA, tool design for search and retrieval, pagination and caching, and the data-shape traps that make a naive wrapper wrong. Part 1 covers TCGA/GDC, Part 2 adds GEO, and Part 3 aggregates the CIViC, OncoKB and ClinVar biomarker databases.
When to Use This Skill
Activate when the user requests:
- An MCP server exposing TCGA, GDC, GEO, or a variant database to an agent
- Programmatic TCGA data access from Python (not R)
- Tools named like
search_cancer_type,get_mutations,get_clinical - Wrapping a bioinformatics REST API for use by Claude, Cursor, or another agent
- Deciding between TCGAbiolinks (R) and the GDC REST API (Python)
- Pagination, caching, or rate-limit handling for a genomics API
- GEO dataset search, Series Matrix retrieval, or probe-to-gene mapping
- Handling NCBI E-utilities rate limits and API keys
- Aggregating CIViC, OncoKB, or ClinVar for variant clinical significance
- Reconciling variant nomenclature or evidence levels across databases
Inputs
| Input | Form | Source |
|---|---|---|
| Cancer type / project | TCGA-LUAD, primary site |
GDC projects endpoint |
| Case or sample filter | GDC filter JSON | built by the tool |
| Gene / variant | symbol, Ensembl ID, genomic change | GDC ssms endpoint |
| Auth token | file, only for controlled-access data | GDC, most data is open |
Environment
Versions verified 2026-08.
pip install "mcp[cli]" # 2.0.0 - the official Model Context Protocol SDK
pip install httpx # HTTP client for the API calls
mcp 2.0.0 is a MAJOR version and the API changed. The server class is
MCPServer, imported from mcp.server. Tutorials and older code use
`from mcp.server.fastmcp import FastMCP`; that path is from the 1.x line.
Verify against the installed version before copying an example.
1.x: from mcp.server.fastmcp import FastMCP ; mcp = FastMCP("name")
2.0: from mcp.server import MCPServer ; mcp = MCPServer("name")
The tool decorator and the type-hints-are-the-schema model are the same in
both, so most tool bodies port unchanged; the import and constructor do not.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 664 lines · 0 tokens per session scan B fb52661b6307
biomedical-mcp is a skill published in the GitHub repository zamushwani/biomedical-ai-skills (1 stars, last pushed 13d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 8,186 tokens. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
automated-soap-note-generator
Generate structured SOAP notes from clinical narratives, transcripts, or existing notes; use when the user needs de-identified clinical documentation organized into Subjective, Objective, Assessment, and Plan sections, with clear assumptions and review points.
estimate-immune-score-analysis
Use this skill to compute ESTIMATE immune-related microenvironment scores from a bulk expression matrix, generate an ESTIMATE score heatmap, and optionally generate group-wise ESTIMATE score boxplots plus significance tables when a sample group file is supplied. Trigger keywords: ESTIMATE, immune score, stromal score…
external-model-validation
Use when validating an existing prognostic risk signature on an external bulk expression cohort with survival outcomes, producing risk scores, Kaplan-Meier curves, risk distribution plots, heatmap, and time-dependent ROC curves. NOT for: model training, feature selection, nomogram construction, calibration analysis…
gsva-analysis-and-visualization
Use this skill to run GSVA or ssGSEA pathway-level differential analysis from a bulk expression matrix and a sample group file, then generate a heatmap from the saved GSVA result object. Trigger keywords: GSVA, ssGSEA, pathway enrichment, KEGG pathway analysis, MSigDB. NOT for: gene-level differential expression…
hierarchical-clustering-plot
Use when building a sample-level hierarchical clustering dendrogram from a bulk expression matrix and sample annotation table, especially for QC, batch inspection, or sample similarity assessment. Trigger keywords: hierarchical clustering, dendrogram, sample QC, batch inspection, sample similarity. NOT for…
immune-pathway-analysis
Run immune pathway GSVA or ssGSEA analysis from a bulk expression matrix, a sample group file, and a local immune Reactome gene-set table, then export differential pathway results and a heatmap for two-group comparison.