# biomedmcp (pypi · biomedmcp)

Integrated public biomedical research with cited, bounded evidence.

- Trust score: 73/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `biomedmcp.unibiointelligence.com`: 60/100, [markdown](https://verifymcp.io/servers/unibio-intelligence-biomedmcp/biomedmcp.md), [page](https://verifymcp.io/servers/unibio-intelligence-biomedmcp/biomedmcp)
- oci · `ghcr.io/unibio-intelligence/biomedmcp`: 33/100, [markdown](https://verifymcp.io/servers/unibio-intelligence-biomedmcp/ghcr-io-unibio-intelligence-biomedmcp.md), [page](https://verifymcp.io/servers/unibio-intelligence-biomedmcp/ghcr-io-unibio-intelligence-biomedmcp)
- pypi · `biomedmcp`: 73/100 (this document), [markdown](https://verifymcp.io/servers/unibio-intelligence-biomedmcp/biomedmcp-2.md), [page](https://verifymcp.io/servers/unibio-intelligence-biomedmcp/biomedmcp-2)

## Channel facts

- Registry: `pypi`
- Package: `biomedmcp`
- Version: `0.2.4`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 4 of 73 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to unibio-intelligence/biomedmcp).
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 0 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 38/100
  - 0% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2131 tokens (~133/item across 16 items; 13 tools + 3 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability observed for 0 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 90/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 64% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 13 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the biomedmcp MCP server?

biomedmcp runs locally as a PyPI package, launched with uvx biomedmcp mcp --transport stdio. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add unibio-intelligence-biomedmcp -- uvx biomedmcp mcp --transport stdio
```

### Cursor

```json
{
  "mcpServers": {
    "unibio-intelligence-biomedmcp": {
      "command": "uvx",
      "args": [
        "biomedmcp",
        "mcp",
        "--transport",
        "stdio"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "unibio-intelligence-biomedmcp": {
      "command": "uvx",
      "args": [
        "biomedmcp",
        "mcp",
        "--transport",
        "stdio"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add unibio-intelligence-biomedmcp -- uvx biomedmcp mcp --transport stdio
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "unibio-intelligence-biomedmcp": {
      "type": "local",
      "command": [
        "uvx",
        "biomedmcp",
        "mcp",
        "--transport",
        "stdio"
      ],
      "enabled": true
    }
  }
}
```

### Hermes

```yaml
mcp_servers:
  unibio-intelligence-biomedmcp:
    command: "uvx"
    args: ["biomedmcp", "mcp", "--transport", "stdio"]
```

### Netclaw

```json
{
  "McpServers": {
    "unibio-intelligence-biomedmcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "biomedmcp",
        "mcp",
        "--transport",
        "stdio"
      ]
    }
  }
}
```

### Other

```json
{
  "mcpServers": {
    "unibio-intelligence-biomedmcp": {
      "command": "uvx",
      "args": [
        "biomedmcp",
        "mcp",
        "--transport",
        "stdio"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 73)

First indexed and scored.

## MCP tools (13)

### `search_records` (~185 tokens)

Search biomedical records

Search genes, proteins, drugs, diseases, phenotypes, pathways, variants, pharmacogenomics, GWAS, diagnostics, adverse events, studies, patents or authors by text; returns IDs for get_record (variants: get_variant_evidence). Papers: search_literature. Trials: search_trials. Patent search is chemistry-linked (SureChEMBL); assignee/inventor/CPC search is query_source(source=patents). e.g. {"entity":"gene","query":"BRCA1","filters":{"species":9606}}

Input parameters:

- `cursor` (string|null): next_cursor from the previous page.
- `entity` (required)
- `filters`
- `freshness`: fresh bypasses the cache.
- `limit` (integer)
- `output`: summary trims excerpts; full keeps source fields. Omitted evidence stays recoverable.
- `query` (string, required)

### `get_record` (~237 tokens)

Get record and evidence sections

Fetch one record by ID with optional evidence sections, e.g. gene expression/eqtl/diseases/druggability, drug label/safety, article fulltext, trial eligibility, protein domains/structures. Variants: get_variant_evidence. List an entity's sections with get_capabilities(entity=...). e.g. {"entity":"gene","id":"PCSK9","species":9606}

Input parameters:

- `entity` (required)
- `freshness`: fresh bypasses the cache.
- `id` (string, required): Exact ID, e.g. PCSK9, PMID:123, NCT04368728, MONDO:0007750, Q8NBP7, R-HSA-109581 or an InChIKey.
- `section_parameters`: Options keyed by requested section.
- `sections` (array): Empty returns the base record; get_capabilities(entity=...) lists sections.
- `source_versions` (object): Pin releases as {source: version}.
- `sources` (array): Restrict lookups to these source IDs.
- `species` (integer): NCBI taxon ID; 9606 is human.

### `search_literature` (~138 tokens)

Search literature

Search papers across PubMed, Europe PMC, PubTator and LitSense with date, author, journal, article-type and open-access filters. Deduplicates across sources and reports each source's outcome. Read abstracts or full text with get_record(entity=article). e.g. {"query":"PCSK9 LDL cholesterol"}

Input parameters:

- `cursor` (string|null): next_cursor from the previous page.
- `filters`
- `freshness`: fresh bypasses the cache.
- `limit` (integer)
- `output`: summary trims excerpts; full keeps source fields. Omitted evidence stays recoverable.
- `query` (string, required)

### `search_trials` (~136 tokens)

Search clinical trials

Search clinical trials (ClinicalTrials.gov, NCI) by condition, intervention, phase and recruitment status. Read arms, eligibility or outcomes with get_record(entity=trial). Does not assess an individual's eligibility. e.g. {"query":"familial hypercholesterolemia","filters":{"status":"RECRUITING"}}

Input parameters:

- `cursor` (string|null): next_cursor from the previous page.
- `filters`
- `freshness`: fresh bypasses the cache.
- `limit` (integer)
- `output`: summary trims excerpts; full keeps source fields. Omitted evidence stays recoverable.
- `query` (string, required)

### `get_variant_evidence` (~188 tokens)

Get variant evidence

Get evidence for one variant (rsID, gene + protein change, HGVS or chr:pos:ref:alt). Defaults: ClinVar, gnomAD population, CIViC; add predictions (AlphaMissense), eve, cosmic, oncokb, hotspots, gwas or cbioportal. Ambiguous assembly or transcript is reported, not guessed; predictions keep source and uncertainty. e.g. {"id":"PCSK9 R46L"}

Input parameters:

- `assembly`: Genome build for coordinate IDs.
- `freshness`: fresh bypasses the cache.
- `id` (string, required): rsID, gene + protein change (PCSK9 R46L), HGVS or chr:pos:ref:alt.
- `section_parameters`: Options keyed by requested section.
- `sections` (array)
- `sources` (array): Restrict lookups to these source IDs.

### `analyze_study` (~96 tokens)

Analyze genomics study

Analyze an installed public cancer genomics study: gene_profile, mutation_cohort, survival, compare, co_occurrence, filter_cohort, top_mutated. List installed studies with get_capabilities(source=study); ubi_synthetic is invented demo data. Report sample denominators and exclusions. Private data analysis uses the Ubi platform. e.g. {"analysis":"gene_profile","study":"ubi_synthetic","gene":"TP53"}

### `resolve_entity` (~115 tokens)

Resolve identifiers

Map a name, alias or ambiguous identifier to exact species-qualified IDs before joining evidence. Returns candidates when ambiguous; a provider match score alone is not identity. Skip when you already hold an exact ID. e.g. {"entity":"gene","query":"LDL receptor","species":9606}

Input parameters:

- `assembly`: Genome build for coordinate IDs.
- `entity`
- `query` (string, required): Name, alias, symbol or identifier.
- `species` (integer): NCBI taxon ID; 9606 is human.

### `find_related` (~149 tokens)

Find related records

List records linked to one record. gene/drug/disease: articles, trials. variant: articles, structure. article: citations, references, recommendations, authors, entities. author: articles. Record attributes are get_record sections, not relations. e.g. {"entity":"article","id":"PMID:123","relation":"references"}

Input parameters:

- `assembly`: Genome build for coordinate IDs.
- `entity` (required)
- `id` (string, required): Record ID, e.g. PCSK9, PMID:123 or openalex:A123.
- `limit` (integer)
- `relation` (string, required)
- `species` (integer): NCBI taxon ID; 9606 is human.

### `build_dossier` (~194 tokens)

Build research dossier

Build a multi-section dossier in one call: verified identity, default record sections and top related papers, with citations and per-source outcomes. Workflows: target_dossier, model_input_bundle (gene), drug_review, disease_landscape, pathway_review, variant_dossier, negative_evidence (bounded literature check; never proves absence). Add sections with get_record. e.g. {"workflow":"target_dossier","focus":"LDLR","species":9606}

Input parameters:

- `assembly`: Genome build for coordinate IDs.
- `focus` (string, required): Gene symbol, drug, disease (MONDO ID or name), pathway (R-HSA ID or exact name), variant, or topic.
- `section_parameters`: Options keyed by requested section.
- `sections` (array|null): Replace the workflow's default sections.
- `species` (integer): NCBI taxon ID; 9606 is human.
- `workflow` (required)

### `query_source` (~149 tokens)

Query source directly

Run a source-specific operation that other tools do not cover, e.g. ChEMBL bioactivities, Ensembl coordinates, PDB structure quality, OmniPath interactions, NCBI Datasets genomes, ncbi-records for GenBank/GEO/SRA. Read get_capabilities(source=...) for operations and params first. e.g. {"source":"gtex","operation":"get_metadata","params":{"info_type":"tissues","dataset_id":"gtex_v10"}}

Input parameters:

- `freshness`: fresh bypasses the cache.
- `operation` (string, required): Operation listed by get_capabilities(source=...).
- `params` (object): Arguments for that operation's schema.
- `source` (required)

### `run_batch` (~97 tokens)

Run batched reads

Run up to ten independent read calls in parallel with one quota reservation; each result keeps its own outcome. build_dossier and utilities are not batchable. e.g. {"calls":[{"operation":"get_record","arguments":{"entity":"gene","id":"PCSK9","species":9606}}]}

Input parameters:

- `calls` (array, required)
- `idempotency_key` (string|null): Reuse when retrying so quota is charged once.

### `get_capabilities` (~78 tokens)

Inspect get_capabilities

List enabled sources, entity sections, dossier workflows and source operations with exact parameter schemas. Narrow with source or entity; diagnose=true probes source health. Examples: biomedmcp://guide. e.g. {}

Input parameters:

- `diagnose` (boolean): Probe live source health (slower).
- `entity`
- `source` (string|null)

### `get_quota` (~28 tokens)

Check quota

Show remaining research allowance and reset times; signed-in accounts get higher limits. e.g. {}

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/unibio-intelligence-biomedmcp/biomedmcp-2#diagnostics

## Score history

- 2026-11-05: 73

## Common questions

### What is the biomedmcp MCP server?

biomedmcp is an MCP server listed in the public MCP registry as io.github.unibio-intelligence/biomedmcp. Integrated public biomedical research with cited, bounded evidence. This page covers its PyPI package (biomedmcp).

### Is the biomedmcp MCP server safe to use?

biomedmcp scores 73 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the biomedmcp MCP server expose?

biomedmcp exposes 13 tools: search_records, get_record, search_literature, search_trials, get_variant_evidence, and 8 more. Their descriptions and schemas cost roughly 1,790 tokens of context every time the server is loaded.

### Is the biomedmcp MCP server still maintained?

biomedmcp is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the biomedmcp MCP server under?

biomedmcp declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the biomedmcp MCP server?

VerifyMCP ran 15 checks on biomedmcp, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about biomedmcp: Stability. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- PyPI project: https://pypi.org/project/biomedmcp/
- Socket report: https://socket.dev/pypi/package/biomedmcp
- Repository: https://github.com/unibio-intelligence/biomedmcp
- Changelog RSS feed: https://verifymcp.io/servers/unibio-intelligence-biomedmcp/biomedmcp-2.xml
- Changelog JSON feed: https://verifymcp.io/servers/unibio-intelligence-biomedmcp/biomedmcp-2/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/unibio-intelligence-biomedmcp/biomedmcp-2.json
- HTML version of this page: https://verifymcp.io/servers/unibio-intelligence-biomedmcp/biomedmcp-2