# biomedmcp (remote · biomedmcp.unibiointelligence.com)

Integrated public biomedical research with cited, bounded evidence.

- Trust score: 60/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

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

## Channel facts

- Endpoint: `https://biomedmcp.unibiointelligence.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.2.4`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, 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.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 35/100
  - 0% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 1495 tokens (~93/item across 16 items; 13 tools + 3 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 73/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 5% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "batch" implies "execute" and declares readOnlyHint instead, contradicting what its own name says it does.
  - 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: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

## Install

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

biomedmcp is a hosted endpoint at https://biomedmcp.unibiointelligence.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http unibio-intelligence-biomedmcp 'https://biomedmcp.unibiointelligence.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "unibio-intelligence-biomedmcp": {
      "url": "https://biomedmcp.unibiointelligence.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "unibio-intelligence-biomedmcp": {
      "type": "http",
      "url": "https://biomedmcp.unibiointelligence.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.unibio-intelligence-biomedmcp]
url = "https://biomedmcp.unibiointelligence.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "unibio-intelligence-biomedmcp": {
      "type": "remote",
      "url": "https://biomedmcp.unibiointelligence.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add unibio-intelligence-biomedmcp --url 'https://biomedmcp.unibiointelligence.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  unibio-intelligence-biomedmcp:
    url: "https://biomedmcp.unibiointelligence.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "unibio-intelligence-biomedmcp": {
      "Transport": "http",
      "Url": "https://biomedmcp.unibiointelligence.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add unibio-intelligence-biomedmcp -t streamable-http -u 'https://biomedmcp.unibiointelligence.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "unibio-intelligence-biomedmcp": {
      "type": "http",
      "url": "https://biomedmcp.unibiointelligence.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## 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 60)

First indexed and scored.

## MCP tools (13)

### `search` (~115 tokens)

Find ordinary records with entity filters. Papers use literature_search; trials use trial_search. e.g. {"entity":"gene","query":"BRCA1","filters":{"species":9606}}; biomedmcp://guide

Input parameters:

- `cursor` (string|null)
- `entity` (required)
- `filters`
- `freshness`
- `limit` (integer)
- `output`: Summary bounds record excerpts; full retains source fields within the response budget. Omitted evidence has recovery resources.
- `query` (string, required)

### `get` (~106 tokens)

Read ordinary records/evidence sections; variants use variant_evidence. Sources constrain all lookups and identity dependencies. e.g. {"entity":"gene","id":"BRAF","species":9606}; biomedmcp://guide

Input parameters:

- `entity` (required)
- `freshness`
- `id` (string, required)
- `section_parameters`
- `sections` (array)
- `source_versions` (object)
- `sources` (array)
- `species` (integer)

### `literature_search` (~102 tokens)

Find papers with publication/topic/source filters; deduplicate evidence and retain source outcomes and opaque continuation. e.g. {"query":"KRAS resistance"}; biomedmcp://guide

Input parameters:

- `cursor` (string|null)
- `filters`
- `freshness`
- `limit` (integer)
- `output`: Summary bounds record excerpts; full retains source fields within the response budget. Omitted evidence has recovery resources.
- `query` (string, required)

### `trial_search` (~112 tokens)

Find public clinical trials using disease/intervention and trial-specific filters. Does not determine individual clinical eligibility. e.g. {"query":"melanoma","filters":{"status":"RECRUITING"}}; biomedmcp://guide

Input parameters:

- `cursor` (string|null)
- `filters`
- `freshness`
- `limit` (integer)
- `output`: Summary bounds record excerpts; full retains source fields within the response budget. Omitted evidence has recovery resources.
- `query` (string, required)

### `variant_evidence` (~112 tokens)

Retrieve variant evidence with assembly/transcript ambiguity preserved. Defaults: ClinVar, population, CIViC. Request predictions for AlphaMissense, or eve for MIT-licensed EVE protein scores; computational predictions retain source and uncertainty. e.g. {"id":"BRAF V600E"}; biomedmcp://guide

Input parameters:

- `assembly`
- `freshness`
- `id` (string, required)
- `section_parameters`
- `sections` (array)
- `sources` (array)

### `study_analysis` (~92 tokens)

Analyze an installed verified public study. Bundled ubi_synthetic is an invented demo; discover installed releases with capabilities(source=study). Report clinical and assayed samples separately, unique mutant samples, events and exclusions. Preserve input hashes and denominators. Private compute uses Ubi platform. e.g. {"analysis":"gene_profile","study":"ubi_synthetic","gene":"TP53"}; biomedmcp://guide

### `resolve` (~89 tokens)

Resolve aliases/ambiguity before evidence joins. One exact species-qualified symbol/ID resolves; provider score alone never establishes identity. Retrieve known unambiguous identifiers directly. e.g. {"entity":"gene","query":"HER2","species":9606}; biomedmcp://guide

Input parameters:

- `assembly`
- `entity`
- `query` (string, required)
- `species` (integer)

### `relate` (~112 tokens)

Traverse an evidence relationship. Relations: gene/drug/disease: articles,trials; variant: articles,structure; article: citations,references,recommendations,authors,entities; author: articles. e.g. {"entity":"article","id":"PMID:123","relation":"references"}; biomedmcp://guide

Input parameters:

- `assembly`
- `entity` (required)
- `id` (string, required)
- `limit` (integer)
- `relation` (string, required)
- `species` (integer)

### `research` (~89 tokens)

Dossiers retain citations/outcomes. Inspect capabilities and get further sections for completeness. e.g. {"workflow":"target_dossier","focus":"ERBB2","species":9606}; biomedmcp://guide

Input parameters:

- `assembly`
- `focus` (string, required)
- `section_parameters`
- `sections` (array|null)
- `species` (integer)
- `workflow` (required)

### `query_source` (~85 tokens)

Run advanced source operations after checking capabilities/schema. Common tasks have dedicated tools. e.g. {"source":"gtex","operation":"get_metadata","params":{"info_type":"tissues","dataset_id":"gtex_v10"}}; biomedmcp://guide

Input parameters:

- `freshness`
- `operation` (string, required)
- `params` (object)
- `source` (required)

### `batch` (~74 tokens)

Execute up to ten independent read operations with one atomic quota reservation. e.g. {"calls":[{"operation":"get","arguments":{"entity":"gene","id":"BRAF","species":9606}}]}; biomedmcp://guide

Input parameters:

- `calls` (array, required)
- `idempotency_key` (string|null)

### `capabilities` (~53 tokens)

Inspect enabled sources, workflows, sections or an advanced operation's exact schema. e.g. {}; biomedmcp://guide

Input parameters:

- `diagnose` (boolean)
- `entity`
- `source` (string|null)

### `quota` (~32 tokens)

Inspect current research allowance and reset times; sign in for higher limits. e.g. {}; biomedmcp://guide

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/unibio-intelligence-biomedmcp/biomedmcp#diagnostics

## Score history

- 2026-11-05: 60

## 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 hosted endpoint (https://biomedmcp.unibiointelligence.com/mcp).

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

biomedmcp scores 60 out of 100 on VerifyMCP. 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, get, literature_search, trial_search, variant_evidence, and 8 more. Their descriptions and schemas cost roughly 1,173 tokens of context every time the server is loaded.

### Does the biomedmcp MCP server require authentication?

No. We connected to biomedmcp without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

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

VerifyMCP ran 12 checks on biomedmcp, covering TLS certificate, Authorization, HTTPS, HSTS header and 8 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. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://biomedmcp.unibiointelligence.com/mcp
- Repository: https://github.com/unibio-intelligence/biomedmcp
- Changelog RSS feed: https://verifymcp.io/servers/unibio-intelligence-biomedmcp/biomedmcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/unibio-intelligence-biomedmcp/biomedmcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/unibio-intelligence-biomedmcp/biomedmcp.json
- HTML version of this page: https://verifymcp.io/servers/unibio-intelligence-biomedmcp/biomedmcp