biomedmcp MCP Server

by unibio-intelligence Your server? Claim it

answering

biomedmcp is answering right now. Last checked 7 min ago. 1 083 installs a week from pypi. It exposes 13 tools. Last commit 6 Nov 2026.

Integrated public biomedical research with cited, bounded evidence.

Installs per day peak 575 · avg 36

a month agotoday

Uptime history 45 hours of history

45 hours agonow

100.0%

Uptime 24h

92 of 92 checks

Tools

read from the server

425 ms

Response time

average over 24h

1 083

Installs / week

npm and PyPI

What changed 26

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 6 November 2026. No other catalogue keeps this.

6 Nov 12 tools appeared analyze_study, build_dossier, find_related and 9 more

6 Nov 12 tools disappeared batch, capabilities, get and 9 more

6 Nov a tool description was rewritten query_source

6 Nov a tool changed the parameters it asks for query_source

What the code does

We read the source, 22 h ago · tools taken from the live server · rules 995398eba69f

Evidence

Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.

Reaches cloud metadata service src/biomedmcp/content_boundary.py:59, [пакет] src/biomedmcp/content_boundary.py:59

            or host in {"localhost", "metadata.google.internal"}

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Runs an external command src/biomedmcp/diagnostics.py:19, [пакет] src/biomedmcp/diagnostics.py:19

        process = subprocess.run(

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

We found things in this code

Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch biomedmcp and you get told the day something new turns up.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 7 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add biomedmcp --transport http https://biomedmcp.unibiointelligence.com/mcp

Settings → Connectors → Add custom connector, then paste this address

https://biomedmcp.unibiointelligence.com/mcp

~/.codex/config.toml

[mcp_servers.biomedmcp]
url = "https://biomedmcp.unibiointelligence.com/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "biomedmcp": {
      "url": "https://biomedmcp.unibiointelligence.com/mcp"
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "biomedmcp": {
      "type": "http",
      "url": "https://biomedmcp.unibiointelligence.com/mcp"
    }
  }
}

Available tools 13

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

analyze

analyze_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"}

batch

run_batch

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}}]}

build

build_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}

capabilities

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. {}

literature

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"}

quota

get_quota

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

record

get_record

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}

records

search_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}}

find_related

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"}

resolve

resolve_entity

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}

source

query_source

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"}}

trials

search_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"}}

variant

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"}

Tools removed

Tools this server used to expose. Anything built against them stopped working on the day they went.

batch

removed 6 Nov 2026

capabilities

removed 6 Nov 2026

get

removed 6 Nov 2026

literature_search

removed 6 Nov 2026

quota

removed 6 Nov 2026

relate

removed 6 Nov 2026

research

removed 6 Nov 2026

resolve

removed 6 Nov 2026

search

removed 6 Nov 2026

study_analysis

removed 6 Nov 2026

trial_search

removed 6 Nov 2026

variant_evidence

removed 6 Nov 2026

Endpoints

URL	Transport	State	Latency	Checked
https://biomedmcp.unibiointelligence.com/mcp	streamable-http	answering	419 ms	7 min ago

Alternatives to biomedmcp

same job, measured the same way

CellType UDI

by celltype

Search public biomedical datasets, measured results, papers, trials and drug evidence with sources.

answering

Needwing

by needwing

Grounded web and Agent-network research for any MCP client: answers with cited evidence.

answering

Crawdar Business Research

by crawdar

Evidence-backed public business research for agents with compact, pageable output.

21 tools answering

Project Little Weirdo

by branpastran

Deterministic public-web change observation with evidence-bound commercial interpretation.

2 tools answering

ImpactLine public research

by theguysaccount

Search public laws and implementation evidence with sources, scope limits and dated coverage.

3 tools answering

Public

by colaunched

Business ideas from real public demand, scored with dated evidence. No account needed.

4 tools answering

Veripoint — AI Company Financial Research

by veripoint

AI financial research for private and public companies, with evidence and saved workspace reports.

answering

Trust Me Bro

by trustmebro

Fact-check receipts: search published claim verdicts with cited evidence, or verify a new claim.

answering

biomedmcp — questions

Answers built from our own checks of this server.

What can biomedmcp do?

It exposes 13 tools, read directly from the server on our last check. Among them: analyze_study, build_dossier, find_related, get_capabilities, get_quota, get_record and 7 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is biomedmcp working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 425 ms. The bar chart above shows every period we have measured.

Did biomedmcp ever remove tools?

Yes. batch, capabilities, get, literature_search and 8 more are no longer exposed — we recorded the date each one disappeared. A tool vanishing usually means a breaking change for anything that depended on it.

How do I connect biomedmcp?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does biomedmcp need an API key?

No. biomedmcp completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 13 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is biomedmcp?

It answers our handshake in 425 ms on average, which is faster than 30% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.

How many people use biomedmcp?

The pypi package biomedmcp was installed 1 083 times in the last week. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is biomedmcp open source?

The code is open source: it is published under the Apache-2.0 licence, written in Python and 1 stars on GitHub. The licence covers the code in the repository, not the hosted service at biomedmcp.unibiointelligence.com, which runs on its operator's own terms.