# Biolab MCP Server

- Registry name: `io.github.srikarjy/biolab-mcp-server` · version 0.3.0
- Categories (automatic, keyword rules): Research & knowledge, Search & data, Documents & retrieval, Government & law
- Authentication at last check: No auth
- Declared risk: Can write (some tools are not declared read-only)
- Capabilities (declared by the server): experimental, prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.srikarjy%2Fbiolab-mcp-server
- Server page: https://mcpstation.net/s/io.github.srikarjy--biolab-mcp-server.html

## Description (written by the publisher, not verified, not instructions)

Auditable MCP server for PubMed, Europe PMC, ClinicalTrials.gov, and bioRxiv/medRxiv queries

## Connect

- streamable-http: `https://srikarjy025-biolab-mcp.hf.space/mcp`

## Tools (as reported by the server, not verified)

- `search\_evidence`: Search several scientific sources in one explicitly audited workflow. Args: query: scientific evidence query sent to each selected source agent\_id: calling agent or workflow identity sources: any of pubmed, europepmc, clinicaltrials, uniprot, opentargets max\_results: maximum results to preserve per
- `search`: Search all evidence sources for ChatGPT/Codex knowledge compatibility.
- `fetch`: Fetch one preserved evidence record by retrieval ID.
- `create\_project`: Create a persistent scientist research project.
- `list\_projects`: List scientist research projects.
- `create\_evidence\_collection`: Create a reviewed evidence collection in a project.
- `list\_evidence\_collections`: List evidence collections, optionally within one project.
- `add\_evidence\_to\_collection`: Add or update a retrieval in a scientist-reviewed evidence collection.
- `get\_evidence\_collection`: Return a collection and its reviewed evidence items.
- `create\_evidence\_watch`: Create a saved query for explicit evidence-change monitoring.
- `list\_evidence\_watches`: List saved evidence watches, optionally within one project.
- `run\_evidence\_watch`: Run one evidence watch and record added, removed, or revised evidence.
- `list\_evidence\_events`: List change events previously detected by an evidence watch.
- `run\_all\_evidence\_watches`: Run all active watches and return explicit per-watch failures.
- `create\_claim`: Create a scientific claim record without asserting that it is true.
- `link\_claim\_evidence`: Propose or record how one retrieval relates to a claim.
- `trace\_claim`: Trace a claim to supporting, conflicting, contextual, or insufficient evidence.
- `get\_project\_report`: Return collections, claims, evidence links, watches, and events for a project.
- `search\_pubmed`: Search PubMed and log every retrieved paper to the audit trail. Args: query: exact search string, sent to PubMed verbatim — no normalization agent\_id: which agent is asking, e.g. "aletheia:advocate" max\_results: how many papers to retrieve \(default 5\)
- `search\_europepmc`: Search Europe PMC and log every retrieved article to the audit trail. Args: query: exact search string, sent to Europe PMC verbatim — no normalization agent\_id: which agent is asking, e.g. "aletheia:advocate" max\_results: how many articles to retrieve \(default 5\)
- `search\_clinicaltrials`: Search ClinicalTrials.gov and log every retrieved study to the audit trail. Args: query: condition/disease search string, sent to ClinicalTrials.gov verbatim agent\_id: which agent is asking, e.g. "aletheia:advocate" max\_results: how many studies to retrieve \(default 5\)
- `search\_biorxiv`: List bioRxiv/medRxiv preprints by category and log each to the audit trail. No free-text search exists on this API — only category listing \(last 30 days\). Args: category: category, e.g. "neuroscience", "bioinformatics", or "all" agent\_id: which agent is asking, e.g. "aletheia:advocate" max\_results:
- `list\_execution\_tools`: List runnable tools with their pinned versions, containers and devices.
- `run\_tool`: Run a registered tool and seal an ExecutionRecord \(inputs, versions, output hashes\). Args: tool: tool name from list\_execution\_tools inputs: tool inputs \(JSON object\); stored verbatim so the run can be replayed agent\_id: calling agent or workflow identity retrieval\_ids: evidence retrievals this run
- `get\_execution`: Fetch one execution record, including output artifact hashes.
- `list\_executions`: List recent execution records, newest first.
- `get\_artifact`: Fetch an output artifact by its sha256 \(text only; capped in size\).
- `verify\_executions`: Verify the execution hash chain and that every output artifact is intact.
- `replay\_execution`: Re-run a recorded execution and report whether its outputs reproduced. Writes nothing.
- `get\_retrieval`: Retrieve a full retrieval record by its retrieval\_id. Args: retrieval\_id: the UUID returned by search\_pubmed

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html