Biolab MCP Server

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

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

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "Biolab MCP Server": {
      "url": "https://srikarjy025-biolab-mcp.hf.space/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (30)

• 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 source (1-50)

  Parameters:

  • query (required) — string
  • agent_id (required) — string
  • sources
  • max_results — integer

  Hints: read-only no · destructive no · idempotent no · open-world yes

• search

  Search all evidence sources for ChatGPT/Codex knowledge compatibility.

  Parameters:

  • query (required) — string

  Hints: read-only no · destructive no · idempotent no · open-world yes

• fetch read-only

  Fetch one preserved evidence record by retrieval ID.

  Parameters:

  • id (required) — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• create_project

  Create a persistent scientist research project.

  Parameters:

  • name (required) — string
  • description — string

  Hints: read-only no · destructive no · idempotent no · open-world no

• list_projects read-only

  List scientist research projects.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• create_evidence_collection

  Create a reviewed evidence collection in a project.

  Parameters:

  • project_id (required) — string
  • name (required) — string
  • description — string

  Hints: read-only no · destructive no · idempotent no · open-world no

• list_evidence_collections read-only

  List evidence collections, optionally within one project.

  Parameters:

  • project_id

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• add_evidence_to_collection

  Add or update a retrieval in a scientist-reviewed evidence collection.

  Parameters:

  • collection_id (required) — string
  • retrieval_id (required) — string
  • note — string
  • relevance — string

  Hints: read-only no · destructive no · idempotent no · open-world no

• get_evidence_collection read-only

  Return a collection and its reviewed evidence items.

  Parameters:

  • collection_id (required) — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• create_evidence_watch

  Create a saved query for explicit evidence-change monitoring.

  Parameters:

  • project_id (required) — string
  • source (required) — string
  • query (required) — string
  • agent_id (required) — string
  • max_results — integer

  Hints: read-only no · destructive no · idempotent no · open-world no

• list_evidence_watches read-only

  List saved evidence watches, optionally within one project.

  Parameters:

  • project_id

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• run_evidence_watch

  Run one evidence watch and record added, removed, or revised evidence.

  Parameters:

  • watch_id (required) — string

  Hints: read-only no · destructive no · idempotent no · open-world yes

• list_evidence_events read-only

  List change events previously detected by an evidence watch.

  Parameters:

  • watch_id (required) — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• run_all_evidence_watches

  Run all active watches and return explicit per-watch failures.

  Hints: read-only no · destructive no · idempotent no · open-world yes

• create_claim

  Create a scientific claim record without asserting that it is true.

  Parameters:

  • project_id (required) — string
  • claim (required) — string

  Hints: read-only no · destructive no · idempotent no · open-world no

• link_claim_evidence

  Propose or record how one retrieval relates to a claim.

  Parameters:

  • claim_id (required) — string
  • retrieval_id (required) — string
  • stance (required) — string
  • note — string
  • assessment — string

  Hints: read-only no · destructive no · idempotent no · open-world no

• trace_claim read-only

  Trace a claim to supporting, conflicting, contextual, or insufficient evidence.

  Parameters:

  • claim_id (required) — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_project_report read-only

  Return collections, claims, evidence links, watches, and events for a project.

  Parameters:

  • project_id (required) — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• 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)

  Parameters:

  • query (required) — string
  • agent_id (required) — string
  • max_results — integer

  Hints: read-only no · destructive no · idempotent no · open-world yes

• 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)

  Parameters:

  • query (required) — string
  • agent_id (required) — string
  • max_results — integer

  Hints: read-only no · destructive no · idempotent no · open-world yes

• 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)

  Parameters:

  • query (required) — string
  • agent_id (required) — string
  • max_results — integer

  Hints: read-only no · destructive no · idempotent no · open-world yes

• 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: how many preprints to retrieve (default 5) server: "biorxiv" or "medrxiv" (default "biorxiv")

  Parameters:

  • category (required) — string
  • agent_id (required) — string
  • server — string
  • max_results — integer

  Hints: read-only no · destructive no · idempotent no · open-world yes

• list_execution_tools read-only

  List runnable tools with their pinned versions, containers and devices.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• 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 was derived from, for provenance links

  Parameters:

  • tool (required) — string
  • inputs (required) — object
  • agent_id (required) — string
  • retrieval_ids

  Hints: read-only no · destructive no · idempotent no · open-world no

• get_execution read-only

  Fetch one execution record, including output artifact hashes.

  Parameters:

  • execution_id (required) — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• list_executions read-only

  List recent execution records, newest first.

  Parameters:

  • tool
  • limit — integer

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_artifact read-only

  Fetch an output artifact by its sha256 (text only; capped in size).

  Parameters:

  • sha256 (required) — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• verify_executions read-only

  Verify the execution hash chain and that every output artifact is intact.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• replay_execution read-only

  Re-run a recorded execution and report whether its outputs reproduced. Writes nothing.

  Parameters:

  • execution_id (required) — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_retrieval read-only

  Retrieve a full retrieval record by its retrieval_id. Args: retrieval_id: the UUID returned by search_pubmed

  Parameters:

  • retrieval_id (required) — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

Publisher website Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.