Biolab MCP Server
Auditable MCP server for PubMed, Europe PMC, ClinicalTrials.gov, and bioRxiv/medRxiv queries
Connect it
Settings → Connectors → Add custom connector
URL: https://srikarjy025-biolab-mcp.hf.space/mcpSettings → Apps & Connectors → Advanced → Developer mode
Create connector with URL: https://srikarjy025-biolab-mcp.hf.space/mcp{
"mcpServers": {
"biolab-mcp-server": {
"url": "https://srikarjy025-biolab-mcp.hf.space/mcp"
}
}
}claude mcp add --transport http biolab-mcp-server https://srikarjy025-biolab-mcp.hf.space/mcp{
"servers": {
"biolab-mcp-server": {
"type": "http",
"url": "https://srikarjy025-biolab-mcp.hf.space/mcp"
}
}
}30 tools, verified live
search_evidenceSearch 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)
searchSearch all evidence sources for ChatGPT/Codex knowledge compatibility.
fetchread-onlyFetch one preserved evidence record by retrieval ID.
create_projectCreate a persistent scientist research project.
list_projectsread-onlyList scientist research projects.
create_evidence_collectionCreate a reviewed evidence collection in a project.
list_evidence_collectionsread-onlyList evidence collections, optionally within one project.
add_evidence_to_collectionAdd or update a retrieval in a scientist-reviewed evidence collection.
get_evidence_collectionread-onlyReturn a collection and its reviewed evidence items.
create_evidence_watchCreate a saved query for explicit evidence-change monitoring.
list_evidence_watchesread-onlyList saved evidence watches, optionally within one project.
run_evidence_watchRun one evidence watch and record added, removed, or revised evidence.
list_evidence_eventsread-onlyList change events previously detected by an evidence watch.
run_all_evidence_watchesRun all active watches and return explicit per-watch failures.
create_claimCreate a scientific claim record without asserting that it is true.
link_claim_evidencePropose or record how one retrieval relates to a claim.
trace_claimread-onlyTrace a claim to supporting, conflicting, contextual, or insufficient evidence.
get_project_reportread-onlyReturn collections, claims, evidence links, watches, and events for a project.
search_pubmedSearch PubMed and log every retrieved paper to the audit trail. Args: query: exact search string, sent to PubMed verbatim â no normalization agent_id: which agent is asking, e.g. "aletheia:advocate" max_results: how many papers to retrieve (default 5)
search_europepmcSearch Europe PMC and log every retrieved article to the audit trail. Args: query: exact search string, sent to Europe PMC verbatim â no normalization agent_id: which agent is asking, e.g. "aletheia:advocate" max_results: how many articles to retrieve (default 5)
search_clinicaltrialsSearch 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_biorxivList bioRxiv/medRxiv preprints by category and log each to the audit trail. No free-text search exists on this API â 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: "bior
list_execution_toolsread-onlyList runnable tools with their pinned versions, containers and devices.
run_toolRun 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
get_executionread-onlyFetch one execution record, including output artifact hashes.
list_executionsread-onlyList recent execution records, newest first.
get_artifactread-onlyFetch an output artifact by its sha256 (text only; capped in size).
verify_executionsread-onlyVerify the execution hash chain and that every output artifact is intact.
replay_executionread-onlyRe-run a recorded execution and report whether its outputs reproduced. Writes nothing.
get_retrievalread-onlyRetrieve a full retrieval record by its retrieval_id. Args: retrieval_id: the UUID returned by search_pubmed
Alternatives in Developer Tools
Compare →MIMiroOfficialA
Official Miro MCP server - Supports context to code and creating diagrams, docs, and data tables.
Context7A
Up-to-date code docs for any prompt
NENetdataA
Real-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.
OMOmnaraA
Deploy durable AI agents with Omnara, an open-source managed-agent platform.
RDRevoGrid DataGrid MCPA
Token-free MCP server for structured RevoGrid Core, Pro, and Enterprise knowledge retrieval.
RDRevoGrid DataGrid MCP ProA
Hosted Pro MCP server for RevoGrid DataGrid docs, examples, feature checks, and migration guidance.