Biolab is a remote MCP server that gives an AI agent 30 tools, among them add_evidence_to_collection, create_claim, create_evidence_collection. It answers at https://srikarjy025-biolab-mcp.hf.space/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 2 of 6 times since 11 September 2026; the last check, on 24 October 2026, succeeded.
Auditable MCP server for PubMed, Europe PMC, ClinicalTrials.gov, and bioRxiv/medRxiv queries
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
add_evidence_to_collection | Add or update a retrieval in a scientist-reviewed evidence collection. Inputs: collection_id, retrieval_id, relevance, note |
create_claim | Create a scientific claim record without asserting that it is true. Inputs: project_id, claim |
create_evidence_collection | Create a reviewed evidence collection in a project. Inputs: project_id, name, description |
create_evidence_watch | Create a saved query for explicit evidence-change monitoring. Inputs: project_id, source, query, agent_id, max_results |
create_project | Create a persistent scientist research project. Inputs: name, description |
fetch | Fetch one preserved evidence record by retrieval ID. Inputs: id |
get_artifact | Fetch an output artifact by its sha256 (text only; capped in size). Inputs: sha256 |
get_evidence_collection | Return a collection and its reviewed evidence items. Inputs: collection_id |
get_execution | Fetch one execution record, including output artifact hashes. Inputs: execution_id |
get_project_report | Return collections, claims, evidence links, watches, and events for a project. Inputs: project_id |
get_retrieval | Retrieve a full retrieval record by its retrieval_id. Args: retrieval_id: the UUID returned by search_pubmed Inputs: retrieval_id |
link_claim_evidence | Propose or record how one retrieval relates to a claim. Inputs: claim_id, retrieval_id, stance, assessment, note |
list_evidence_collections | List evidence collections, optionally within one project. Inputs: project_id |
list_evidence_events | List change events previously detected by an evidence watch. Inputs: watch_id |
list_evidence_watches | List saved evidence watches, optionally within one project. Inputs: project_id |
list_execution_tools | List runnable tools with their pinned versions, containers and devices. |
list_executions | List recent execution records, newest first. Inputs: tool, limit |
list_projects | List scientist research projects. |
replay_execution | Re-run a recorded execution and report whether its outputs reproduced. Writes nothing. Inputs: execution_id |
run_all_evidence_watches | Run all active watches and return explicit per-watch failures. |
run_evidence_watch | Run one evidence watch and record added, removed, or revised evidence. Inputs: watch_id |
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 wo Inputs: tool, inputs, agent_id, retrieval_ids |
search | Search all evidence sources for ChatGPT/Codex knowledge compatibility. Inputs: query |
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: w Inputs: category, agent_id, max_results, server |
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 st Inputs: query, agent_id, max_results |
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 Inputs: query, agent_id, max_results |
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, unipro Inputs: query, agent_id, sources, max_results |
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 Inputs: query, agent_id, max_results |
trace_claim | Trace a claim to supporting, conflicting, contextual, or insufficient evidence. Inputs: claim_id |
verify_executions | Verify the execution hash chain and that every output artifact is intact. |
Every block below points at https://srikarjy025-biolab-mcp.hf.space/mcp. Pick your client and copy.
claude mcp add --transport http biolab https://srikarjy025-biolab-mcp.hf.space/mcp
{
"mcpServers": {
"biolab": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://srikarjy025-biolab-mcp.hf.space/mcp"]
}
}
}{
"mcpServers": {
"biolab": {
"url": "https://srikarjy025-biolab-mcp.hf.space/mcp"
}
}
}{
"servers": {
"biolab": {
"type": "http",
"url": "https://srikarjy025-biolab-mcp.hf.space/mcp"
}
}
}{
"context_servers": {
"biolab": {
"url": "https://srikarjy025-biolab-mcp.hf.space/mcp"
}
}
}{
"mcpServers": {
"biolab": {
"serverUrl": "https://srikarjy025-biolab-mcp.hf.space/mcp"
}
}
}{
"mcpServers": {
"biolab": {
"url": "https://srikarjy025-biolab-mcp.hf.space/mcp"
}
}
}name: Biolab
version: 0.0.1
schema: v1
mcpServers:
- name: Biolab
type: streamable-http
url: https://srikarjy025-biolab-mcp.hf.space/mcp{
"mcpServers": {
"biolab": {
"httpUrl": "https://srikarjy025-biolab-mcp.hf.space/mcp"
}
}
}{
"mcpServers": {
"biolab": {
"type": "http",
"url": "https://srikarjy025-biolab-mcp.hf.space/mcp"
}
}
}{
"mcpServers": {
"biolab": {
"url": "https://srikarjy025-biolab-mcp.hf.space/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fsrikarjy025-biolab-mcp.hf.space%2Fmcp&type=streamable_http&id=biolab&name=Biolab
It answered our last check on 24 October 2026 in 253 ms. Over 6 checks since 11 September 2026 it answered 2. Status here comes from Neuronto's own probes, not from the publisher.
30, as returned by the server's own tools/list on 8 October 2026: add_evidence_to_collection, create_claim, create_evidence_collection, create_evidence_watch, create_project, fetch, get_artifact, get_evidence_collection, and 22 more.
It answered our last check on 24 October 2026 in 253 ms. Over 6 checks since 11 September 2026 it answered 2.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://srikarjy025-biolab-mcp.hf.space/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.srikarjy. Endpoint host: srikarjy025-biolab-mcp.hf.space. ARD identifier: urn:air:io.github.srikarjy:mcp:biolab-mcp-server.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.