Biolab MCP Server
REMOTE · SRIKARJY025-BIOLAB-MCP.HF.SPACE
Auditable MCP server for PubMed, Europe PMC, ClinicalTrials.gov, and bioRxiv/medRxiv queries
Available components
Last scanned (20 hours ago)
Scores higher than 63% of remote servers
Reachable. Last reached 18 Oct 2026.
Category Education and Research
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security74
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one. See how to fix → View diagnostics → Partial
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability58
- AI-judged instruction clarity (fair).Partial
- Tool/resource definitions use about 1464 tokens (~48/item across 30 items; 30 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management50
- Stability observed for 15 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage67
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 0% of tool parameters carry a description.Fail
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 30 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 30 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 17 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.
- 14 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.
- 10 Oct 26 +46
- Authorization: unverified → partial ▲ security
- Injection markers: unverified → pass ▲ security
- Transport: fail → pass ▲ security
- Schema quality: 1186 → 1464 ▼ functional
- Endpoint reachability: not serving MCP → reachable ▲ functional
- Tool coverage: unverified → 100 ▲ functional
- Stability: unverified → 0.23 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- New tool “get_artifact” functional
- New tool “get_execution” functional
- New tool “list_execution_tools” functional
- New tool “list_executions” functional
- New tool “replay_execution” functional
- New tool “run_tool” functional
- New tool “verify_executions” functional
- 5 Oct 26 −43
- Endpoint reachability: reachable → not serving MCP ▼ security
- Authorization: partial → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Stability: 0.03 → unverified ▼ security
- Transport: pass → fail ▼ security
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- 4 Oct 26 +1
- Stability: unverified → 0.03 ▲ functional
- 3 Oct 26 +42
- Authorization: unverified → partial ▲ security
- Injection markers: unverified → pass ▲ security
- Transport: fail → pass ▲ security
- First check of Judged manipulation: pass security
- Endpoint reachability: not serving MCP → reachable ▲ functional
- Schema quality: 102 → 51 ▲ functional
- Tool coverage: unverified → 100 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- First check of Destructive annotations: pass functional
- Schema quality: good → fair functional
- New tool “add_evidence_to_collection” functional
- New tool “create_claim” functional
- New tool “create_evidence_collection” functional
- New tool “create_evidence_watch” functional
- New tool “create_project” functional
- New tool “fetch” functional
- New tool “get_evidence_collection” functional
- New tool “get_project_report” functional
- New tool “link_claim_evidence” functional
- New tool “list_evidence_collections” functional
- New tool “list_evidence_events” functional
- New tool “list_evidence_watches” functional
- New tool “list_projects” functional
- New tool “run_all_evidence_watches” functional
- New tool “run_evidence_watch” functional
- New tool “search” functional
- New tool “search_evidence” functional
- New tool “trace_claim” functional
- 28 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 18 Oct 2026 · Probed https://srikarjy025-biolab-mcp.hf.space/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=hf.space | CN=Amazon RSA 2048 M04,O=Amazon,C=US | 27 Sept 2026 | 12 Apr 2027 | RSA 2048 | SHA256-RSA | f51719dcdf7239b73ac39d3e38d8e9d |
| SANs: hf.space, *.hf.space | ||||||
| CN=Amazon RSA 2048 M04,O=Amazon,C=US (CA) | CN=Amazon Root CA 1,O=Amazon,C=US | 23 Aug 2022 | 23 Aug 2030 | RSA 2048 | SHA256-RSA | 773124f2a952e3ed18a58bdb85d1bc0ce5f27 |
| CN=Amazon Root CA 1,O=Amazon,C=US (CA) | CN=Starfield Services Root Certificate Authority - G2,O=Starfield Technologies\, Inc.,L=Scottsdale,ST=Arizona,C=US | 25 May 2015 | 31 Dec 2037 | RSA 2048 | SHA256-RSA | 67f944a2a27cdf3fac2ae2b01f908eeb9c4c6 |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of srikarjy025-biolab-mcp.hf.space. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| space. | present | 51168 | 13 | Verified |
| hf.space. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://srikarjy025-biolab-mcp.hf.space/mcp | Verified | 200 | |
| http (plaintext) | http://srikarjy025-biolab-mcp.hf.space/mcp | HTTPS enforced | 301 | https://srikarjy025-biolab-mcp.hf.space:443/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
add_evidence_to_collection ~53
Add or update a retrieval in a scientist-reviewed evidence collection.
| Name | Type | Req | Description |
|---|---|---|---|
| collection_id | string | yes | – |
| note | string | – | – |
| relevance | string | – | – |
| retrieval_id | string | yes | – |
No output schema declared.
No examples provided.
create_claim ~35
Create a scientific claim record without asserting that it is true.
| Name | Type | Req | Description |
|---|---|---|---|
| claim | string | yes | – |
| project_id | string | yes | – |
No output schema declared.
No examples provided.
create_evidence_collection ~41
Create a reviewed evidence collection in a project.
| Name | Type | Req | Description |
|---|---|---|---|
| description | string | – | – |
| name | string | yes | – |
| project_id | string | yes | – |
No output schema declared.
No examples provided.
create_evidence_watch ~58
Create a saved query for explicit evidence-change monitoring.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | – |
| max_results | integer | – | – |
| project_id | string | yes | – |
| query | string | yes | – |
| source | string | yes | – |
No output schema declared.
No examples provided.
create_project ~29
Create a persistent scientist research project.
| Name | Type | Req | Description |
|---|---|---|---|
| description | string | – | – |
| name | string | yes | – |
No output schema declared.
No examples provided.
fetch ~23
Fetch one preserved evidence record by retrieval ID.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | – |
No output schema declared.
No examples provided.
get_artifact ~33
Fetch an output artifact by its sha256 (text only; capped in size).
| Name | Type | Req | Description |
|---|---|---|---|
| sha256 | string | yes | – |
No output schema declared.
No examples provided.
get_evidence_collection ~27
Return a collection and its reviewed evidence items.
| Name | Type | Req | Description |
|---|---|---|---|
| collection_id | string | yes | – |
No output schema declared.
No examples provided.
get_execution ~26
Fetch one execution record, including output artifact hashes.
| Name | Type | Req | Description |
|---|---|---|---|
| execution_id | string | yes | – |
No output schema declared.
No examples provided.
get_project_report ~33
Return collections, claims, evidence links, watches, and events for a project.
| Name | Type | Req | Description |
|---|---|---|---|
| project_id | string | yes | – |
No output schema declared.
No examples provided.
get_retrieval ~44
Retrieve a full retrieval record by its retrieval_id. Args: retrieval_id: the UUID returned by search_pubmed
| Name | Type | Req | Description |
|---|---|---|---|
| retrieval_id | string | yes | – |
No output schema declared.
No examples provided.
link_claim_evidence ~59
Propose or record how one retrieval relates to a claim.
| Name | Type | Req | Description |
|---|---|---|---|
| assessment | string | – | – |
| claim_id | string | yes | – |
| note | string | – | – |
| retrieval_id | string | yes | – |
| stance | string | yes | – |
No output schema declared.
No examples provided.
list_evidence_collections ~26
List evidence collections, optionally within one project.
| Name | Type | Req | Description |
|---|---|---|---|
| project_id | – | – | – |
No output schema declared.
No examples provided.
list_evidence_events ~28
List change events previously detected by an evidence watch.
| Name | Type | Req | Description |
|---|---|---|---|
| watch_id | string | yes | – |
No output schema declared.
No examples provided.
list_evidence_watches ~27
List saved evidence watches, optionally within one project.
| Name | Type | Req | Description |
|---|---|---|---|
| project_id | – | – | – |
No output schema declared.
No examples provided.
list_execution_tools ~21
List runnable tools with their pinned versions, containers and devices.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_executions ~30
List recent execution records, newest first.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | – |
| tool | – | – | – |
No output schema declared.
No examples provided.
list_projects ~13
List scientist research projects.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
replay_execution ~31
Re-run a recorded execution and report whether its outputs reproduced. Writes nothing.
| Name | Type | Req | Description |
|---|---|---|---|
| execution_id | string | yes | – |
No output schema declared.
No examples provided.
run_all_evidence_watches ~23
Run all active watches and return explicit per-watch failures.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
run_evidence_watch ~32
Run one evidence watch and record added, removed, or revised evidence.
| Name | Type | Req | Description |
|---|---|---|---|
| watch_id | string | yes | – |
No output schema declared.
No examples provided.
run_tool ~114
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
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | – |
| inputs | object | yes | – |
| retrieval_ids | – | – | – |
| tool | string | yes | – |
No output schema declared.
No examples provided.
search ~27
Search all evidence sources for ChatGPT/Codex knowledge compatibility.
| Name | Type | Req | Description |
|---|---|---|---|
| query | string | yes | – |
No output schema declared.
No examples provided.
search_biorxiv ~160
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")
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | – |
| category | string | yes | – |
| max_results | integer | – | – |
| server | string | – | – |
No output schema declared.
No examples provided.
search_clinicaltrials ~104
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)
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | – |
| max_results | integer | – | – |
| query | string | yes | – |
No output schema declared.
No examples provided.
search_europepmc ~102
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)
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | – |
| max_results | integer | – | – |
| query | string | yes | – |
No output schema declared.
No examples provided.
search_evidence ~112
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)
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | – |
| max_results | integer | – | – |
| query | string | yes | – |
| sources | – | – | – |
No output schema declared.
No examples provided.
search_pubmed ~100
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)
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | – |
| max_results | integer | – | – |
| query | string | yes | – |
No output schema declared.
No examples provided.
trace_claim ~30
Trace a claim to supporting, conflicting, contextual, or insufficient evidence.
| Name | Type | Req | Description |
|---|---|---|---|
| claim_id | string | yes | – |
No output schema declared.
No examples provided.
verify_executions ~23
Verify the execution hash chain and that every output artifact is intact.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
How do I install the Biolab MCP Server server?
Biolab MCP Server is a hosted endpoint at https://srikarjy025-biolab-mcp.hf.space/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · srikarjy025-biolab-mcp.hf.space
claude mcp add --transport http srikarjy-biolab-mcp-server 'https://srikarjy025-biolab-mcp.hf.space/mcp'
What is the Biolab MCP Server server?
Biolab MCP Server is listed in the public MCP registry as io.github.srikarjy/biolab-mcp-server. Auditable MCP server for PubMed, Europe PMC, ClinicalTrials.gov, and bioRxiv/medRxiv queries. This page covers its hosted endpoint (https://srikarjy025-biolab-mcp.hf.space/mcp).
Is the Biolab MCP Server server safe to use?
Biolab MCP Server scores 72 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Biolab MCP Server server expose?
Biolab MCP Server exposes 30 tools: search_evidence, search, fetch, create_project, list_projects, and 25 more. Their descriptions and schemas cost roughly 1,464 tokens of context every time the server is loaded.
Does the Biolab MCP Server server require authentication?
No. We connected to Biolab MCP Server without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Biolab MCP Server server still maintained?
Biolab MCP Server is still listed as active in the MCP registry. We last reached this channel on 18 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.