47
/ 100
1 month ago
glama

MedSci Agent

An open source biomedical research agent that provides LLMs with 28 tools for drug discovery, protein analysis, literature search, medical imaging, omics, and sandbox execution, all running locally via Ollama and MedGemma.

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find.

Install from

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
🔐
You'll be asked for 2 credentials: OPENROUTER_API_KEY, ANTHROPIC_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// required environment variables
This server reads these from process.env. You'll be asked to provide them before it can run.
configACQ_CACHE_DIR.opencode/acquired_docs Cache location for acquired document payloads
configACQ_MAX_BYTES_HARD_CAP10000000 Hard upper bound on response body bytes regardless of per-call options
configACQ_PYTHON_unset_ Optional explicit Python binary for acquisition sidecar (defaults to PaperQA venv path)
configMEDSCI_OLLAMA_MODELmedgemma:latest Default Ollama model for interpretation
configMEDSCI_OLLAMA_TIMEOUT120000 Ollama request timeout in milliseconds
configMEDSCI_OLLAMA_URL
configMEDSCI_OPENALEX_EMAIL
configMEDSCI_PROFILEstandard Hardware profile: lite, standard, or full
configMEDSCI_PYTHONUpdate the path in each server's environment block if your virtual environment is in a different location.
configMEDSCI_PYTHON_TIMEOUT60000 Python sidecar request timeout in milliseconds
configMEDSCI_SANDBOX_ARTIFACT_ROOTsandbox-artifacts Artifact root directory for run logs/metadata
configMEDSCI_SANDBOX_DEFAULT_TEMPLATE_unset_ Optional default Docker sandbox template
configMEDSCI_SANDBOX_DEFAULT_TIMEOUT_SEC600 Default run timeout (seconds)
configMEDSCI_SANDBOX_MAX_TIMEOUT_SEC3600 Max allowed run timeout (seconds)
configMEDSCI_SANDBOX_PULL_TEMPLATEmissing Template pull policy: missing, always, never
configMEDSCI_SANDBOX_STATUS_RETRY_ATTEMPTS2 Number of status retries before returning unknown
configMEDSCI_SANDBOX_STATUS_RETRY_BACKOFF_MS1000 Milliseconds between status retries
configPQA_EMAILmedsci-agent@localhost Email for NCBI API access (required by NCBI usage policy)
configPQA_LLM_TIMEOUT_SECONDS180 Timeout (seconds) for LLM and summary LLM requests via LiteLLM. Sidecar timeout auto-adjusts above this.
configPQA_QUERY_TIMEOUT_MS_(auto-calculated)_ Direct override for PaperQA total query timeout in milliseconds (caps at 540,000 ms). Overrides the automatic per-paper calculation.
configMEDSCI_PRELOAD
configPQA_LLM_MODELollama/medgemma:latest LLM model PaperQA uses for summarization/answering (litellm format)
configPQA_OLLAMA_URL
configPQA_EMBEDDING_MODELollama/mxbai-embed-large Embedding model PaperQA uses for document indexing
configPQA_LLM_BACKENDollama LLM backend for PaperQA: ollama (local), openrouter, or anthropic (cloud). Cloud backends skip Ollama preflight entirely.
🔐 secretOPENROUTER_API_KEYexport ="sk-or-..." # needed for ACE MCP and cloud PaperQA
🔐 secretANTHROPIC_API_KEYexport ="sk-ant-..." # only if using Anthropic directly
configPQA_TEST_MODE
// full audit trail
The full breakdown of what we checked, the deductions that landed, the network hosts, the dependency advisories, and concrete fix guidance is available to verified publishers.
// improvement guidance — verified publishers only
We have 1 concrete improvement we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Score](https://m8ven.ai/badge/mcp/omar-a-hassan-medsci-agent-1snev2)](https://m8ven.ai/mcp/omar-a-hassan-medsci-agent-1snev2)
commit: a3aafded47391d2dcb3bfa3496b43f79f11b5e31
code hash: 1cfa56c9870885ad64df327733fbf240ce6abc3fdbf7888bc185956fc0bac15f
verified: 6/18/2026, 11:08:29 AM
view raw JSON →