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.
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.
process.env. You'll be asked to provide them before it can run.ACQ_CACHE_DIR— .opencode/acquired_docs Cache location for acquired document payloadsACQ_MAX_BYTES_HARD_CAP— 10000000 Hard upper bound on response body bytes regardless of per-call optionsACQ_PYTHON— _unset_ Optional explicit Python binary for acquisition sidecar (defaults to PaperQA venv path)MEDSCI_OLLAMA_MODEL— medgemma:latest Default Ollama model for interpretationMEDSCI_OLLAMA_TIMEOUT— 120000 Ollama request timeout in millisecondsMEDSCI_OLLAMA_URLMEDSCI_OPENALEX_EMAILMEDSCI_PROFILE— standard Hardware profile: lite, standard, or fullMEDSCI_PYTHON— Update the path in each server's environment block if your virtual environment is in a different location.MEDSCI_PYTHON_TIMEOUT— 60000 Python sidecar request timeout in millisecondsMEDSCI_SANDBOX_ARTIFACT_ROOT— sandbox-artifacts Artifact root directory for run logs/metadataMEDSCI_SANDBOX_DEFAULT_TEMPLATE— _unset_ Optional default Docker sandbox templateMEDSCI_SANDBOX_DEFAULT_TIMEOUT_SEC— 600 Default run timeout (seconds)MEDSCI_SANDBOX_MAX_TIMEOUT_SEC— 3600 Max allowed run timeout (seconds)MEDSCI_SANDBOX_PULL_TEMPLATE— missing Template pull policy: missing, always, neverMEDSCI_SANDBOX_STATUS_RETRY_ATTEMPTS— 2 Number of status retries before returning unknownMEDSCI_SANDBOX_STATUS_RETRY_BACKOFF_MS— 1000 Milliseconds between status retriesPQA_EMAIL— medsci-agent@localhost Email for NCBI API access (required by NCBI usage policy)PQA_LLM_TIMEOUT_SECONDS— 180 Timeout (seconds) for LLM and summary LLM requests via LiteLLM. Sidecar timeout auto-adjusts above this.PQA_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.MEDSCI_PRELOADPQA_LLM_MODEL— ollama/medgemma:latest LLM model PaperQA uses for summarization/answering (litellm format)PQA_OLLAMA_URLPQA_EMBEDDING_MODEL— ollama/mxbai-embed-large Embedding model PaperQA uses for document indexingPQA_LLM_BACKEND— ollama LLM backend for PaperQA: ollama (local), openrouter, or anthropic (cloud). Cloud backends skip Ollama preflight entirely.OPENROUTER_API_KEY— export ="sk-or-..." # needed for ACE MCP and cloud PaperQAANTHROPIC_API_KEY— export ="sk-ant-..." # only if using Anthropic directlyPQA_TEST_MODE[](https://m8ven.ai/mcp/omar-a-hassan-medsci-agent-1snev2)