Aletheia Advocate Agent
    ↓  MCP tool call (e.g. search_pubmed)
Biolab MCP Server
    ↓  HTTP
Source API (PubMed, Europe PMC, ClinicalTrials.gov, bioRxiv/medRxiv)
    ↓  paper
Biolab writes retrieval record to database
    ↓  paper + retrieval_id
Back to Advocate Agent

pipx install biolab-mcp
# or
pip install biolab-mcp

# Download from GitHub Releases
curl -L https://github.com/srikarjy/biolab-mcp/releases/latest/download/biolab_darwin_arm64.tar.gz | tar xz
./biolab search "BRCA1 pancreatic cancer" --max 3

docker run -v $(pwd)/data:/data ghcr.io/srikarjy/biolab-mcp:latest

brew tap srikarjy/tap
brew install biolab

# Search PubMed
biolab search "BRCA1 pancreatic cancer" --max 5

# Search Europe PMC
biolab search-europepmc "BRCA1 pancreatic cancer" --max 5

# Search ClinicalTrials.gov
biolab search-clinicaltrials "pancreatic cancer" --max 5

# List bioRxiv preprints (no free-text search - API limitation)
biolab search-biorxiv neuroscience --max 10
biolab search-biorxiv all --server medrxiv --max 10

# Retrieve full audit record
biolab get <retrieval_id>

# List recent retrievals
biolab list --source pubmed --limit 10

# Export for analysis
biolab export evidence.jsonl --source clinicaltrials

# Run demo
biolab demo --query "BRCA1 pancreatic cancer"

// Search any source
{"name": "search_pubmed", "arguments": {"query": "BRCA1 pancreatic cancer", "agent_id": "aletheia:advocate", "max_results": 5}}
{"name": "search_europepmc", "arguments": {"query": "BRCA1 pancreatic cancer", "agent_id": "aletheia:advocate", "max_results": 5}}
{"name": "search_clinicaltrials", "arguments": {"query": "pancreatic cancer", "agent_id": "aletheia:advocate", "max_results": 5}}
{"name": "search_biorxiv", "arguments": {"category": "neuroscience", "agent_id": "aletheia:advocate", "max_results": 5, "server": "biorxiv"}}

// Retrieve full audit record (works for ALL sources)
{"name": "get_retrieval", "arguments": {"retrieval_id": "uuid-from-search"}}

from biolab.pubmed_client import search_and_fetch
from biolab.retrieval_log import write_retrieval, get_retrieval
from biolab.db import connect

conn = connect("biolab.db")
papers = search_and_fetch("BRCA1 pancreatic cancer", 3)
for p in papers:
    record = write_retrieval(conn, query="...", pmid=p.pmid, ...)
    print(record.retrieval_id)

CREATE TABLE retrievals (
    retrieval_id     TEXT PRIMARY KEY,  -- UUID
    source           TEXT NOT NULL,     -- "pubmed", "europepmc", "clinicaltrials", "biorxiv"
    external_id      TEXT NOT NULL,     -- PMID, NCT ID, DOI, etc.
    query_text       TEXT NOT NULL,     -- exact query sent to source
    retrieved_at     TEXT NOT NULL,     -- ISO 8601 UTC
    agent_id         TEXT NOT NULL,     -- e.g. "aletheia:advocate"
    source_metadata  TEXT NOT NULL,     -- JSON: source-specific fields
    raw_response     TEXT NOT NULL,     -- verbatim XML/JSON from source
    snapshot         TEXT NOT NULL,     -- JSON: structured fields (title, abstract, authors, journal, DOI, pub types, MeSH/conditions)
    response_hash    TEXT NOT NULL      -- SHA-256 of raw_response
);

biolab/
├── cli.py              # Typer CLI (search, get, list, export, demo)
├── server.py           # FastMCP server (5 tools)
├── db.py               # SQLite + schema
├── models.py           # RetrievalRecord dataclass
├── retrieval_log.py    # Only writer + background queue
├── pubmed_client.py    # PubMed E-utilities wrapper
├── europepmc/          # Europe PMC adapter
├── clinicaltrials/     # ClinicalTrials.gov adapter
└── biorxiv/            # bioRxiv/medRxiv adapter

# Python
pip install -e .[dev]
pytest tests/ -v

# Go
cd go-biolab
go test ./...
go build -o biolab ./cmd/cli
go build -o biolab-server ./cmd/server