# Option 1: Zero-install with uvx (recommended for trying out)
uvx pubmed-search-mcp

# Option 2: Add as project dependency
uv add pubmed-search-mcp

# Option 3: pip install
pip install pubmed-search-mcp

from pubmed_search.api import PubMedSearchClient, PubMedSearchConfig

client = PubMedSearchClient(PubMedSearchConfig(email="your@email.com"))
result = await client.unified_search("remimazolam ICU sedation", limit=20)

print(result.articles)
print(result.source_counts)
print(result.artifact)  # artifact locator when persistence is enabled

{
  "servers": {
    "pubmed-search": {
      "type": "stdio",
      "command": "uvx",
      "args": ["pubmed-search-mcp"],
      "env": {
        "NCBI_EMAIL": "your@email.com"
      }
    }
  }
}

{
  "servers": {
    "pubmed-search": {
      "type": "stdio",
      "command": "uvx",
      "args": ["pubmed-search-mcp"],
      "env": {
        "NCBI_EMAIL": "your@email.com",
        "BROWSER_FETCH_CONFIG": "{\"enabled\":true,\"auto_enabled\":true,\"broker_url\":\"http://127.0.0.1:8766/fetch\",\"token\":\"local-dev-token\",\"allowed_hosts\":[\"jamanetwork.com\",\"*.jamanetwork.com\",\"nejm.org\",\"*.nejm.org\"]}"
      }
    }
  }
}

uv sync --extra browser-broker
uv run playwright install chromium
uv run pubmed-browser-fetch-broker --token local-dev-token

{
  "mcpServers": {
    "pubmed-search": {
      "command": "uvx",
      "args": ["pubmed-search-mcp"],
      "env": {
        "NCBI_EMAIL": "your@email.com"
      }
    }
  }
}

claude mcp add pubmed-search -- uvx pubmed-search-mcp

{
  "mcpServers": {
    "pubmed-search": {
      "command": "uvx",
      "args": ["pubmed-search-mcp"],
      "env": {
        "NCBI_EMAIL": "your@email.com"
      }
    }
  }
}

{
  "context_servers": {
    "pubmed-search": {
      "command": "uvx",
      "args": ["pubmed-search-mcp"],
      "env": {
        "NCBI_EMAIL": "your@email.com"
      }
    }
  }
}

openclaw plugins install mcp-adapter

{
  "plugins": {
    "entries": {
      "mcp-adapter": {
        "enabled": true,
        "config": {
          "servers": [
            {
              "name": "pubmed-search",
              "transport": "stdio",
              "command": "uvx",
              "args": ["pubmed-search-mcp"],
              "env": {
                "NCBI_EMAIL": "your@email.com"
              }
            }
          ]
        }
      }
    }
  }
}

openclaw gateway restart
openclaw plugins list  # Should show: mcp-adapter | loaded

{
  "mcpServers": {
    "pubmed-search": {
      "command": "uvx",
      "args": ["pubmed-search-mcp"],
      "env": {
        "NCBI_EMAIL": "your@email.com",
        "S2_API_KEY": "your_semantic_scholar_key",
        "PUBMED_SEARCH_DISABLED_SOURCES": ""
      },
      "alwaysAllow": [],
      "disabled": false
    }
  }
}

# Command
uvx pubmed-search-mcp

# With environment variable
NCBI_EMAIL=your@email.com uvx pubmed-search-mcp

# Required
NCBI_EMAIL=your@email.com          # Required by NCBI policy

# Optional - For higher rate limits
NCBI_API_KEY=your_ncbi_api_key     # Get from: https://www.ncbi.nlm.nih.gov/account/settings/
CORE_API_KEY=your_core_api_key     # Get from: https://core.ac.uk/services/api
CROSSREF_EMAIL=your@email.com      # Optional override; defaults to server/NCBI email
UNPAYWALL_EMAIL=your@email.com     # Optional override; defaults to server/NCBI email
S2_API_KEY=your_s2_api_key         # Alias: SEMANTIC_SCHOLAR_API_KEY
PUBMED_SEARCH_DISABLED_SOURCES=    # Example: semantic_scholar

# Optional - Network settings
HTTP_PROXY=http://proxy:8080       # HTTP proxy for API requests
HTTPS_PROXY=https://proxy:8080     # HTTPS proxy for API requests

# Optional - Institutional fulltext access
INSTITUTIONAL_DIRECT_FETCH=true    # Try DOI publisher pages before CORE fallback
EZPROXY_ENABLED=false              # Enable only after configuring EZPROXY_HOST + cookie
EZPROXY_HOST=ezproxy.example.edu
EZPROXY_COOKIE_FILE=/path/to/cookies.json

# Optional - Local note export
PUBMED_NOTES_DIR=/path/to/wiki/references  # save_literature_notes target folder
PUBMED_WORKSPACE_DIR=/path/to/project       # fallback: references/ under this workspace
PUBMED_DATA_DIR=~/.pubmed-search-mcp        # fallback: references/ under this data dir

┌─────────────────────────────────────────────────────────────────────────────┐
│                              AI AGENT                                        │
│                                                                              │
│   "Find papers about I10 hypertension treatment in diabetic patients"       │
│                                                                              │
└─────────────────────────────────┬───────────────────────────────────────────┘
                                  │
                                  ▼
┌─────────────────────────────────────────────────────────────────────────────┐
│                     🔄 PUBMED SEARCH MCP (MIDDLEWARE)                        │
│  ┌─────────────────────────────────────────────────────────────────────────┐│
│  │  1️⃣ VOCABULARY TRANSLATION                                              ││
│  │     • ICD-10 "I10" → MeSH "Hypertension"                                ││
│  │     • "diabetic" → MeSH "Diabetes Mellitus"                             ││
│  │     • ESpell: "hypertention" → "hypertension"                           ││
│  └─────────────────────────────────────────────────────────────────────────┘│
│  ┌─────────────────────────────────────────────────────────────────────────┐│
│  │  2️⃣ INTELLIGENT ROUTING                                                 ││
│  │     ┌──────────┐  ┌──────────┐  ┌──────────┐  ┌──────────┐             ││
│  │     │ PubMed   │  │Europe PMC│  │   CORE   │  │ OpenAlex │             ││
│  │     │  36M+    │  │   33M+   │  │  200M+   │  │  250M+   │             ││
│  │     │  (MeSH)  │  │(fulltext)│  │  (OA)    │  │(metadata)│             ││
│  │     └────┬─────┘  └────┬─────┘  └────┬─────┘  └────┬─────┘             ││
│  │          └──────────────┴──────────────┴──────────────┘                 ││
│  │                              ▼                                          ││
│  │  3️⃣ RESULT AGGREGATION: Dedupe + Rank + Enrich                         ││
│  └─────────────────────────────────────────────────────────────────────────┘│
└─────────────────────────────────┬───────────────────────────────────────────┘
                                  │
                                  ▼
┌─────────────────────────────────────────────────────────────────────────────┐
│                         UNIFIED RESULTS                                      │
│   • 150 unique papers (deduplicated from 4 sources)                          │
│   • Ranked by relevance + citation impact (RCR)                              │
│   • Full text links enriched from Europe PMC                                 │
└─────────────────────────────────────────────────────────────────────────────┘

┌─────────────────────────────────────────────────────────────────┐
│                      SEARCH ENTRY POINT                          │
├─────────────────────────────────────────────────────────────────┤
│                                                                  │
│   unified_search()          ← 🌟 Single entry for all sources    │
│        │                                                         │
│        ├── Quick search     → Direct multi-source query          │
│        ├── PICO hints       → Detects comparison, shows P/I/C/O  │
│        └── ICD expansion    → Auto ICD→MeSH conversion           │
│                                                                  │
│   Sources: PubMed · Europe PMC · CORE · OpenAlex                 │
│   Auto: Deduplicate → Rank → Enrich full-text links              │
│                                                                  │
├─────────────────────────────────────────────────────────────────┤
│   QUERY INTELLIGENCE                                             │
│                                                                  │
│   generate_search_queries() → MeSH expansion + synonym discovery │
│   parse_pico()              → Agent-provided PICO handoff        │
│   analyze_search_query()    → Query analysis without execution   │
│                                                                  │
└─────────────────────────────────────────────────────────────────┘

                        Found important paper (PMID)
                                   │
           ┌───────────────────────┼───────────────────────┐
           │                       │                       │
           ▼                       ▼                       ▼
    ┌─────────────┐        ┌─────────────┐        ┌─────────────┐
    │  BACKWARD   │        │  SIMILAR    │        │  FORWARD    │
    │  ◀──────    │        │  ≈≈≈≈≈≈     │        │  ──────▶    │
    │             │        │             │        │             │
    │ get_article │        │find_related │        │find_citing  │
    │ _references │        │ _articles   │        │ _articles   │
    │             │        │             │        │             │
    │ Foundation  │        │  Similar    │        │ Follow-up   │
    │  papers     │        │   topic     │        │  research   │
    └─────────────┘        └─────────────┘        └─────────────┘

    fetch_article_details()   → Detailed article metadata
    get_citation_metrics()    → iCite RCR, citation percentile
    build_citation_tree()     → Full network visualization (6 formats)

read_session(action="list_artifacts")
read_session(action="artifact", artifact_id="...")
read_session(action="artifact", artifact_uri="artifact://...")
read_session(action="artifact", artifact_uri="artifact://...", artifact_file="audit.json")
read_session(action="artifact", artifact_uri="artifact://...", artifact_file="query_strategy.json")
read_session(action="artifact", artifact_uri="artifact://...", artifact_file="results.json", offset=0, max_chars=200000)
read_session(action="list_artifacts", include_local_paths=true)

unified_search(query="remimazolam ICU sedation", options="counts_first")

# Agent just asks naturally - middleware handles everything
unified_search(query="remimazolam ICU sedation", limit=20)

# Or with clinical codes - auto-converted to MeSH
unified_search(query="I10 treatment in E11.9 patients")
#                     ↑ ICD-10           ↑ ICD-10
#                     Hypertension       Type 2 Diabetes

# unified_search searches as-is; detects "A vs B" pattern and shows PICO hints in metadata
unified_search(query="Is remimazolam better than propofol for ICU sedation?")
# → Multi-source keyword search + PICO hint metadata in output
# ⚠️ This does NOT auto-decompose PICO or expand MeSH!
# For structured PICO search, use the Agent workflow below

┌─────────────────────────────────────────────────────────────────────────┐
│  "Is remimazolam better than propofol for ICU sedation?"                │
└─────────────────────────────────┬───────────────────────────────────────┘
                                  │
                                  ▼
┌─────────────────────────────────────────────────────────────────────────┐
│                         parse_pico()                                     │
│  ┌─────────┐  ┌─────────┐  ┌─────────┐  ┌─────────┐                     │
│  │    P    │  │    I    │  │    C    │  │    O    │                     │
│  │  ICU    │  │remimaz- │  │propofol │  │sedation │                     │
│  │patients │  │  olam   │  │         │  │outcomes │                     │
│  └────┬────┘  └────┬────┘  └────┬────┘  └────┬────┘                     │
└───────┼────────────┼────────────┼────────────┼──────────────────────────┘
        │            │            │            │
        ▼            ▼            ▼            ▼
┌─────────────────────────────────────────────────────────────────────────┐
│              generate_search_queries() × 4 (parallel)                    │
│                                                                          │
│  P → "Intensive Care Units"[MeSH]                                        │
│  I → "remimazolam" [Supplementary Concept], "CNS 7056"                   │
│  C → "Propofol"[MeSH], "Diprivan"                                        │
│  O → "Conscious Sedation"[MeSH], "Deep Sedation"[MeSH]                   │
└─────────────────────────────────┬───────────────────────────────────────┘
                                  │
                                  ▼
┌─────────────────────────────────────────────────────────────────────────┐
│              Agent combines with Boolean logic                           │
│                                                                          │
│  (P) AND (I) AND (C) AND (O)  ← High precision                           │
│  (P) AND (I OR C) AND (O)     ← High recall                              │
└─────────────────────────────────┬───────────────────────────────────────┘
                                  │
                                  ▼
┌─────────────────────────────────────────────────────────────────────────┐
│              unified_search() (auto multi-source + dedup)                │
│                                                                          │
│  PubMed + Europe PMC + CORE + OpenAlex → Auto deduplicate & rank         │
└─────────────────────────────────────────────────────────────────────────┘

# Step 1: Agent extracts P/I/C/O, then validates the structured handoff
pico = parse_pico(
    description="Is remimazolam better than propofol for ICU sedation?",
    p="ICU patients requiring sedation",
    i="remimazolam",
    c="propofol",
    o="sedation efficacy, delirium, hypotension"
)
# Returns validation plus a ready-to-run `template: pico` pipeline.

# Step 2: Get MeSH for each element (parallel!)
generate_search_queries(topic="ICU patients")   # P
generate_search_queries(topic="remimazolam")    # I
generate_search_queries(topic="propofol")       # C
generate_search_queries(topic="sedation")       # O

# Step 3: Either pass expanded fragments back as p_query/i_query/c_query/o_query
# or let the backend pipeline use the structured P/I/C/O labels.

# Step 4: Search (backend runs O-aware precision/recall searches, dedup, rank)
unified_search(
    query="Is remimazolam better than propofol for ICU sedation?",
    pipeline=pico["pipeline"]
)

# Found landmark paper PMID: 33475315
find_related_articles(pmid="33475315")   # Similar methodology
find_citing_articles(pmid="33475315")    # Who built on this?
get_article_references(pmid="33475315")  # What's the foundation?

# Build complete research map
build_citation_tree(pmid="33475315", depth=2, output_format="mermaid")

# Research a gene
search_gene(query="BRCA1", organism="human")
get_gene_literature(gene_id="672", limit=20)

# Research a drug compound
search_compound(query="propofol")
get_compound_literature(cid="4943", limit=20)

# Export last search results
prepare_export(pmids="last", format="ris")      # → EndNote/Zotero
prepare_export(pmids="last", format="bibtex", source="local")  # → LaTeX
prepare_export(pmids="last", format="csl")      # → CSL JSON from the official NCBI Citation API
save_literature_notes(pmids="last")              # → local wiki note + Foam-compatible wikilinks + CSL JSON
save_literature_notes(pmids="last", note_format="medpaper", output_dir="./references")
save_literature_notes(pmids="last", template_file="./reference-template.md")

# Retrieve full text for a selected paper from the last search
get_fulltext(pmid="12345678", extended_sources=True)

# Include preprints alongside peer-reviewed results
unified_search(query="COVID-19 vaccine efficacy", options="preprints")
# → Main aggregated results include labelled arXiv, medRxiv, and bioRxiv preprints

# Include preprints and retain non-peer-reviewed items in main results
unified_search(query="CRISPR gene therapy", options="preprints, all_types")
# → Preprint-server crawl + non-peer-reviewed items retained in main results

# Only peer-reviewed (default behavior)
unified_search("diabetes treatment")
# → Preprints from any source automatically filtered out

# Add a research context graph preview to the same search response
unified_search("remimazolam ICU sedation", options="context_graph")

# Save a template-based pipeline through the primary facade
manage_pipeline(
  action="save",
    name="icu_sedation_weekly",
    config="template: pico\nparams:\n  P: ICU patients\n  I: remimazolam\n  C: propofol\n  O: delirium",
    tags="anesthesia,sedation",
    description="Weekly ICU sedation monitoring"
)

# Save a custom DAG pipeline
manage_pipeline(
  action="save",
    name="brca1_comprehensive",
    config="""
steps:
  - id: expand
    action: expand
    params: { topic: BRCA1 breast cancer }
  - id: pubmed
    action: search
    params: { query: BRCA1, sources: pubmed, limit: 50 }
  - id: expanded
    action: search
    inputs: [expand]
    params: { strategy: mesh, sources: pubmed,openalex, limit: 50 }
  - id: merged
    action: merge
    inputs: [pubmed, expanded]
    params: { method: rrf }
  - id: enriched
    action: metrics
    inputs: [merged]
output:
  limit: 30
  ranking: quality
"""
)

# Execute a saved pipeline
unified_search(pipeline="saved:icu_sedation_weekly")

# List & manage
manage_pipeline(action="list", tag="anesthesia")
manage_pipeline(action="load", source="brca1_comprehensive")  # Review YAML
manage_pipeline(action="history", name="icu_sedation_weekly")  # View past runs

┌─────────────────────────────────────────────────────────────────────────┐
│                        SEARCH MODE DECISION TREE                         │
├─────────────────────────────────────────────────────────────────────────┤
│                                                                          │
│   "What kind of search do I need?"                                       │
│         │                                                                │
│         ├── Know exactly what to search?                                 │
│         │   └── unified_search(query="topic keywords")                   │
│         │       → Quick, auto-routing to best sources                    │
│         │                                                                │
│         ├── Have a clinical question (A vs B)?                           │
│         │   └── Agent P/I/C/O → parse_pico() handoff                  │
│         │       → unified_search(template:pico) or expanded Boolean    │
│         │                                                                │
│         ├── Need comprehensive systematic coverage?                      │
│         │   └── generate_search_queries() → parallel search              │
│         │       → MeSH expansion, multiple strategies, merge             │
│         │                                                                │
│         └── Exploring from a key paper?                                  │
│             └── find_related/citing/references → build_citation_tree     │
│                 → Citation network, research context                     │
│                                                                          │
└─────────────────────────────────────────────────────────────────────────┘

src/pubmed_search/
├── domain/                     # Core business logic
│   └── entities/article.py     # UnifiedArticle, Author, etc.
├── application/                # Use cases
│   ├── search/                 # QueryAnalyzer, ResultAggregator
│   ├── export/                 # Citation export (RIS, BibTeX...)
│   └── session/                # SessionManager
├── infrastructure/             # External systems
│   ├── ncbi/                   # Entrez, iCite, Citation Exporter
│   ├── sources/                # Europe PMC, CORE, CrossRef...
│   └── http/                   # HTTP clients
├── presentation/               # User interfaces
│   ├── mcp_server/             # MCP tools, prompts, resources
│   │   └── tools/              # discovery, strategy, pico, export...
│   └── api/                    # Auxiliary HTTP API routes (not pubmed_search.api)
└── shared/                     # Cross-cutting concerns
    ├── exceptions.py           # Unified error handling
    └── async_utils.py          # Rate limiter, retry, circuit breaker

# Agent calls unified_search with clinical terminology
unified_search(query="I10 treatment outcomes")

# Server auto-expands to PubMed-compatible query
"(I10 OR Hypertension[MeSH]) treatment outcomes"

{
  "mesh_terms": [
    {
      "input": "remimazolam",
      "preferred": "remimazolam [Supplementary Concept]",
      "synonyms": ["CNS 7056", "ONO 2745"]
    }
  ],
  "all_synonyms": ["CNS 7056", "ONO 2745", ...],
  "suggested_queries": [
    {
      "id": "q1_title",
      "query": "(remimazolam sedation)[Title]",
      "purpose": "Exact title match - highest precision",
      "estimated_count": 8,
      "pubmed_translation": "\"remimazolam sedation\"[Title]"
    },
    {
      "id": "q3_and",
      "query": "(remimazolam AND sedation)",
      "purpose": "All keywords required",
      "estimated_count": 561,
      "pubmed_translation": "(\"remimazolam\"[Supplementary Concept] OR \"remimazolam\"[All Fields]) AND (\"sedate\"[All Fields] OR ...)"
    }
  ]
}

# Step 1: Generate SSL certificates
./scripts/generate-ssl-certs.sh

# Step 2: Start HTTPS service (Docker)
./scripts/start-https-docker.sh up

# Verify deployment
curl -k https://localhost/

{
  "mcpServers": {
    "pubmed-search": {
      "url": "https://localhost/mcp"
    }
  }
}

# Start with Streamable HTTP transport (required by Copilot Studio)
pubmed-search-mcp-http --transport streamable-http --port 8765

# Enable Copilot-compatible HTTP semantics while keeping full tool schemas
pubmed-search-mcp-http --transport streamable-http --copilot-compatible --port 8765

# Or use the dedicated script with ngrok
./scripts/start-copilot-studio.sh --with-ngrok

@software{pubmed_search_mcp,
  title = {PubMed Search MCP},
  author = {u9401066},
  url = {https://github.com/u9401066/pubmed-search-mcp}
}