FastMCP server template — replace this with your description
Project description
scholar-mcp
A FastMCP server providing structured academic literature access via Semantic Scholar, with OpenAlex enrichment and optional docling-serve PDF conversion.
Features
Search & Retrieval
search_papers— full-text search with year, field-of-study, venue, and citation-count filtersget_paper— fetch full metadata for a single paper by DOI, S2 ID, arXiv ID, ACM ID, or PubMed IDget_author— fetch author profile and publications, or search by name
Citation Graph
get_citations— forward citations (papers that cite a given paper)get_references— backward references (papers cited by a given paper)get_citation_graph— BFS traversal returning nodes + edges up to configurable depthfind_bridge_papers— shortest citation path between two papers
Recommendations
recommend_papers— paper recommendations from positive (and optional negative) examples
Utility
batch_resolve— resolve up to 100 identifiers to full metadata in one callenrich_paper— augment S2 metadata with OpenAlex fields (open-access URL, topics, concepts)
PDF Conversion (requires docling-serve)
fetch_paper_pdf— download open-access PDF for a paperconvert_pdf_to_markdown— convert local PDF to Markdown via docling-servefetch_and_convert— full pipeline: fetch OA PDF → convert to Markdown
Cache Management (CLI)
scholar-mcp cache stats— show cache row counts and file sizescholar-mcp cache clear [--older-than N]— clear cache entries
Quick Start
With uvx
# stdio transport (default, for Claude Desktop / MCP clients)
SCHOLAR_MCP_S2_API_KEY=your-key uvx --from pvliesdonk-scholar-mcp scholar-mcp serve
# HTTP transport
uvx --from pvliesdonk-scholar-mcp scholar-mcp serve --transport http --port 8000
Note: The PyPI package is
pvliesdonk-scholar-mcp. The CLI command installed isscholar-mcp.
With Docker
docker run -e SCHOLAR_MCP_S2_API_KEY=your-key \
-v scholar-mcp-data:/data/scholar-mcp \
ghcr.io/pvliesdonk/scholar-mcp:latest
Configuration
All settings are controlled via environment variables with the SCHOLAR_MCP_ prefix.
| Variable | Default | Description |
|---|---|---|
SCHOLAR_MCP_S2_API_KEY |
— | Semantic Scholar API key (optional; unauthenticated rate limit applies without it) |
SCHOLAR_MCP_READ_ONLY |
true |
If true, write-tagged tools (fetch_paper_pdf) are hidden |
SCHOLAR_MCP_CACHE_DIR |
/data/scholar-mcp |
Directory for the SQLite cache database |
SCHOLAR_MCP_DOCLING_URL |
— | Base URL of a running docling-serve instance (e.g. http://localhost:5001) |
SCHOLAR_MCP_VLM_API_URL |
— | OpenAI-compatible VLM endpoint for formula/figure-enriched PDF conversion |
SCHOLAR_MCP_VLM_API_KEY |
— | API key for the VLM endpoint |
SCHOLAR_MCP_VLM_MODEL |
gpt-4o |
Model name for VLM-enriched conversion |
SCHOLAR_MCP_LOG_LEVEL |
INFO |
Logging level (DEBUG, INFO, WARNING, ERROR) |
SCHOLAR_MCP_BEARER_TOKEN |
— | Bearer token for HTTP transport authentication |
SCHOLAR_MCP_OIDC_ISSUER |
— | OIDC issuer URL for JWT authentication |
SCHOLAR_MCP_OIDC_AUDIENCE |
— | Expected audience for OIDC tokens |
Docker Compose
services:
scholar-mcp:
image: ghcr.io/pvliesdonk/scholar-mcp:latest
restart: unless-stopped
environment:
SCHOLAR_MCP_S2_API_KEY: "${SCHOLAR_MCP_S2_API_KEY}"
SCHOLAR_MCP_DOCLING_URL: "http://docling-serve:5001"
SCHOLAR_MCP_VLM_API_URL: "${VLM_API_URL}"
SCHOLAR_MCP_VLM_API_KEY: "${VLM_API_KEY}"
SCHOLAR_MCP_CACHE_DIR: "/data/scholar-mcp"
SCHOLAR_MCP_READ_ONLY: "false"
volumes:
- scholar-mcp-data:/data/scholar-mcp
labels:
- "traefik.enable=true"
- "traefik.http.routers.scholar-mcp.rule=Host(`scholar-mcp.yourdomain.com`)"
- "traefik.http.routers.scholar-mcp.middlewares=authelia@docker"
docling-serve:
image: ghcr.io/ds4sd/docling-serve:latest
restart: unless-stopped
volumes:
scholar-mcp-data:
Cache Management
# Show cache statistics
scholar-mcp cache stats
# Clear all cached data (preserves identifier aliases)
scholar-mcp cache clear
# Remove entries older than 30 days
scholar-mcp cache clear --older-than 30
# Override cache directory
scholar-mcp cache stats --cache-dir /path/to/cache
Development
# Install with dev dependencies
uv sync --extra dev --extra mcp
# Run tests
uv run pytest
# Lint and format
uv run ruff check src/ tests/
uv run ruff format src/ tests/
# Type check
uv run mypy src/
License
MIT
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file pvliesdonk_scholar_mcp-1.0.0.tar.gz.
File metadata
- Download URL: pvliesdonk_scholar_mcp-1.0.0.tar.gz
- Upload date:
- Size: 206.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
8402a3c0ba2dac8d0693379fbe95630a11b86757c97303d1dd8342e14e1322cb
|
|
| MD5 |
376e62bcc2a2042d3dc71abf6914a112
|
|
| BLAKE2b-256 |
676c92c57610135a7b6a94fdea567116cbb3a3ed8f704cd47b9a638c45e00ed4
|
Provenance
The following attestation bundles were made for pvliesdonk_scholar_mcp-1.0.0.tar.gz:
Publisher:
release.yml on pvliesdonk/scholar-mcp
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
pvliesdonk_scholar_mcp-1.0.0.tar.gz -
Subject digest:
8402a3c0ba2dac8d0693379fbe95630a11b86757c97303d1dd8342e14e1322cb - Sigstore transparency entry: 1234652859
- Sigstore integration time:
-
Permalink:
pvliesdonk/scholar-mcp@6d98757b9c984068626a278edd1f5e97226d0af5 -
Branch / Tag:
refs/heads/main - Owner: https://github.com/pvliesdonk
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
release.yml@6d98757b9c984068626a278edd1f5e97226d0af5 -
Trigger Event:
workflow_dispatch
-
Statement type:
File details
Details for the file pvliesdonk_scholar_mcp-1.0.0-py3-none-any.whl.
File metadata
- Download URL: pvliesdonk_scholar_mcp-1.0.0-py3-none-any.whl
- Upload date:
- Size: 34.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
575d1818a827505572dc28e71ed92065e93c7f73f77939a44c2844558232ef90
|
|
| MD5 |
cdf79cb731dd32ca1d24821e9cedf498
|
|
| BLAKE2b-256 |
8979370e1fab7f70e864a103378dd84abd9964521920531cc2d5c15e66006592
|
Provenance
The following attestation bundles were made for pvliesdonk_scholar_mcp-1.0.0-py3-none-any.whl:
Publisher:
release.yml on pvliesdonk/scholar-mcp
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
pvliesdonk_scholar_mcp-1.0.0-py3-none-any.whl -
Subject digest:
575d1818a827505572dc28e71ed92065e93c7f73f77939a44c2844558232ef90 - Sigstore transparency entry: 1234652887
- Sigstore integration time:
-
Permalink:
pvliesdonk/scholar-mcp@6d98757b9c984068626a278edd1f5e97226d0af5 -
Branch / Tag:
refs/heads/main - Owner: https://github.com/pvliesdonk
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
release.yml@6d98757b9c984068626a278edd1f5e97226d0af5 -
Trigger Event:
workflow_dispatch
-
Statement type: