semantic-scholar-mcp

# Semantic Scholar MCP Server

<!-- mcp-name: io.github.smaniches/semantic-scholar-mcp -->

[![CI](https://github.com/smaniches/semantic-scholar-mcp/actions/workflows/ci.yml/badge.svg)](https://github.com/smaniches/semantic-scholar-mcp/actions/workflows/ci.yml)
[![codecov](https://codecov.io/gh/smaniches/semantic-scholar-mcp/graph/badge.svg)](https://codecov.io/gh/smaniches/semantic-scholar-mcp)
[![PyPI version](https://img.shields.io/pypi/v/s2-mcp-server)](https://pypi.org/project/s2-mcp-server/)
[![PyPI downloads/30d](https://img.shields.io/pypi/dm/s2-mcp-server?label=downloads%2F30d)](https://pypistats.org/packages/s2-mcp-server)
[![DOI](https://img.shields.io/badge/DOI-10.5281%2Fzenodo.19324159-3C5A99?logo=zenodo&logoColor=white)](https://doi.org/10.5281/zenodo.19324159)
[![Provenance: SLSA + SBOM](https://img.shields.io/badge/provenance-SLSA_+_SBOM-blue)](#provenance--supply-chain)
[![Docker](https://img.shields.io/badge/ghcr.io-semantic--scholar--mcp-blue?logo=docker)](https://ghcr.io/smaniches/semantic-scholar-mcp)
[![GitHub Release](https://img.shields.io/github/v/release/smaniches/semantic-scholar-mcp)](https://github.com/smaniches/semantic-scholar-mcp/releases)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
[![MCP](https://img.shields.io/badge/MCP-Compatible-blue)](https://modelcontextprotocol.io)
[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)
[![Glama score](https://glama.ai/mcp/servers/smaniches/semantic-scholar-mcp/badges/score.svg)](https://glama.ai/mcp/servers/smaniches/semantic-scholar-mcp)
[![Awesome MCP Servers](https://img.shields.io/badge/Awesome_MCP-Listed-blue?logo=github)](https://github.com/punkpeye/awesome-mcp-servers#research)

**A 14-tool Semantic Scholar MCP server for academic research workflows.** Direct access to 200M+ papers from [Semantic Scholar](https://www.semanticscholar.org/) — paper search, citation graph traversal, author profiles, and recommendations — from any [Model Context Protocol](https://modelcontextprotocol.io) client (e.g., Claude Desktop, Claude Code, Cursor, Cline, Continue, and others).

Every release ships **verifiable supply-chain provenance**: Sigstore-signed SLSA build-provenance attestations on the wheel, sdist, and container image; PEP 740 attestations on the PyPI upload; and a CycloneDX SBOM — so you can prove the artifact you installed was built from this repo. See [Provenance & supply chain](#provenance--supply-chain).

> Author: **Santiago Maniches** · ORCID [0009-0005-6480-1987](https://orcid.org/0009-0005-6480-1987) · TOPOLOGICA LLC

---

## Quick start

```bash
uvx s2-mcp-server                                      # run instantly, no install
claude mcp add semantic-scholar -- uvx s2-mcp-server   # or register it in Claude Code
```

No API key is needed to start (public rate limit: 1 req/sec); set
`SEMANTIC_SCHOLAR_API_KEY` for 10 req/sec. Claude Desktop, Docker, pip, and
remote (Streamable HTTP) setups are in [Installation](#installation).

---

## Provenance & supply chain

A research tool is only as trustworthy as the chain from its source to the
binary you run. Every release of this server ships cryptographically
verifiable supply-chain evidence, all generated in CI from the tagged commit:

| Guarantee | What it proves | Where it is produced |
|---|---|---|
| **SLSA build provenance** (wheel + sdist) | the published distributions were built by this repo's `publish.yml` from the released tag, not hand-uploaded | [`publish.yml`](.github/workflows/publish.yml) — `actions/attest-build-provenance` (`build` job) |
| **SLSA build provenance** (container image) | the `ghcr.io` image digest was built by this repo's `docker.yml` | [`docker.yml`](.github/workflows/docker.yml) — `actions/attest-build-provenance`, `push-to-registry` (lines 141–147) |
| **PEP 740 attestations** | the PyPI upload itself carries Sigstore-backed attestations under Trusted Publishing | [`publish.yml`](.github/workflows/publish.yml) — `attestations: true` (`publish-pypi` job) |
| **CycloneDX SBOM** | a machine-readable bill of materials, generated in an unprivileged job from the exact wheel's statically resolved dependency metadata (wheels only, none of it executed), SHA-256-bound to that wheel, then attested against the wheel alone | [`publish.yml`](.github/workflows/publish.yml) — `cyclonedx-py` + `scripts/release_sbom.py` (`sbom` job) + `actions/attest-sbom` (`attest-sbom` job) |
| **SHA-pinned Actions** | every CI action is pinned to a commit SHA, so the release pipeline itself cannot silently change | all jobs in `.github/workflows/` (e.g. `publish.yml`, `docker.yml`) |

Verify the wheel and the container image against their attestations with the
GitHub CLI:

```bash
# Wheel / sdist (download from the PyPI project or the release assets first)
gh attestation verify s2_mcp_server-*.whl --repo smaniches/semantic-scholar-mcp

# Container image
gh attestation verify oci://ghcr.io/smaniches/semantic-scholar-mcp:latest \
  --repo smaniches/semantic-scholar-mcp
```

The full supply-chain posture, including the known-limitations list, is in
[SECURITY.md](SECURITY.md). This is **release-time** provenance (proving how
the artifact was built); the server does not currently attach a per-response
receipt to individual API results.

---

## How it compares

There is no public Semantic Scholar MCP standard, so the most useful
comparison is against the obvious alternative: calling the
[Semantic Scholar REST API](https://api.semanticscholar.org/) yourself from an
agent. Everything in the right-hand column is plumbing this server already owns
and the caller would otherwise reimplement.

| | This server | Raw S2 REST API from an agent |
|---|---|---|
| Tool surface | 14 typed MCP tools (search, retrieval, recommendations, status) | caller composes raw HTTP requests |
| Citation graph | both directions (citations and references) in `get_paper` | manual paging over two endpoints |
| Bulk operations | papers (≤500) and authors (≤1000) in one call | caller batches and paginates |
| Full-text snippet search | `snippet_search` with surrounding context | separate endpoint, caller-assembled |
| Paper-ID resolution | seven formats — Semantic Scholar ID, DOI, ArXiv, PubMed, Corpus ID, ACL, URL — validated pre-flight ([`validators.py`](src/semantic_scholar_mcp/validators.py)) | caller normalizes and validates IDs |
| Rate limiting | client-side per-tier limiter, never exceeds the interval ([`client.py`](src/semantic_scholar_mcp/client.py)) | caller throttles by hand |
| Retry / backoff | bounded, jittered retry on 429/502/503/timeout, honors `Retry-After` ([`client.py`](src/semantic_scholar_mcp/client.py)) | caller implements retry |
| Errors | typed exception hierarchy, branchable by caller ([`errors.py`](src/semantic_scholar_mcp/errors.py)) | parse HTTP status strings |
| Output | chat-tuned Markdown or JSON per call ([`formatters.py`](src/semantic_scholar_mcp/formatters.py)) | raw JSON |
| Supply-chain provenance | SLSA + PEP 740 + CycloneDX SBOM per release ([see above](#provenance--supply-chain)) | n/a |
| Citability | minted Zenodo DOI, MIT licensed | n/a |

---

## Installation

### Option 1: One-Line Install (Recommended)
```bash
# No cloning needed — runs directly from PyPI
uvx s2-mcp-server
```

### Option 2: Claude Code
```bash
claude mcp add semantic-scholar -- uvx s2-mcp-server
```

### Option 3: Claude Desktop (Windows)

Add to `%APPDATA%\Claude\claude_desktop_config.json`:

```json
{
  "mcpServers": {
    "semantic-scholar": {
      "command": "uvx",
      "args": ["s2-mcp-server"],
      "env": {
        "SEMANTIC_SCHOLAR_API_KEY": "your-key-here"
      }
    }
  }
}
```

### Option 4: Claude Desktop (macOS)

Add to `~/Library/Application Support/Claude/claude_desktop_config.json`:

```json
{
  "mcpServers": {
    "semantic-scholar": {
      "command": "uvx",
      "args": ["s2-mcp-server"],
      "env": {
        "SEMANTIC_SCHOLAR_API_KEY": "your-key-here"
      }
    }
  }
}
```

### Option 5: pip / From Source
```bash
pip install s2-mcp-server
# or
git clone https://github.com/smaniches/semantic-scholar-mcp.git
cd semantic-scholar-mcp && pip install -e .
```

### Option 6: Docker
```bash
docker pull ghcr.io/smaniches/semantic-scholar-mcp:latest
docker run -e SEMANTIC_SCHOLAR_API_KEY=your-key ghcr.io/smaniches/semantic-scholar-mcp
```

### Option 7: Remote server (Streamable HTTP) — requires ≥ 1.5.0
```bash
# Serve MCP over HTTP at http://127.0.0.1:8000/mcp instead of stdio
# (--from pins the floor: uvx may otherwise reuse a cached older version)
uvx --from "s2-mcp-server>=1.5.0" s2-mcp-server --transport http
```
See [Remote access (Streamable HTTP)](#remote-access-streamable-http) for client
configuration, per-request API keys, and deployment guidance.

> **Note:** Get a free API key at [semanticscholar.org/product/api](https://www.semanticscholar.org/product/api). Without a key, you get rate-limited public access (1 req/sec).

---

## Architecture

```mermaid
flowchart LR
  Client["MCP client<br/>(Claude Desktop, Claude Code,<br/>Cursor, Cline, Continue, …)"]
  subgraph Server ["s2-mcp-server (this package)"]
    direction TB
    FastMCP["FastMCP runtime<br/>(stdio / Streamable HTTP, lifespan)"]
    Tools["14 @mcp.tool functions<br/>(server.py)"]
    Models["Pydantic input models<br/>+ field sets (models.py)"]
    Validators["Paper-ID validator<br/>(validators.py)"]
    Cache["TTL cache<br/>(cache.py)"]
    Fmt["Markdown formatters<br/>(formatters.py)"]
    HTTP["httpx client<br/>+ rate limit + retry/backoff<br/>(client.py)"]
    Errors["Typed exceptions<br/>(errors.py)"]
    Log["Structured JSON logger<br/>(logging_config.py)"]
  end
  S2Graph["Semantic Scholar<br/>Graph API"]
  S2Recs["Semantic Scholar<br/>Recommendations API"]

  Client <-- "stdio or Streamable HTTP<br/>(JSON-RPC)" --> FastMCP
  FastMCP --> Tools
  Tools --> Models
  Tools --> Validators
  Tools