Semantic ScholarSAFE
A FastMCP server implementation for the Semantic Scholar API, providing comprehensive access to academic paper data, author information, and citation networks.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://mseep.ai/app/zongmin-yu-semantic-scholar-fastmcp-mcp-server)
[](https://smithery.ai/server/semantic-scholar-fastmcp-mcp-server)
A FastMCP server implementation for the Semantic Scholar API, providing comprehensive access to academic paper data, author information, and citation networks.
Looking for Claude Code skills? Check out semantic-scholar-skills — the next-generation toolkit that bundles this MCP server with ready-to-use Claude Code skills (/expand-references,/trace-citations,/paper-triage) and a Python workflow engine.
Project Structure
The project has been refactored into a modular structure for better maintainability:
semantic-scholar-server/ ├── semantic_scholar/ # Main package │ ├── __init__.py # Package initialization │ ├── server.py # Server setup and main functionality │ ├── mcp.py # Centralized FastMCP instance definition │ ├── config.py # Configuration classes │ ├── utils/ # Utility modules │ │ ├── __init__.py │ │ ├── errors.py # Error handling │ │ └── http.py # HTTP client and rate limiting │ ├── api/ # API endpoints │ ├── __init__.py │ ├── papers.py # Paper-related endpoints │ ├── authors.py # Author-related endpoints │ └── recommendations.py # Recommendation endpoints ├── run.py # Entry point script
This structure:
- Separates concerns into logical modules
- Makes the codebase easier to understand and maintain
- Allows for better testing and future extensions
- Keeps related functionality grouped together
- Central
eabd442c0396OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add semantic-scholar-fastmcp --env SEMANTIC_SCHOLAR_API_KEY=${SEMANTIC_SCHOLAR_API_KEY} -- uvx semantic-scholar-fastmcp{
"mcpServers": {
"semantic-scholar-fastmcp": {
"command": "uvx",
"args": [
"semantic-scholar-fastmcp"
],
"env": {
"SEMANTIC_SCHOLAR_API_KEY": "${SEMANTIC_SCHOLAR_API_KEY}"
}
}
}
}Exposed tools (16)
16 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
author_batch_details | read | try: |
author_details | read | try: |
author_papers | read | try: |
author_search | read | try: |
get_paper_recommendations_multi | read | try: |
get_paper_recommendations_single | read | try: |
paper_authors | read | try: |
paper_autocomplete | read | try: |
paper_batch_details | read | try: |
paper_bulk_search | read | try: |
paper_citations | read | try: |
paper_details | read | try: |
paper_references | read | try: |
paper_relevance_search | read | try: |
paper_title_search | read | try: |
snippet_search | read | try: |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (4 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (2)
logger.info(f"API Key found: {'Yes' if api_key else 'No'}")httpx, pytest, pytest-asyncio, python-dotenv, fastmcp, fastapi, uvicorn
Gates applied: no_behavioural_pass.
eabd442c0396full audit observations/trust-audit/mcp-server/yuzongmin__semantic-scholar.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | eabd442c0396 | SAFE | B | 89 | first audit |
Questions
What is the Semantic Scholar MCP server?
A FastMCP server implementation for the Semantic Scholar API, providing comprehensive access to academic paper data, author information, and citation networks.
What tools does Semantic Scholar expose?
16 in total: 16 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Semantic Scholar safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Semantic Scholar need?
It reads SEMANTIC_SCHOLAR_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Semantic Scholar run?
It speaks streamable-http, so it runs as a service you connect to over the network. It is published on PyPI as semantic-scholar-fastmcp.
How current is this page?
The grade is for one exact copy of the source (eabd442c0396), read on 2026-10-08. The repository is watched and re-audited when it changes.