Is Semantic Scholar safe to install?
hy20191108 · Reference · stdio (local process)
Search academic papers and citations through the Semantic Scholar API.
Capabilities
What Semantic Scholar declares it can do
A server's blast radius is the most powerful thing each of its tools can do. This grades the tools it declares, read-only, not whether it is secure.
- Execute0
- Delete1
- Write2
- Read30
- highTool declares a high-privilege capability×3
Tools
Every tool Semantic Scholar exposes
33 tools
Control
Govern Semantic Scholar with AxioRank
Installed as-is, all 33 of Semantic Scholar's tools are callable by your agent without restriction, including any that write, delete, or execute.
Flip the switch to see the policy AxioRank would apply.
Advisories
Informational content flags
Keyword matches in tool descriptions and schemas. These are shown for transparency and are not part of the grade.
- highShell/command injection×15
- highCredential / secret access capability×3
- highSQL DELETE/UPDATE without WHERE×2
Install
Add Semantic Scholar to your client
Drop this into your MCP client config (Claude Desktop, Cursor, and others).
{
"mcpServers": {
"semantic-scholar": {
"command": "uvx",
"args": [
"semantic-scholar-mcp"
]
}
}
}Embed
Show the grade in your README
[](https://axiorank.com/mcp-index/semantic-scholar)Directory
More Reference servers
How it works
About this grade
The grade reflects the blast radius of what Semantic Scholar declares it can do, read-only, not whether it is secure or trustworthy, and not a judgment of the vendor. Maintain this server? Claim this listing or request a re-scan. See the methodology.
Email me this scorecard
Get the Semantic Scholar grade in your inbox.
Let your agents use Semantic Scholar safely
Route this server through AxioRank to allowlist its tools, hold risky calls for approval, and keep a signed audit trail of every action.
Start free