Registry / search / mcp-scholarly

mcp-scholarly

JSON →
library0.1.0pypypiunverified

A Model Context Protocol (MCP) server for searching academic articles. Allows AI agents to query scholarly databases (e.g., arXiv, Semantic Scholar) and retrieve structured paper metadata. Current version 0.1.0, monthly releases expected.

pip install mcp-scholarly
INSTALL
IMPORT
SIG · MCP-SCHOLARLY
M
mcp-scholarly
searchpythonv0.1.0
harness data pending
Install & Compatibility
Where this runs

No compatibility data collected yet for this library.

Code
Verified usage

Verified import paths — ran on the pinned version, not inferred.

mcp_scholarly_server
from mcp_scholarly import mcp_scholarly_server
import mcp_scholarly_server
The package is a module, not a top-level import.

Basic server startup. The SCHOLARLY_API_KEY is required only for some endpoints.

import os from mcp_scholarly import mcp_scholarly_server # Set environment variables for APIs (optional) os.environ.setdefault('SCHOLARLY_API_KEY', 'your-api-key') # Run the server (blocks) mcp_scholarly_server.run()
Debug
Known issues
gotchaThe server expects a specific MCP client; not all AI frameworks are compatible out-of-the-box.
fix
Use an MCP client library like `mcp-client` or integrate with OpenAI/Anthropic via MCP adapters.
affects: 0.1.0
breakingThe library renames `search` tool to `search_papers` in v0.2.0.
fix
Update client code to call `search_papers` instead of `search`.
affects: >=0.2.0
deprecatedEnvironment variable `ARXIV_API_ENDPOINT` is deprecated; use `SCHOLARLY_ARXIV_ENDPOINT` instead.
fix
Replace `ARXIV_API_ENDPOINT` with `SCHOLARLY_ARXIV_ENDPOINT`.
affects: 0.1.0
Upgrade
Version history
0.1.0latest on PyPI · released Jan 11, 2025
Audit
Dependencies
mcprequiredRequired to run the MCP server; provides the protocol framework.
requestsrequiredHTTP requests to scholarly APIs.
arxivrequiredQuerying arXiv API for papers.
semanticscholaroptionalQuerying Semantic Scholar API for papers.
Agent activity
29 hits · last 30 days
node
26
Amazon
1
OpenAI (training)
1
Resources

No resource links recorded.

mcp-scholarly — pip install mcp-scholarly · libregistry