harcx-mcp
An MCP server that enables AI assistants to verify BibTeX citations and URLs against academic databases like Semantic Scholar and DBLP. It allows users to ensure bibliography accuracy and link accessibility directly within their research workflows.
README
harcx-mcp
MCP server for verifying BibTeX citations using harcx. Allows AI assistants like Claude to check your bibliography against Semantic Scholar, DBLP, and other academic databases.
Thanks to the original harcx package for providing the citation verification functionality.
Quick Setup
- Create a
.vscodefolder in your project (if it doesn't exist) - Create
.vscode/mcp.jsonwith:{ "servers": { "harcx": { "command": "python", "args": ["/path/to/harcx_mcp.py"] } } } - Use
#harcxin Claude Code to access the tools:verify citations in references.bib verify urls in references.bib
Installation
pip install "mcp[cli]" harcx
Usage
With Claude Code
Add to your project's .mcp.json:
{
"mcpServers": {
"harcx": {
"command": "python",
"args": ["/path/to/harcx_mcp.py"]
}
}
}
Then ask Claude to verify your citations:
verify citations in references.bib
With Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"harcx": {
"command": "python",
"args": ["/path/to/harcx_mcp.py"]
}
}
}
Tools
verify_citations
Verify academic papers and books against Semantic Scholar and DBLP.
Parameters:
bib_content(required): Path to .bib file or inline BibTeX contentauthor_threshold(optional): Author name match tolerance, 0.0-1.0 (default: 0.6)check_urls(optional): Also verify URLs in citations (default: false)api_key(optional): Semantic Scholar API key for higher rate limits
Example:
Check the citations in my thesis.bib file
verify_urls
Check that URLs in your bibliography are accessible.
Parameters:
bib_content(required): Path to .bib file or inline BibTeX content
Example:
Verify all URLs in references.bib are still working
Rate Limits
Semantic Scholar has rate limits. If you're checking many citations, you may see 429 errors and retries. For higher limits, get a free API key from Semantic Scholar and pass it via the api_key parameter.
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
E2B
Using MCP to run code via e2b.