Inspirehep MCP Server

Add to `~/.gemini/settings.json` (user scope) or `.gemini/settings.json` (project scope):

Local serverstdio

What is the Inspirehep MCP MCP server?

Add to ~/.gemini/settings.json (user scope) or .gemini/settings.json (project scope):. The inspirehep mcp mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 9 defined tools rather than through you.

Its toolset

Everything the assistant can do here goes through one of these:

  • search_papers — Search papers by topic, author, collaboration, or free text
  • get_paper_details — Get full metadata for a paper by Inspire ID, arXiv ID, or DOI
  • get_author_papers — Retrieve an author's publications and citation metrics
  • get_citations — Explore citation graph — who cites a paper, or what it cites
  • search_by_collaboration — Find publications from ATLAS, CMS, LHCb, etc
  • get_paper_figures — Retrieve figures and download URLs for a paper
  • get_references — Generate BibTeX, LaTeX, or JSON reference lists
  • get_bibtex — Retrieve BibTeX citation entry by DOI, arXiv ID, or Inspire ID
  • server_stats — Monitor cache hit rates and API performance

Configuration

You will need one environment variable: INSPIREHEP_CACHE_DB_PATH. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Adding it to your client

The server ships on PyPI as inspirehep-mcp, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

When to reach for it

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Inspirehep MCP's toolset — search_papers, get_paper_details, get_author_papers and 6 more — is a fair guide to whether it matches your workflow. It is maintained by mohamedelashri; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Inspirehep MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 9 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Inspirehep MCP.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the inspirehep mcp mcp server does with a few real requests.

Available tools

ToolWhat it does
search_papersSearch papers by topic, author, collaboration, or free text
get_paper_detailsGet full metadata for a paper by Inspire ID, arXiv ID, or DOI
get_author_papersRetrieve an author's publications and citation metrics
get_citationsExplore citation graph — who cites a paper, or what it cites
search_by_collaborationFind publications from ATLAS, CMS, LHCb, etc.
get_paper_figuresRetrieve figures and download URLs for a paper
get_referencesGenerate BibTeX, LaTeX, or JSON reference lists
get_bibtexRetrieve BibTeX citation entry by DOI, arXiv ID, or Inspire ID
server_statsMonitor cache hit rates and API performance

How to install the Inspirehep MCP MCP server

{
  "mcpServers": {
    "inspirehep": {
      "command": "uvx",
      "args": ["inspirehep-mcp"],
      "env": {
        "INSPIREHEP_CACHE_DB_PATH": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
INSPIREHEP_CACHE_DB_PATHFilesystem location the server is allowed to use.Optional

Example prompts to try

  • Use Inspirehep MCP to search papers.
  • Use Inspirehep MCP to get paper details.
  • Use Inspirehep MCP to get author papers.

Frequently asked questions

It connects Inspirehep MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 9 tools (search_papers, get_paper_details, get_author_papers, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Inspirehep MCP directly.