Skip to main content

Installable MCP server for the Retrieval academic-paper search + ACE journal + index inventory API

Project description

retrieval-mcp

An MCP server for the Retrieval academic-paper API — semantic paper search, document matching, ACE journal memory, and index inventory. Self-contained: it talks to the backend over HTTP only (just mcp + httpx), so it installs anywhere with uvx / pip — no repo checkout, no GPU, no models.

By default it targets the compute box on the lab LAN (http://10.100.100.111:8000), which trusts LAN callers so no key is needed. Off-LAN, point RETRIEVAL_API_URL at the public gateway (https://retrieval.rnarket.com) and set RETRIEVAL_API_KEY (sk-...).

Tools

Tool What it does
search_papers Semantic hybrid search over 95k+ top-venue CS papers
search_within_paper Every matching passage inside one paper
match_document / match_paper Content-nearest papers to a passage / a paper
list_conferences / corpus_stats Venue registry / corpus size
journal_record / journal_search / journal_recent ACE journal work-memory (cwd-scoped)
index_inventory Your indexed-file tree: user → host → project → dir → file

Install

Claude Code

# LAN (no key):
claude mcp add retrieval -- uvx retrieval-mcp
# Off-LAN (public gateway + key):
claude mcp add retrieval \
  --env RETRIEVAL_API_URL=https://retrieval.rnarket.com \
  --env RETRIEVAL_API_KEY=sk-... \
  -- uvx retrieval-mcp

Claude Desktop / any MCP client

claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\):

{
  "mcpServers": {
    "retrieval": {
      "command": "uvx",
      "args": ["retrieval-mcp"],
      "env": {
        "RETRIEVAL_API_URL": "https://retrieval.rnarket.com",
        "RETRIEVAL_API_KEY": "sk-...",
        "JOURNAL_PROJECT_SLUG": "my-project"
      }
    }
  }
}

No uv? pip install retrieval-mcp then use "command": "retrieval-mcp".

Config (env)

Var Default Notes
RETRIEVAL_API_URL http://10.100.100.111:8000 LAN compute box (no key). Off-LAN, set to https://retrieval.rnarket.com.
RETRIEVAL_API_KEY sk-... key for the gateway (create under /auth/keys). Required off-LAN.
JOURNAL_PROJECT_SLUG current dir name Journal namespace; scopes journal reads/writes so projects don't leak into each other.

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

retrieval_mcp-0.1.0.tar.gz (7.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

retrieval_mcp-0.1.0-py3-none-any.whl (7.7 kB view details)

Uploaded Python 3

File details

Details for the file retrieval_mcp-0.1.0.tar.gz.

File metadata

  • Download URL: retrieval_mcp-0.1.0.tar.gz
  • Upload date:
  • Size: 7.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.8.15

File hashes

Hashes for retrieval_mcp-0.1.0.tar.gz
Algorithm Hash digest
SHA256 890df573a55f55f991d3632be54716508cd505fc5370a28441e5b21e700447b8
MD5 75a2402586479f4ff2de5babe4b3bff4
BLAKE2b-256 ee0808bdc0191327872ffa331d1c7fb3db06874924e1b11fa2939315918efc17

See more details on using hashes here.

File details

Details for the file retrieval_mcp-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for retrieval_mcp-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 ceec90159927096fdbe612c5eb32122ffc0d1387ac8ae924f7fa9ce24cb8c869
MD5 81f5ab693d8ec88d2a853968ae305e9a
BLAKE2b-256 cb5952b4668f5ce15cf20ee311bed76ca8364529de3d18669cb458ca5b23e26f

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page