Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "compendium": {
      "command": "cargo",
      "args": [
        "run",
        "--",
        "Compendium"
      ]
    }
  }
}

README Excerpt

<p align="center"> <img src="assets/logo.svg" alt="Compendium" width="420" /> </p> MCP server that **minimizes LLM token usage** by compressing, summarizing, filtering, and chunk-referencing large context before it reaches the model. Built in Rust with the official [`rmcp`](https://crates.io/crates/rmcp) SDK.

Tools (20)

COMPENDIUM_ARCHIVE_MAX_BYTESCOMPENDIUM_ARCHIVE_MAX_FILESCOMPENDIUM_ARCHIVE_MAX_UNCOMPRESSEDCOMPENDIUM_AUDIT_PATHCOMPENDIUM_BRIEF_ROOTCOMPENDIUM_CACHE_DIRCOMPENDIUM_CACHE_MAX_BYTESCOMPENDIUM_CHARS_PER_TOKENCOMPENDIUM_CROSS_ENCODER_TOP_NCOMPENDIUM_DEFAULT_MAX_TOKENSCOMPENDIUM_HTTP_BINDCOMPENDIUM_HYBRID_ALPHACOMPENDIUM_LOCAL_EMBED_MODELCOMPENDIUM_LOCAL_LLM_API_KEYCOMPENDIUM_LOCAL_LLM_MODELCOMPENDIUM_LOCAL_LLM_TIMEOUT_SECSCOMPENDIUM_LOCAL_LLM_URLCOMPENDIUM_MAX_BLANK_LINESCOMPENDIUM_PLAYBOOKS_DIRCOMPENDIUM_RERANK_CROSS_ENCODER

Topics

claudecompressioncontext-managementcursorllmmcpmodel-context-protocolnpmollamarusttiktokentokens

Compendium

Quick Install

README Excerpt

Tools (20)

Topics

Related AI/LLM Servers