llmcache is an MCP server that caches AI-generated understanding of your source code. Claude reads each file once and every session after that starts from cached understanding, saving you tokens and…
Llmcache is an MCP project maintained in the sp98/llmcache-site repository. The maintainer describes its purpose as “llmcache is an MCP server that caches AI-generated understanding of your source code. Claude reads each file once and every session after that starts from…”. Read the project documentation for the complete scope.
Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-08.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| understand_file | Returns a cached summary of a source file. If the file has changed (git hash mismatch), generates a fresh summary. If uncommitted, tells Claude to read… |
| understand_package | Summarizes all source files in a directory, giving Claude a package-level overview in one call. |
| get_file_detail | Extracts a specific function or type from a file. Uses Go AST for Go files, pattern search for others. |
| list_summaries | Lists all cached summaries for a repository with hit counts and freshness. |
Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
The WordPress MCP server enables AI assistants to interact with WordPress sites through a standardized interface. It handles authentication and
Link multiple pug ASTs together using include/extends
To install URL Shortener Tool for Claude Desktop automatically via [Smithery](https://smithery.ai/server/@Talismanic/cleanuri-url-shortener-mcp):
Aggregates Lemon Squeezy, Gumroad, Polar, and Stripe revenue into one Claude-queryable view.