CompactPrompt is an MCP server and library that shortens prompts, documents, and skills while preserving meaning, using trimming, reversible abbreviation, numeric quantization, and example selection. It also provides file review/compaction commands for markdown and skill files, with support for built-in, LLMLingua, and Caveman engines.
From the registry: Review and compact prompts, docs, and AI-agent skills to save tokens, preserving structure.
$ pip install 'compactprompt[mcp]'Please install the `compactprompt` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install CompactPrompt MCP package** — Install the Python package with the MCP extra, which provides the `compactprompt-mcp` command. Run: `pip install 'compactprompt[mcp]'`
Canonical MCP server config (stdio transport):
- command: `compactprompt-mcp`
- args: []
Note: README states the MCP server is provided by the `compactprompt[mcp]` extra and exposes the `compactprompt-mcp` command. No environment variables or additional runtime arguments are documented for the MCP server.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Persistent codebase knowledge graph. Survives session restarts and context compaction.
A powerful toolkit for coding, providing semantic retrieval and editing capabilities.