Review and compact prompts, docs, and AI-agent skills to save tokens, preserving structure.
Review and compact prompts, docs, and AI-agent skills to save tokens, preserving structure.
CompactPrompt shortens the text you send to an AI model while preserving its meaning. The result costs less to run, returns faster, and is less likely to exceed the model's input limit. The common case is a single function call, and no background in machine learning is required to use it.
Once CompactPrompt is connected, these are the calls the assistant has available:
Engine — ApproachLLMLingua — Microsoft's established tool, which uses a small model to decide what to removeCaveman — Rewrites the text in a concise style, preserving code, links, and headingsField — MeaningCompare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
{
"mcpServers": {
"compactprompt": {
"command": "uvx",
"args": ["compactprompt"]
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
Retrieve public web pages as readable Markdown with the reference Fetch MCP server, including pagination for longer responses.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
Search and read your Drive — Docs, Sheets and files become context your assistant can actually use.
Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.
AWS Labs' official server suite — current AWS docs, CDK guidance, cost analysis and service tools.
Workers, KV, R2 and D1 by conversation — Cloudflare's official remote servers for building and observability.