LLMTrim
MCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.
An MCP server and proxy that compresses LLM prompts, tool outputs, and replies to reduce token usage and cut costs. Supports configurable compression strategies for different message types.
Source
Repository: https://github.com/fkiene/llmtrim
Maintain LLMTrim?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[LLMTrim on getagentictools](https://getagentictools.com/mcp/fkiene-llmtrim?ref=badge) Related mcp
LLM Completions Connect to OpenAI-compatible chat completion APIs.
Figma REST API Integrates with the Figma REST API to manage design system elements, enabling variable handling, file operations, and collaborativ
A2A Bridge Bridges Google's Agent-to-Agent protocol with MCP, enabling agent discovery, registration, message sending, and task management th
Asana Integrates with Asana to enable task automation, project tracking, and team collaboration through the Asana API.
Scaffold Generator Generates code scaffolding for modern web applications using template-based boilerplate creation and feature addition with variabl
Google Workspace Integrates with Gmail and Google Calendar to enable email operations, calendar management, and multi-account support for Google Wo