Agentfit

Name: Agentfit
Author: MukundaKatta

by MukundaKattacommunityv0.1.0

MCP server that wraps @mukundakatta/agentfit so MCP clients can estimate token counts and trim chat histories to fit a model context budget. It runs over stdio and supports multiple model estimator families and message-fitting strategies.

From the registry: Token-aware message truncation: fit a chat history into your model's context budget.

GitHub Repository Website

Install & configure

Prerequisites

required
Install Node.js and npm/npx
Required to run the MCP server via npx.
https://nodejs.org/'}],
optional
None
No environment variables or extra setup are described in the README.

Install in your client

Paste into the AI you're chatting with — it will figure out the rest

Please install the `agentfit` MCP server into my current AI client (that's you).

Required prerequisites (do these first if not already done):
- **Install Node.js and npm/npx** — Required to run the MCP server via npx. (https://nodejs.org/'}],)

Optional prerequisites:
- None — No environment variables or extra setup are described in the README.

Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","@mukundakatta/agentfit-mcp"]

Note: The server speaks plain MCP over stdio. README shows client-specific examples, but the canonical configuration is command `npx` with args `-y @mukundakatta/agentfit-mcp`. No environment variables are documented.

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.

Note: The server speaks plain MCP over stdio. README shows client-specific examples, but the canonical configuration is command `npx` with args `-y @mukundakatta/agentfit-mcp`. No environment variables are documented.