Agentfit runs on your own machine — the client starts it, so there is no endpoint to ping. 54 installs a week from npm. Last commit 13 Jun 2026.
Token-aware message truncation: fit a chat history into your model's context budget.
Today is the operative word: we check Agentfit every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add agentfit -- npx -y @mukundakatta/agentfit-mcp
{
"mcpServers": {
"agentfit": {
"command": "npx",
"args": [
"-y",
"@mukundakatta/agentfit-mcp"
]
}
}
}
[mcp_servers.agentfit]
command = "npx"
args = ["-y", "@mukundakatta/agentfit-mcp"]
{
"mcpServers": {
"agentfit": {
"command": "npx",
"args": [
"-y",
"@mukundakatta/agentfit-mcp"
]
}
}
}
{
"servers": {
"agentfit": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@mukundakatta/agentfit-mcp"
]
}
}
}
Token-budget-aware text handling: count, truncate, and chunk for LLM prompts.
MCP Server for SlimContext - AI chat history compression tools
Give your coding agent the right code: graph + hybrid search, packed into a token budget. Local.
Token and context budget for AI agents. Tracks spend and gates the session.
Context-aware reminders that surface when your situation matches, not at a fixed time.
MCP server that cuts AI coding agent token usage via framework-aware context optimization
Search and read your local AI chat-history corpus: full-text search, transcripts, inventory.
Context window token analysis and budget management
Answers built from our own checks of this server.