Claude Token Saver MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 45 installs a week from npm. Last commit 31 Mar 2026.
MCP server that offloads routine coding tasks to local LLM (Ollama) to save Claude API tokens
Today is the operative word: we check Claude Token Saver MCP 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 claude-token-saver-mcp -- npx -y claude-token-saver-mcp
{
"mcpServers": {
"claude-token-saver-mcp": {
"args": [
"-y",
"claude-token-saver-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.claude-token-saver-mcp]
command = "npx"
args = ["-y", "claude-token-saver-mcp"]
{
"mcpServers": {
"claude-token-saver-mcp": {
"args": [
"-y",
"claude-token-saver-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"claude-token-saver-mcp": {
"args": [
"-y",
"claude-token-saver-mcp"
],
"command": "npx"
}
}
}
MCP server mode for Qoder CLI — delegate coding tasks to local Qoder agents from any MCP client.
Unified MCP server bridging Claude Code and Ollama to Roblox Studio and Blender.
Connect Claude to any OpenAI-compatible LLM endpoint and offload routine work to a local model.
Local MCP server to sync, clean, and index AI chat logs locally. Saves up to 40% context tokens.
Ready-to-clone Rust MCP server with chat, token-counting, and model tools for Claude
Local long-term memory MCP server (SQLite) for AI coding agents — OpenCode, Claude Code, Cursor
Delegate mechanical text tasks to a local OpenAI-compatible LLM to save Claude quota.
A local-first MCP server that routes development tasks to authoritative project documentation.
Answers built from our own checks of this server.