tokenmizer
Graph-backed session memory for LLMs: checkpoint, resume, file analysis, token-savings stats.
Open the source (opens github.com) https://github.com/shweta-mishra-ai/tokenmizer
Before you use it
- Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
- Needs credentials: TOKENMIZER_API_KEY. Use a key with the least access you can.
What it is
MCP servers from io.github.Shweta-Mishra-ai.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
pypi package (stdio)
tokenmizer@0.3.1
From the server's entry in the official MCP Registry
Settings it asks for
TOKENMIZER_URL· Base URL of the running TokenMizer proxy (default http://localhost:8000)TOKENMIZER_API_KEYsecret · API key if the proxy has auth enabled
Related
-
tokenmaxxen-mcp
MCP serversCollective episodic memory for AI coding agents — search, deposit, comment, showcase builds.
tokenmaxxen-mcp@0.3.0 -
tokenmonkey
MCP serversP2P wagering protocol for AI agents on Solana. Coinflip & dice challenges for USDC.
tokenmonkey-mcp-server@0.1.1 -
TokenMark
MCP serversMeasured local-LLM speeds and model picks for Strix Halo, DGX Spark, Mac and GPU cards.
@altronis/tokenmark-mcp@0.4.1 -
Tokenmaxxing
MCP serversCoordinate coding agents through MCP using existing AI plans, saved work, and independent checks.
-
GitHub MCP server
MCP serversGitHub's official MCP server. It lets an agent read and work with repositories, issues and pull requests.
https://api.githubcopilot.com/mcp/ -
Official MCP Registry
MCP serversThe MCP project's own registry of public MCP servers, so you can look for a connector before building one.