Developer · Local MCP server
Tokenmizer
Graph-backed session memory for LLMs: checkpoint, resume, file analysis, token-savings stats.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.Shweta-Mishra-ai/tokenmizer- Version
- 0.3.1
- Status
- Active
- Category
- developer
- Transport
- stdio (local process)
- Package
- PyPI
- Published
- 2026-07-04
- Updated
- 2026-07-04
- Publisher
- Shweta-Mishra-ai (GitHub)
- Namespace
- Namespace verified by the MCP Registry via GitHub (github.com/Shweta-Mishra-ai) · how
- Repository
- github.com/Shweta-Mishra-ai/tokenmizer
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| PyPI | tokenmizer | 0.3.1 | stdio |
How to connect Tokenmizer
Tokenmizer runs locally from a Python package published to PyPI: tokenmizer version 0.3.1. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install - the usual command is uvx tokenmizer. It reads these environment variables: TOKENMIZER_URL and TOKENMIZER_API_KEY (secret); set them in the client's configuration for this server.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"tokenmizer": {
"command": "uvx",
"args": [
"tokenmizer"
],
"env": {
"TOKENMIZER_URL": "<value>",
"TOKENMIZER_API_KEY": "<secret>"
}
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More developer servers
| Server | Runs |
|---|---|
| TokenEyezTrack every AI token across Claude, ChatGPT, Gemini, Cursor, and Claude Code. | Local · stdio |
| TokenKnowsDistill AI coding sessions into weekly reports, ADRs and a knowledge graph - self-hosted. | Local · stdio |
| Tokenmaxxen MCPCollective episodic memory for AI coding agents - search, deposit, comment, showcase builds. | Local · stdio |
| TokenmaxxingCoordinate coding agents through MCP using existing AI plans, saved work, and independent checks. | Remote · HTTPLive check: sign-in required |
| TokennukeCode indexing MCP: 15 tools, 10 languages, hybrid search, call graphs, O(1) retrieval. | Local · stdio |
| TokenSaveCode intelligence for 15+ languages: semantic graph queries instead of file reads. 37 MCP tools. | Local · stdio |
| TokenSaverStructural warm start for AI coding agents in.NET: cheap Roslyn signature maps of C#/.NET files. | Local · stdio |
| TokenscopeAnalyze Claude Code session cost & context attribution: output, cached re-reads, cache writes. | Local · stdio |