Developer · Local MCP server
Token Savior
Structural codebase MCP server with persistent memory: navigate by symbol, recall across sessions.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.Mibayy/token-savior- Version
- 4.13.0
- Status
- Active
- Category
- developer
- Transport
- stdio (local process)
- Package
- PyPI
- Published
- 2026-07-26
- Updated
- 2026-07-26
- Publisher
- Mibayy (GitHub)
- Repository
- github.com/Mibayy/token-savior
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| PyPI | token-savior-recall | 4.13.0 | stdio |
How to connect Token Savior
Token Savior runs locally from a Python package published to PyPI: token-savior-recall version 4.13.0. 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 token-savior-recall. It reads these environment variables: WORKSPACE_ROOTS (required), TOKEN_SAVIOR_CLIENT and TOKEN_SAVIOR_PROFILE; 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": {
"token-savior": {
"command": "uvx",
"args": [
"token-savior-recall"
],
"env": {
"WORKSPACE_ROOTS": "<value>",
"TOKEN_SAVIOR_CLIENT": "<value>",
"TOKEN_SAVIOR_PROFILE": "<value>"
}
}
}
}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 |
|---|---|
| Token CompressorCompress prompts 40-60% using local LLM + embedding validation. Preserves all conditionals. | Local · stdio |
| Token EnhancerCuts AI web-fetching costs up to 99.9% by stripping page junk before it reaches your LLM. | Local · stdio |
| Token MeterLocal-first dashboard + MCP for Claude Code and Codex token usage. Per-MCP/tool breakdown. | Local · stdio |
| Token PilotSave up to 80% tokens when AI reads code via AST-aware structural reading. | Local · stdio |
| Token ToolDeploy compliant ERC-20 tokens from any AI agent. 17 tools, 10 networks, CertiK-audited. | Local · stdio |
| Tokencost DevLLM pricing oracle — model lookup, cost estimation, and comparison via LiteLLM. | Local · stdio |
| Tokenectomy RazorAutonomous log surgery & secret redaction MCP server for AI coding agents. | Local · stdio |
| Tokenectomy RazorCut 95% of framework noise and token bloat from error logs for AI agents. | Local · stdio |