CuratedMCP
OpenAI Agents SDK
PyPI

How to install token-savior in OpenAI Agents SDK

Structural codebase MCP server with persistent memory: navigate by symbol, recall across sessions.

Indexed, not yet reviewed

We found token-savior in the official MCP registry. Our automated check passed on Nov 1, 2026 (it confirms the server is published and reachable), but no one at CuratedMCP has reviewed its code, permissions or credentials handling. Check what it can access before you give it keys. Scan your machine free to see every MCP server you have installed.

Steps

  1. 1Install uv (for uvx): https://docs.astral.sh/uv/
  2. 2pip install openai-agents
  3. 3Use the snippet below inside an async function

Python snippet

Python
from agents import Agent
from agents.mcp import MCPServerStdio

async with MCPServerStdio(
    params={
        "command": "uvx",
        "args": [
            "token-savior-recall"
        ],
        "env": {
            "WORKSPACE_ROOTS": "<workspace-roots>"
        }
    },
) as server:
    agent = Agent(name="Assistant", mcp_servers=[server])

Replace the values in angle brackets. Optional settings are listed below.

Environment variableRequiredWhat it is
WORKSPACE_ROOTSYesComma-separated list of absolute paths to project roots to index.
TOKEN_SAVIOR_CLIENTNoOptional client identifier (e.g. 'claude-code', 'cursor', 'hermes') for usage attribution.
TOKEN_SAVIOR_PROFILENoManifest size. 'optimized' (recommended) advertises the Pareto-optimal 15-tool set; 'auto' sizes it from your own usage; 'full' advertises every tool; 'compact-only' if you already run symbol navigati

Install in other clients

About token-savior: repo, license and check results →

Maintain token-savior?

Claim this page to get a full CuratedMCP listing: edit your description, see listing analytics, and add our README badge. Listing is free, and a person checks every submission before it goes live. We'll pre-fill the form from the registry.

    How to install token-savior MCP server in OpenAI Agents SDK | CuratedMCP