Save up to 80% tokens when AI reads code via AST-aware structural reading
Save up to 80% tokens when AI reads code via AST-aware structural reading. That is what the token mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.
smart_read, read_symbol, read_for_edit, …). Ask for an outline or load one function by name instead of the whole file. 2. PreToolUse hooks — intercept heavy native tool calls (Read on large files, recursive Grep, unbounded git diff) and redirect to token-efficient alternatives. 3. tp-* subagents — Claude Code delegates with MCP-first behaviour and tight response budgets.The server publishes 1 tool. What each one is for:
Benchmarks — The Benchmarks tool exposed by this serverConfiguration is passed through the environment: TOKEN_PILOT_WORKFLOW_ID. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
tsx on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.
This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Token's toolset — Benchmarks — is a fair guide to whether it matches your workflow. It is maintained by Digital-Threads; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| Benchmarks | The Benchmarks tool exposed by this server. |
{
"mcpServers": {
"token-pilot": {
"command": "npx",
"args": ["-y", "tsx"],
"env": {
"TOKEN_PILOT_WORKFLOW_ID": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| TOKEN_PILOT_WORKFLOW_ID | Credential the server authenticates with. | Yes |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.