Reduziert den Token-Verbrauch beim KI-Coding um bis zu 90 % durch AST-basierte strukturelle Reads und Tool-Interception-Hooks.
Auch bekannt als Digital-Threads/token-pilot
- Stars
- 5
- Tools
- —
- Downloads, 30 Tage
- —
- Neueste Version
- 2.0.0
- Letzter Commit
- 6. Nov. 2026
- Lizenz
- —
Was ist token-pilot MCP?
token-pilot ist ein MCP server. Reduziert den Token-Verbrauch beim KI-Coding um bis zu 90 % durch AST-basierte strukturelle Reads und Tool-Interception-Hooks.
Zusammenfassung generiert aus dem README des Projekts
Über token-pilot MCP server
Token Pilot ist ein spezialisiertes Tool, das darauf ausgelegt ist, den Token-Verbrauch von KI-Coding-Assistenten um bis zu 90 % zu reduzieren. Diese Einsparungen werden erreicht, indem schwere Full-File-Reads durch strukturelle, AST-basierte Operationen ersetzt werden. So können Entwickler ihre teuren Frontier-Modelle auf das Reasoning konzentrieren, anstatt massenhaft redundanten Code-Kontext verarbeiten zu müssen. Das System arbeitet über zwei primäre Ebenen: eine Suite von 25 MCP tools für gezielte Datenabfragen und PreToolUse-Hooks, die ineffiziente native Commands abfangen und umleiten.
Nutzer können diesen Server lokal über npx bereitstellen, um die Konfiguration zu initialisieren. Er ist speziell für Claude Code und Codex CLI durch fortschrittliche Hook-Systeme optimiert, bietet aber auch Standard-MCP tools für andere Clients wie Cursor, Cline und Gemini CLI. Der Server unterstützt eine Vielzahl von Programmiersprachen, darunter TypeScript, Python, Go, Rust und Java. Er bietet verschiedene Enforcement-Modi, die von advisory-Hinweisen bis hin zum strict-Modus reichen, der schwere Grep- oder Bash-Aufrufe blockiert und Output-Caps erzwingt, um die Budgeteinhaltung sicherzustellen.
Was du damit machen kannst
- 1Kontextfenster-Nutzung reduzierenEin Entwickler kann eine strukturelle Übersicht einer Datei anfordern, anstatt hunderte Zeilen Code zu laden.
- 2Gezielte Symbol-AbfrageAnstatt ein ganzes Modul zu lesen, kann eine KI nur die spezifische Funktion abrufen, die für eine Änderung benötigt wird.
Geschrieben aus dem README des Projekts. Jeder Use Case wurde gegen ein Zitat daraus geprüft.
So installierst du token-pilot MCP
Formate geprüft am 10. Nov. 2026Zu Cursor hinzufügenZu Goose hinzufügentoken-pilot MCP in Claude Code installieren
$ claude mcp add token-pilot -- npx -y token-pilottoken-pilot MCP in Cursor installieren
~/.cursor/mcp.json
{
"mcpServers": {
"token-pilot": {
"command": "npx",
"args": [
"-y",
"token-pilot"
]
}
}
}token-pilot MCP in VS Code installieren
.vscode/mcp.json
{
"servers": {
"token-pilot": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"token-pilot"
]
}
}
}token-pilot MCP in VS Code CLI installieren
$ code --add-mcp '{"name":"token-pilot","type":"stdio","command":"npx","args":["-y","token-pilot"]}'token-pilot MCP in Claude Desktop installieren
claude_desktop_config.json
{
"mcpServers": {
"token-pilot": {
"command": "npx",
"args": [
"-y",
"token-pilot"
]
}
}
}token-pilot MCP in Codex installieren
$ codex mcp add token-pilot -- npx -y token-pilottoken-pilot MCP in Codex config.toml installieren
~/.codex/config.toml
[mcp_servers.token-pilot] command = "npx" args = ["-y", "token-pilot"]
token-pilot MCP in Gemini CLI installieren
$ gemini mcp add -s user token-pilot npx -- -y token-pilottoken-pilot MCP in Gemini settings.json installieren
~/.gemini/settings.json
{
"mcpServers": {
"token-pilot": {
"command": "npx",
"args": [
"-y",
"token-pilot"
]
}
}
}Konfiguration
TOKEN_PILOT_MODE
| Name | Beschreibung | Typ |
|---|---|---|
| TOKEN_PILOT_MODE | — |
Automatisierte Checks
Geluften am 13. Nov. 2026Vollständiger Bericht →Unsere automatisierten Checks bestanden. Das ist kein Security-Audit: Lies den Code und gib dem Server nur den minimal notwendigen Zugriff. Wie die Checks funktionieren · Was du für mehr Punkte verbessern kannst
- Source Repository verknüpft und erreichbardigital-threads/token-pilot is public and reachablegithub.com/digital-threads/token-pilot ↗Bestanden
- Paket nennt dieses Repository als Quelletoken-pilot names digital-threads/token-pilot as sourcenpmjs.com/package/token-pilot ↗Bestanden
- Build-Provenienz (Sigstore-Attestierung)No build attestation published for this releaseNicht geprüft
- Open Source Lizenz (OSI)No licenseBefund
- Commit oder Release im letzten JahrLast commit or release 2026-11-06github.com/digital-threads/token-pilot ↗Bestanden
- OpenSSF ScorecardNicht geprüft
- Package-Name ähnelt keinem populären PackageNo popular package one edit away from token-pilotBestanden
- Keine kritischen Advisories im Paket oder seinen Abhängigkeiten116 resolved dependencies checked; no critical advisoryosv.dev ↗Bestanden
- Keine versteckten Anweisungen an das Modell0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersBestanden
- Destruktive Tools sind markiertNicht geprüft
- Remote-Endpoint beantwortet den MCP-HandshakeNicht geprüft
README
Auf GitHub ansehenToken Pilot
Token-efficient AI coding, enforced. Cuts context consumption in AI coding assistants by up to 90% without changing the way you work.
Why it matters more now: as frontier models move up in price, the tokens you don't spend reading code are worth more, not less. The savings are in tokens; the value is in tokens × price. Token Pilot keeps the expensive main thread lean so the premium model spends its budget on reasoning, not on re-reading files.
Two layers, each useful on its own, stronger together:
- MCP tools — structural reads (
smart_read,read_symbol,read_for_edit, …). Ask for an outline or load one function by name instead of the whole file. - PreToolUse hooks — intercept heavy native tool calls (
Readon large files, recursiveGrep, unboundedgit diff) and redirect to token-efficient alternatives.
How It Works
Traditional: Read("user-service.ts") → 500 lines → ~3000 tokens
Token Pilot: smart_read("user-service.ts") → 15-line outline → ~200 tokens
read_symbol("UserService.updateUser") → 45 lines → ~350 tokens
After edit: read_diff("user-service.ts") → ~20 tokens
Files under 200 lines are returned in full — zero overhead for small files.
Benchmarks
Measured on public open-source repos. Files ≥50 lines only:
| Repo | Files | Raw Tokens | Outline Tokens | Savings |
|---|---|---|---|---|
| token-pilot (TS) | 55 | 102,086 | 8,992 | 91% |
| express (JS) | 6 | 14,421 | 193 | 99% |
| fastify (JS) | 23 | 50,000 | 3,161 | 94% |
| flask (Python) | 20 | 78,236 | 7,418 | 91% |
| Total | 104 | 244,743 | 19,764 | 92% |
smart_readoutline savings only. Real sessions additionally benefit from session cache,read_symbol, andread_for_edit. Reproduce:npx tsx scripts/benchmark.ts.
Quick Start
npx -y token-pilot init
Creates (or merges into) .mcp.json with token-pilot + context-mode. Restart your AI assistant to activate.
What You Get
- 25 MCP tools — structural reads, symbol search, git analysis, module routing, session analytics → tools reference
- PreToolUse hooks — block heavy
Grep/Bash/Readcalls; redirect to efficient alternatives → hooks & modes - Tool profiles — trim advertised
tools/listto save ~2 k tokens per session → profiles & config
Client Support Matrix
| Client | MCP tools | PreToolUse hooks |
|---|---|---|
| Claude Code | ✅ | ✅ |
| Codex CLI | ✅ | ✅ |
| Cursor | ✅ | ❌ |
| Gemini CLI | ✅ | ❌ |
| Cline (VS Code) | ✅ | ❌ |
| Antigravity | ✅ | ❌ |
Hooks are written for Claude Code (the plugin's own hooks/hooks.json, or
~/.claude/settings.json for an npm install) and for Codex CLI
(npx token-pilot install-hook --client=codex, then /hooks inside Codex to
trust them). The other clients get the MCP tools; their hook systems exist but
token-pilot does not write to them yet.
On Claude Code 2.1.275 and later the plugin runs its hooks inside Claude Code as a mod — no process per tool call, and a big Read comes back as an outline instead of a refusal. Older versions keep the command hooks → Claude Code mods
Manual config snippets for each client → installation guide
Enforcement Mode
TOKEN_PILOT_MODE controls how aggressively Token Pilot redirects heavy native tool calls:
| Value | Behaviour |
|---|---|
advisory |
Allow all — hooks pass through, advisory notes only |
deny (default) |
Block heavy Grep/Bash patterns; intercept large Read calls |
strict |
Deny + auto-cap MCP output (smart_read ≤ 2 000 tokens, find_usages → list mode, smart_log → 20 commits) + refuse an Edit of a code file not prepared with read_for_edit |
TOKEN_PILOT_MODE=strict npx token-pilot
Ecosystem
Token Pilot owns input tokens — the stuff Claude reads from files, git, search. The other half of a session (what Claude writes back, how it executes code, how it remembers state across days) is owned by separate tools. They compose cleanly:
| Tool | Owns | Typical savings |
|---|---|---|
| Token Pilot | code reads, git, search | 60-90% input |
| caveman | Claude's response prose (terse-speak skill) | ~75% output |
| ast-index | the structural indexer Token Pilot rides on | foundation |
| context-mode | sandboxed shell / python / js execution | 90%+ on big stdout |
A session that pairs token-pilot + caveman typically hits ~85-90% total reduction — each cuts a different half, no overlap. Install what you need; none of them assume the others are present.
Rules of thumb: read code → smart_read/read_symbol; execute code with big output → context-mode execute; bash-only agent → ast-index CLI. Never copy the whole stack into CLAUDE.md — Token Pilot's doctor warns when CLAUDE.md exceeds 60 lines.
Supported Languages
TypeScript, JavaScript, Python, Go, Rust, Java, Kotlin, C#, C/C++, PHP, Ruby. Non-code (JSON/YAML/Markdown/TOML) gets structural summaries. Regex fallback handles most other languages.
Update / New Machine
Claude Code (plugin — recommended):
# Install on a new machine:
claude plugin marketplace add https://github.com/Digital-Threads/token-pilot
claude plugin install token-pilot@token-pilot
# Update to latest:
claude plugin update token-pilot
Other clients (Cursor, Codex, Cline, …):
# Install on a new machine:
npx -y token-pilot init
# Update to latest — npx always pulls fresh, just restart your client.
# Or if installed globally:
npm i -g token-pilot@latest
npx token-pilot install-hook
Tips for Claude Code 2.1.139+
The May 2026 Claude Code update changed a few things that affect how token-pilot is invoked. Nothing breaks on older versions — these are quality-of-life notes for the newer ones.
-
Cold ast-index calls — raise
MCP_TOOL_TIMEOUT. The firstfind_usages/outline/read_symbolon a large repo triggers an index build. Default per-MCP-tool timeout (60 s) is enough for ~50k-file repos; bigger ones benefit fromMCP_TOOL_TIMEOUT=120000in~/.claude/settings.json. Subsequent calls hit the cache and return in ~50 ms. -
Background sessions with
--mcp-config. Dispatching a worker viaclaude agentsor--bgwith--mcp-config /path/to/other.jsonswaps the MCP set for that session. Iftoken-pilotis not in the override config, MCP tools (smart_read,find_usages, …) are unavailable in that worker. On a Claude Code that loads the token-pilot mod, the hooks (Read / Bash / Grep / Edit in strict mode / Agent) see the tools are missing and step aside. The command hooks of an older Claude Code only see a server turned off in/mcp. Addtoken-pilotto the override config if you want the tools. -
claude plugin details token-pilot. Shows the projected per-turn token cost, the hook event names, and the MCP server entry. The skill list and the LSP list are all auto-discovered from the canonical sub-folders.
Power-user — undocumented Claude Code features that pair with token-pilot
These fields come from reverse-engineering @anthropic-ai/claude-code@2.1.87
source (see the May 2026 Habr write-up). They work today but are
not in the official Claude Code docs, so use at your own risk.
Bootstrap-once hook (once: true)
The plugin ships a SessionStart hook flagged once: true —
Claude Code runs it once per project then auto-removes the entry.
It surfaces a friendly hint when
install-ast-index hasn't been run yet. v0.35.0+.
Async telemetry (async: true)
PostToolUse hooks (Bash, Task) are marked async: true so they
no longer add wall-clock to the hot path — telemetry writes fire
in the background.
Auto-mode permissions (user-side)
If you want full auto-approval for safe commands, the YOLO classifier reads natural-language environment descriptions:
{
"autoMode": {
"allow": ["Bash(git status)", "Bash(npm test)", "Read", "Grep"],
"soft_deny": ["Bash(git push *)", "Bash(rm *)", "Write(.env)"],
"environmentDescription":
"This is a development laptop. Read-only ops are safe; deny anything touching credentials or production."
}
}
token-pilot's enforcement still runs on top (raw Read on large files is denied first, regardless of autoMode).
Permission rule syntax cheat-sheet
Bash(npm *) # wildcard after "npm "
Bash(git commit *) # specific subcommand
Read(*.ts) # extension
Read(src/**/*.ts) # recursive + extension
Write(src/**) # recursive all files
mcp__token-pilot # all token-pilot MCP tools
mcp__token-pilot__smart_read # one specific MCP tool
* matches inside word boundaries (shell-glob); ** is recursive.
The if field on hooks uses the same syntax.
Experimental: transparent Read rewrite
Set TOKEN_PILOT_HOOK_REWRITE=1 to swap the "deny + suggest" Read
hook behaviour for an updatedInput rewrite — Claude Code's
undocumented field that silently bounds the Read to its first 200
lines instead of bouncing the call. The structural summary still
rides along in additionalContext. Default OFF because the field
is undocumented and may change.
Experimental: SubagentStop budget feedback (CC 2.1.163+)
Every subagent completion lands a task-telemetry row via the
SubagentStop hook (that's how stats --tasks knows what you
dispatched). With TOKEN_PILOT_SUBAGENT_FEEDBACK=1 the same hook also
returns additionalContext — when a token-pilot workflow fan-out is
at ≥90 % of its token ceiling, each completing agent gets a wind-down
note so a hundred-agent /workflow run stops before blowing the
budget.
Requires Claude Code 2.1.163+. Returning additionalContext from
SubagentStop is only honoured there; older Claude Code labels it a
hook error. Default OFF for that reason — enable only once
claude --version reports 2.1.163 or later.
What's new for Claude Code 2.1.151+
These notes are about behaviour you'll see automatically once you
update both Claude Code and token-pilot@latest. No extra
configuration required.
Session title badge ([TP] Nk saved)
The SessionStart hook now sets the window/tab title to the cumulative
token savings for the current project, using Claude Code 2.1.152's
hookSpecificOutput.sessionTitle field. You'll see a badge like
[TP] 1.2M saved in the title bar so you can confirm at a glance
that the plugin is doing its job.
Hardened skills (disallowed-tools)
The three bundled skills (guide, install, stats) declare
disallowed-tools (Claude Code 2.1.152+) so a runaway model can't
issue Write / Edit / Task while the skill is on display. The
install skill keeps Bash because it has to run
npx token-pilot install-ast-index; the other two have Bash
disallowed too.
Auto mode on third-party providers
Claude Code 2.1.158 opened auto mode to Bedrock / Vertex / Foundry
on Opus 4.7 + 4.8. If you're on one of those, opt in with
CLAUDE_CODE_ENABLE_AUTO_MODE=1. token-pilot's deny-Read /
deny-Bash gates still run on top — auto mode never bypasses them.
Fleet workflows (v0.38.0)
When you fan a task across many subagents — via Claude Code's
/workflow, the Agent tool, or your own orchestration — token-pilot
can treat the whole run as one budgeted, telemetry-tagged unit.
token-pilot owns the workflow boundary, so this works regardless of whether Claude Code propagates a workflow id. You wrap the batch:
# Start a workflow — prints an export line you eval into your shell
eval "$(token-pilot workflow start "review every PR from last sprint" --budget=2000000)"
# ...now run your fan-out work. Every hook event is tagged with the
# workflow id automatically (TOKEN_PILOT_WORKFLOW_ID is set).
token-pilot workflow status # live budget + task counts
token-pilot workflow list # all recorded workflows
token-pilot workflow end # stamp it finished + print summary
While a workflow is active:
- Every
event:"task"/denied/diagnosticrow inhook-events.jsonlcarriesworkflow_id, so you can slice one fan-out run out of the global log. - The PreToolUse:Agent hook watches the token ceiling. At ≥90 % it
adds a wind-down note ("finish in-flight
work rather than starting new branches") and logs a
workflow_near_budgetdiagnostic — visible inworkflow status. Dispatch is never hard-blocked on budget (a half-finished fan-out is worse than a small overrun). - The window title switches to
[TP] wf · N tasks · X%so a long run shows live progress.
Claude Code's own /workflow (2.1.154+) does not expose a
per-workflow id env var to subagents (verified against the 2.1.161
bundle — it has only a CLAUDE_CODE_WORKFLOWS feature flag). So
token-pilot's workflows are independent: they rely on our own
TOKEN_PILOT_WORKFLOW_ID. If CC adds a per-workflow env var later,
activeWorkflowId() already probes for it — no config change needed.
Troubleshooting
npx token-pilot doctor # diagnose: ast-index, config, upstream drift
# "ast-index not found" → npx token-pilot install-ast-index
# "hooks not firing" → restart your AI assistant
Credits
Built on ast-index · @ast-grep/cli · MCP SDK · chokidar
License
MIT
token-pilot MCP Fragen
Wie füge ich token-pilot MCP zu Claude Code hinzu?
Führe claude mcp add token-pilot -- npx -y token-pilot in deinem Terminal aus. Füge --scope user hinzu, damit der Server in jedem Projekt verfügbar ist.
Wie füge ich token-pilot MCP zu Cursor hinzu?
Öffne ~/.cursor/mcp.json und füge den Server unter mcpServers hinzu, mit der Cursor-Config aus dem Installationsabschnitt oben.
Wie viel kann ich an Tokens sparen?
Du kannst den Kontextverbrauch in KI-Coding-Assistenten um bis zu 90 % senken.
Was passiert mit kleinen Dateien?
Dateien mit weniger als 200 Zeilen werden vollständig ohne zusätzlichen Overhead zurückgegeben.
Welche KI-Clients werden unterstützt?
Es unterstützt Claude Code und Codex CLI mit vollen MCP tools und Hooks, während Clients wie Cursor, Gemini CLI und Cline die MCP tools unterstützen.
Welche Enforcement-Modi gibt es?
Es gibt drei Modi: advisory (erlaubt alles), deny (blockiert schwere Aufrufe, Standard) und strict (blockiert schwere Aufrufe und setzt automatische Limits für den MCP-Output).