AST tabanlı yapısal okumalar ve araç müdahale kancaları kullanarak yapay zeka kodlama token tüketimini %90'a kadar azaltır.
Ayrıca bilinen adı Digital-Threads/token-pilot
- Yıldızlar
- 5
- Araçlar
- —
- İndirmeler, 30 gün
- —
- En son sürüm
- 2.0.0
- Son commit
- 6 Kas 2026
- Lisans
- —
token-pilot MCP nedir?
token-pilot bir MCP sunucusudur. AST tabanlı yapısal okumalar ve araç müdahale kancaları kullanarak yapay zeka kodlama token tüketimini %90'a kadar azaltır.
Özet, projenin README dosyasından oluşturuldu
token-pilot MCP sunucusu hakkında
Token Pilot, yapay zeka kodlama asistanlarının token tüketimini %90'a kadar azaltmak için tasarlanmış özel bir araçtır. Bu tasarrufu, ağır ve tam dosya okuma işlemleri yerine yapısal, AST tabanlı işlemler kullanarak sağlar. Bu sayede geliştiriciler, pahalı frontier modellerinin devasa miktardaki gereksiz kod bağlamını işlemek yerine akıl yürütmeye odaklanmasını sağlar. Sistem iki ana katman üzerinden çalışır: hedeflenmiş veri alımı için 25 adet MCP aracı seti ve verimsiz yerel komutları yakalayıp yönlendiren PreToolUse kancaları.
Kullanıcılar, yapılandırmayı başlatmak için npx kullanarak bu sunucuyu yerel olarak dağıtabilirler. Gelişmiş kanca sistemleri sayesinde özellikle Claude Code ve Codex CLI için optimize edilmiştir; ancak Cursor, Cline ve Gemini CLI gibi diğer istemciler için de standart MCP araçları sunar. Sunucu; TypeScript, Python, Go, Rust ve Java dahil olmak üzere geniş bir programlama dili yelpazesini destekler. Tavsiye niteliğindeki notlardan, ağır Grep veya Bash çağrılarını engelleyen ve bütçe uyumluluğunu sağlamak için çıktı sınırlandırması uygulayan katı (strict) moda kadar farklı uygulama modları sunar.
Neler yapabilirsiniz
- 1Bağlam penceresi kullanımını azaltınBir geliştirici, yüzlerce satır kod yüklemek yerine bir dosyanın yapısal taslağını talep edebilir.
- 2Hedefli sembol alımıBir yapay zeka, tüm bir modülü okumak yerine yalnızca düzenleme için gereken belirli fonksiyonu çekebilir.
Projenin README dosyasından alınmıştır. Her kullanım durumu, oradaki bir alıntı ile kontrol edilir.
token-pilot MCP nasıl yüklenir
Biçimler 10 Kas 2026 tarihinde doğrulandıCursor'a ekleGoose'a ekletoken-pilot MCP'yi Claude Code içine yükleyin
$ claude mcp add token-pilot -- npx -y token-pilottoken-pilot MCP'yi Cursor içine yükleyin
~/.cursor/mcp.json
{
"mcpServers": {
"token-pilot": {
"command": "npx",
"args": [
"-y",
"token-pilot"
]
}
}
}token-pilot MCP'yi VS Code içine yükleyin
.vscode/mcp.json
{
"servers": {
"token-pilot": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"token-pilot"
]
}
}
}token-pilot MCP'yi VS Code CLI içine yükleyin
$ code --add-mcp '{"name":"token-pilot","type":"stdio","command":"npx","args":["-y","token-pilot"]}'token-pilot MCP'yi Claude Desktop içine yükleyin
claude_desktop_config.json
{
"mcpServers": {
"token-pilot": {
"command": "npx",
"args": [
"-y",
"token-pilot"
]
}
}
}token-pilot MCP'yi Codex içine yükleyin
$ codex mcp add token-pilot -- npx -y token-pilottoken-pilot MCP'yi Codex config.toml içine yükleyin
~/.codex/config.toml
[mcp_servers.token-pilot] command = "npx" args = ["-y", "token-pilot"]
token-pilot MCP'yi Gemini CLI içine yükleyin
$ gemini mcp add -s user token-pilot npx -- -y token-pilottoken-pilot MCP'yi Gemini settings.json içine yükleyin
~/.gemini/settings.json
{
"mcpServers": {
"token-pilot": {
"command": "npx",
"args": [
"-y",
"token-pilot"
]
}
}
}Yapılandırma
TOKEN_PILOT_MODE
| Ad | Açıklama | Sunucu |
|---|---|---|
| TOKEN_PILOT_MODE | — |
Otomatik kontroller
Çalıştırıldı 13 Kas 2026Tam rapor →Otomatik kontrollerimizden geçti. Bu bir güvenlik denetimi değildir: kodu okuyun ve sunucuya ihtiyaç duyduğu en dar erişimi verin. Kontroller nasıl çalışır · Daha fazla puan için nelerin düzeltileceği
- Kaynak deposu bağlantılı ve erişilebilirdigital-threads/token-pilot is public and reachablegithub.com/digital-threads/token-pilot ↗Geçti
- Paket, bu depoyu kaynağı olarak gösteriyortoken-pilot names digital-threads/token-pilot as sourcenpmjs.com/package/token-pilot ↗Geçti
- Derleme kökeni (Sigstore onayı)No build attestation published for this releaseKontrol edilmedi
- Açık kaynak lisansı (OSI)No licenseBulgu
- Son bir yıl içinde commit veya sürüm mevcutLast commit or release 2026-11-06github.com/digital-threads/token-pilot ↗Geçti
- OpenSSF ScorecardKontrol edilmedi
- Paket adı popüler bir pakete yakın değilNo popular package one edit away from token-pilotGeçti
- Pakette veya bağımlılıklarında kritik uyarı yok116 resolved dependencies checked; no critical advisoryosv.dev ↗Geçti
- Modele yönelik gizli talimat yok0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersGeçti
- Yıkıcı araçlar etiketlenmişKontrol edilmedi
- Uzak uç nokta MCP el sıkışmasına yanıt veriyorKontrol edilmedi
Token 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 soruları
token-pilot MCP'yi Claude Code'a nasıl eklerim?
Terminalinizde claude mcp add token-pilot -- npx -y token-pilot komutunu çalıştırın. Her projede kullanılabilir olması için --scope user ekleyin.
token-pilot MCP'yi Cursor'a nasıl eklerim?
~/.cursor/mcp.json dosyasını açın ve yukarıdaki yükleme bölümünde gösterilen Cursor yapılandırmasını kullanarak sunucuyu mcpServers altına ekleyin.
Token kullanımında ne kadar tasarruf edebilirim?
Yapay zeka kodlama asistanlarında bağlam (context) tüketiminden %90'a kadar tasarruf edebilirsiniz.
Küçük dosyalara ne oluyor?
200 satırın altındaki dosyalar, herhangi bir ek yük getirilmeden tamamen döndürülür.
Hangi yapay zeka istemcileri destekleniyor?
Tam MCP araçları ve kancalarıyla Claude Code ve Codex CLI'ı destekler; Cursor, Gemini CLI ve Cline gibi istemciler ise MCP araçlarını destekler.
Uygulama modları nelerdir?
Üç mod bulunur: advisory (tümüne izin verir), deny (ağır çağrıları engeller, varsayılan) ve strict (ağır çağrıları engeller ve MCP çıktısını otomatik olarak sınırlar).