Mede os custos de tokens por turno para arquivos de instrução de agentes de IA e fornece correções automatizadas para reduzir o overhead de contexto do repositório.
Também conhecido como TorutDev/turntax
- Stars
- 0
- Ferramentas
- —
- Downloads, 30 dias
- —
- Versão mais recente
- 0.11.0
- Último commit
- 9 de nov. de 2026
- Licença
- MIT
O que é o MCP turntax?
turntax é um MCP server. Mede os custos de tokens por turno para arquivos de instrução de agentes de IA e fornece correções automatizadas para reduzir o overhead de contexto do repositório.
Resumo gerado a partir do README do projeto
Sobre o MCP server de turntax
Desenvolvedores que utilizam agentes de codificação de IA podem reduzir o overhead de contexto do repositório e os custos de tokens usando o turntax para medir os gastos de arquivos de instrução por turno. A ferramenta analisa como diferentes agentes como Cursor, Claude Code, GitHub Copilot e Windsurf carregam arquivos como CLAUDE.md ou AGENTS.md para determinar exatamente quantos tokens são enviados em cada interação. Ela fornece um relatório detalhado mostrando custos estimados e identifica ineficiências na sua configuração.
Os usuários podem executar a ferramenta localmente via npx ou analisar repositórios públicos do GitHub por meio de uma interface web. Para contagens precisas de tokens com Claude ou Gemini, o servidor requer uma API key via as flags --claude-api ou --gemini-api. Além da medição, a ferramenta oferece correções automatizadas para resolver linhas duplicadas, regras conflitantes ou seções excessivamente grandes que deveriam ser movidas para arquivos com escopo de path ou skills. Isso ajuda a manter conjuntos de instruções enxutos que minimizam tanto a latência quanto o custo em cada turno do agente.
O que você pode fazer com ele
- 1Analisar custos de tokens por turnoCalcule exatamente quantos tokens estão sendo enviados para um agente como Cursor ou Aider toda vez que um novo turno começa.
- 2Identificar instruções de agentes conflitantesEncontre regras contraditórias dentro do seu repositório, como requisitos diferentes de gerenciadores de pacotes, que confundem seu agente de IA.
- 3Automatizar a limpeza de arquivos de instruçãoAplique correções seguras para remover linhas duplicadas ou mover seções grandes e específicas para pastas aninhadas para reduzir o contexto global.
Escrito a partir do README do projeto. Cada caso de uso é verificado com uma citação dele.
Como instalar o MCP turntax
Formatos verificados em 10 nov 2026Adicionar ao CursorAdicionar ao GooseInstalar o MCP turntax no Claude Code
$ claude mcp add turntax -- npx -y turntaxInstalar o MCP turntax no Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"turntax": {
"command": "npx",
"args": [
"-y",
"turntax"
]
}
}
}Instalar o MCP turntax no VS Code
.vscode/mcp.json
{
"servers": {
"turntax": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"turntax"
]
}
}
}Instalar o MCP turntax no VS Code CLI
$ code --add-mcp '{"name":"turntax","type":"stdio","command":"npx","args":["-y","turntax"]}'Instalar o MCP turntax no Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"turntax": {
"command": "npx",
"args": [
"-y",
"turntax"
]
}
}
}Instalar o MCP turntax no Codex
$ codex mcp add turntax -- npx -y turntaxInstalar o MCP turntax no Codex config.toml
~/.codex/config.toml
[mcp_servers.turntax] command = "npx" args = ["-y", "turntax"]
Instalar o MCP turntax no Gemini CLI
$ gemini mcp add -s user turntax npx -- -y turntaxInstalar o MCP turntax no Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"turntax": {
"command": "npx",
"args": [
"-y",
"turntax"
]
}
}
}Verificações automatizadas
Executado em 14 de nov. de 2026Relatório completo →Passou em nossas verificações automatizadas. Isso não é uma auditoria de segurança: leia o código e dê ao servidor o acesso mais restrito de que ele precisa. Como as verificações funcionam
- Repositório de origem vinculado e acessíveltorutdev/turntax is public and reachablegithub.com/torutdev/turntax ↗Passou
- O pacote indica este repositório como sua origemturntax names torutdev/turntax as sourcenpmjs.com/package/turntax ↗Passou
- Proveniência da build (atestação Sigstore)No build attestation published for this releaseNão verificado
- Licença de código aberto (OSI)MITspdx.org/licenses/MIT.html ↗Passou
- Commit ou release no último anoLast commit or release 2026-11-09github.com/torutdev/turntax ↗Passou
- OpenSSF ScorecardNão verificado
- Nome do pacote não é próximo a um pacote popularNo popular package one edit away from turntaxPassou
- Nenhum aviso crítico no pacote ou em suas dependências2 resolved dependencies checked; no critical advisoryosv.dev ↗Passou
- Sem instruções ocultas para o modelo0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPassou
- Ferramentas destrutivas estão rotuladasNão verificado
- O endpoint remoto responde ao handshake do MCPNão verificado
README
Ver no GitHubturntax
Coding agents re-send their instruction files with every turn. turntax measures that fixed per-turn cost for a repository, for every agent that reads it, and shows where to cut it.
npx turntax
Try it in the browser, with nothing uploaded: https://torutdev.github.io/turntax/ — drop a folder or enter a public GitHub repository. Links like https://torutdev.github.io/turntax/?repo=owner/name open straight to that repository's report.
State of agent instruction files: what turntax finds in 100 popular repositories, a new edition every month with pinned commits and the script to reproduce it (scripts/state-of.mjs).
Set up the GitHub Action and a config in one command:
npx turntax init
Supported agents
Each agent's documented loading rules decide what is sent on every turn, what loads only when the agent works in a folder or touches a matching file, and what is ignored.
| Agent | Files it reads from the repository |
|---|---|
| Aider | files listed under read: in .aider.conf.yml (CONVENTIONS.md only when listed or passed with --read) |
| Amp | AGENTS.md (or AGENT.md / CLAUDE.md), nested AGENTS.md, @-mentioned files, .agents/skills, .claude/skills |
| Augment Code | AGENTS.md and CLAUDE.md at every level, .augment-guidelines, .augment/rules/ (by type), skills in .augment, .claude, .agents |
| Claude Code | CLAUDE.md, CLAUDE.local.md, .claude/rules, skills, commands, subagents, AGENTS.md when there is no CLAUDE.md |
| Cline | .clinerules/, .cline/rules/, skills in .cline, .clinerules, .claude |
| Continue | .continue/rules/ |
| Cursor | .cursor/rules/*.mdc, .cursorrules, AGENTS.md, CLAUDE.md, skills in .agents, .cursor, .claude, .codex |
| Devin Local / Devin CLI | AGENTS.md, AGENTS.local.md, AGENT.md, .windsurfrules, CLAUDE.md at every level, .devin/rules/, .windsurf/rules/, .cursor/rules/, skills |
| Factory Droid | AGENTS.md / CLAUDE.md (also in .factory, .agents, .agent), DESIGN.md, .factory/skills, .agents/skills, .factory/droids |
| Gemini CLI | GEMINI.md, skills in .agents and .gemini |
| GitHub Copilot | .github/copilot-instructions.md, .github/instructions/, AGENTS.md, CLAUDE.md, GEMINI.md, .claude/rules, skills in .github, .claude, .agents (as Copilot CLI loads them) |
| Goose | .goosehints, AGENTS.md, @-included files, skills in .agents, .goose, .claude |
| Google Jules | root AGENTS.md |
| JetBrains Junie | .junie/AGENTS.md, or AGENTS.md with .junie/rules/, or .junie/guidelines; skills in .junie, .agents |
| Kilo Code | the first of AGENTS.md, AGENT.md, CLAUDE.md, CONTEXT.md, .kilo/rules, .kilocode/rules, mode rules, .kilocoderules, skills |
| Kiro | .kiro/steering/, AGENTS.md (nested ones too, every turn), .kiro/skills |
| OpenAI Codex | AGENTS.md, AGENTS.override.md, .agents/skills |
| OpenCode | AGENTS.md, or CLAUDE.md when there is none; skills in .opencode, .claude, .agents |
| Roo Code | .roo/rules/, .roo/rules-{mode}/, .roorules, AGENTS.md, skills in .roo, .agents |
| TRAE | .trae/rules/ (alwaysApply, globs, description; three folder levels), .trae/skills |
| Warp | WARP.md, else AGENTS.md; skills in .agents, .warp, .claude and seven other folders |
| Windsurf Cascade | .devin/rules/, .windsurf/rules/, .windsurfrules, AGENTS.md, skills (legacy agent; new conversations use Devin Local) |
| Zed | the first of .rules, .cursorrules, .windsurfrules, .clinerules, .github/copilot-instructions.md, AGENT.md, AGENTS.md, CLAUDE.md, GEMINI.md; .agents/skills |
Where an agent reads the same skill name from two folders, it is counted once, in the order the agent documents (or an assumed order, noted for that agent).
Agents that load exactly the same files share one row in the report (files loaded only as a /command, which cost nothing per turn, do not split a row):
always o200k/turn on-demand model tokens/turn counted by 100 turns cached agents
4 272 53 (no selected model) Claude Code
1 63 0 GPT-6.1 Sol 63 estimate (o200k_base proxy) $0.01 $0.0006 OpenAI Codex, Roo Code, Kiro, JetBrains Junie
1 17 0 (no selected model) Gemini CLI
5 311 59 GPT-6.1 Sol 311 estimate (o200k_base proxy) $0.06 $0.0031 Cursor
4 307 55 GPT-6.1 Sol 307 estimate (o200k_base proxy) $0.06 $0.0031 GitHub Copilot
2 75 0 GPT-6.1 Sol 75 estimate (o200k_base proxy) $0.01 $0.0008 Windsurf Cascade
2 21 32 GPT-6.1 Sol 21 estimate (o200k_base proxy) $0.0042 $0.0002 Cline
1 11 0 GPT-6.1 Sol 11 estimate (o200k_base proxy) $0.0022 $0.0001 Zed
3 84 32 GPT-6.1 Sol 84 estimate (o200k_base proxy) $0.02 $0.0008 Goose, OpenCode, Kilo Code
3 84 51 GPT-6.1 Sol 84 estimate (o200k_base proxy) $0.02 $0.0008 Amp
3 108 32 GPT-6.1 Sol 108 estimate (o200k_base proxy) $0.02 $0.0011 Warp
2 282 19 GPT-6.1 Sol 282 estimate (o200k_base proxy) $0.06 $0.0028 Factory Droid
4 303 51 GPT-6.1 Sol 303 estimate (o200k_base proxy) $0.06 $0.0030 Augment Code
1 63 0 (no selected model) Google Jules
7 330 69 GPT-6.1 Sol 330 estimate (o200k_base proxy) $0.07 $0.0033 Devin Local / Devin CLI
Advice (savings are estimates in o200k tokens per turn)
HIGH duplicate CLAUDE.md, AGENTS.md [saves ~48 tokens/turn]
3 identical lines are loaded twice every turn by cursor, copilot, factory-droid, augment, devin. Keep them in one file.
HIGH contradiction AGENTS.md, CLAUDE.md [saves ~11 tokens/turn]
Conflicting package manager: "Always use npm for installs and scripts in this repository." (AGENTS.md:3) vs "Always use pnpm for installs and scripts in this repository." (CLAUDE.md:5). (Removing the outdated line.)
MEDIUM scopable-section CLAUDE.md:12 [saves ~128 tokens/turn]
Section "API package" is mostly about packages/api/. Move it to packages/api/AGENTS.md (or CLAUDE.md), a path-scoped rule, or an instructions file ...
(Excerpt of the output for test/fixtures/mixed with --models gpt-6.1-sol.)
What it counts, and how
| Model family | How tokens are counted | Label |
|---|---|---|
| OpenAI GPT-5.x, gpt-oss | Offline with o200k_base (the encoding OpenAI's tiktoken maps them to) |
exact |
| OpenAI GPT-6.x | Offline with o200k_base; OpenAI has not published a newer encoding |
estimate |
| Claude | Only Anthropic's count_tokens API, with your key and --claude-api |
API count |
| Gemini | Only Google's countTokens API, with your key and --gemini-api |
API count |
Claude's tokenizer is not public, and Anthropic's docs note that newer Claude models produce noticeably more tokens than older ones for the same text. turntax never shows an OpenAI count as a Claude or Gemini number: without a key those rows say "needs API key". The o200k column is a labelled reference count for every file.
Cost per N turns = tokens per turn × N × input price. The "cached" column assumes every turn reads the context from the prompt cache. Prices come from a dated table with a source link per model (turntax --list-models); pass --prices my-prices.json to use your own.
See docs/how-it-counts.md for the loading rules per agent and their sources.
Advice
All checks are deterministic. Each one shows an estimated saving in o200k tokens per turn.
- duplicate: identical lines in two files. A per-turn saving only when one tool loads both; otherwise flagged as drift risk.
- contradiction: conflicting rules reaching the same agent (package manager, indentation, quotes, semicolons).
- scopable-section: a section mostly about one directory that could load only there (nested file, path-scoped rule,
applyTo). - oversized-section: a large always-loaded section that could become an on-demand skill.
- size-limit: documented limits (CLAUDE.md under 200 lines, Codex's 32 KiB cut-off, Windsurf's 12,000 characters per rule and 6,000 for global rules, Cursor's 500 lines, Factory's 80,000 characters, Augment's 49,512 characters).
- misconfigured: files a tool ignores, such as
.mdfiles in.cursor/rulesor Windsurf rules without atrigger. - stale-reference: referenced files or
npm runscripts that no longer exist. - non-english: non-English sections. The token multiplier is measured only against an English version you supply (
--english CLAUDE.md=CLAUDE.en.md) or, if you opt in, a Claude translation (--translate).
Fixing
npx turntax --fix # print a diff of the safe fixes; nothing is changed
npx turntax --fix --write # apply them
--fix handles four kinds of advice:
- duplicate: removes lines from a file when every agent that reads the file also reads the same lines every turn from another file. Skill, command and subagent files are left whole. A
CLAUDE.mdthat repeats at least 80% of the lines of theAGENTS.mdnext to it, at least 3 of them full sentences, and every file it imports, keeps only its own lines and imports the rest with@AGENTS.md, as Claude Code's docs suggest; agents that read both stop paying for the copy, and the summary says how much any agent now reads on top. - scopable-section: moves a section into the folder it is about: the same file name there (
packages/api/CLAUDE.md), a nestedAGENTS.md, or a Claude Code rule withpaths:. The folder the section is about must already exist, and sections with@importsor relative links stay put. A section moves together with its subsections. - oversized-section: moves a large procedure (a section of at least
--section-tokens, 600 by default, whose heading names a release, deploy, setup or similar procedure, or that is mostly numbered steps; each subsection must pass too) into a new skill,.claude/skills/<name>/SKILL.mdfor Claude Code or.agents/skills/<name>/SKILL.mdfor Codex, and leaves the heading with a one-line pointer. Only the skill's name and description load every turn. Many agents now read one or both folders, but not all of them do (Zed reads only.agents/skills, for example), so by default this fix is often refused;--toolslimits the check to the agents you use. - misconfigured: renames
.mdfiles in.cursor/rulesto.mdc.
Before a fix is kept, the files are classified again with the change applied: every agent must still read every line it read before, including files reached through @imports, and as often as before. The exceptions are moved text: a section moved into a folder may load only when the agent works there, and a procedure moved into a skill only when the skill is used. Otherwise the fix is skipped and the reason is printed. A moved section can reach agents that did not read it before (a nested AGENTS.md is read by more agents than a CLAUDE.md); the summary names them. By default that check covers every supported agent, so a section of AGENTS.md usually stays where it is, because some agents read only the root file. --tools codex,claude-code limits the check to the agents you use.
In preview the diff is on stdout and works with git apply, and the summary is on stderr; with --write the summary is on stdout. --write checks that no file changed since it was read and writes nothing if one did. Symlinked files, their targets and files in symlinked folders are never changed. Contradictions and stale references need a person to decide, so --fix leaves them alone. Files that are also documents for people (DESIGN.md, CONTEXT.md, agents.md, Agents.md, Claude.md) are never changed, and no file is created whose name differs from one of them only by case.
The web page shows the same fixes for any repository you load, with a downloadable fix.patch.
Config file
Put defaults in turntax.config.json in the audited folder (or pass --config <file>). Command-line flags override it.
{
"tools": ["claude-code", "codex", "cursor"],
"models": ["claude-sonnet-5.5", "gpt-6.1-sol"],
"maxTokens": 8000,
"maxIncrease": 500,
"ignore": ["docs/agents/archive/", "**/*.draft.md"]
}
Keys: tools, models, turns, maxTokens, maxIncrease (applies only with --compare or --baseline), sectionTokens, and ignore: globs of instruction files to leave out, relative to the audited folder (* and ? within a folder name, ** across folders, a trailing / for a whole folder). Ignored files are also left out of --compare and are never changed by --fix. Unknown keys and ids are errors.
MCP servers
Every MCP server an agent starts adds its tool definitions (names, descriptions, input schemas) to the context. turntax reads the agents' MCP configs and lists the servers each agent starts:
| Agent | Project config | User config |
|---|---|---|
| Claude Code | .mcp.json |
~/.claude.json (user and per-project servers) |
| Cursor | .cursor/mcp.json |
~/.cursor/mcp.json |
| GitHub Copilot | .mcp.json, .github/mcp.json, .vscode/mcp.json (deprecated) |
~/.copilot/mcp-config.json |
| Gemini CLI | .gemini/settings.json |
~/.gemini/settings.json |
| Kiro | .kiro/settings/mcp.json |
~/.kiro/settings/mcp.json |
| Roo Code | .roo/mcp.json |
|
| OpenAI Codex | .codex/config.toml (trusted projects) |
~/.codex/config.toml |
| OpenCode | opencode.json, opencode.jsonc |
~/.config/opencode/opencode.json |
| Zed | .zed/settings.json |
|
| Windsurf Cascade | ~/.config/devin/mcp_config.json |
|
| Devin Local / Devin CLI | .devin/mcp_config.json, .devin/mcp_config.local.json; imports .mcp.json, .cursor/mcp.json, opencode.json, .zed/settings.json |
~/.config/devin/mcp_config.json; imports Claude Code, Windsurf, OpenCode and Zed user configs |
| Augment Code | .augment/settings.json, .augment/settings.local.json |
~/.augment/settings.json |
| Factory Droid | .factory/mcp.json |
~/.factory/mcp.json |
| Kilo Code | kilo.json(c), .kilo/kilo.json(c), opencode.json(c) |
~/.config/kilo/kilo.json(c) |
| Warp | (project configs never start on their own) | ~/.warp/.mcp.json |
A server name an agent finds in several configs is counted once, by the agent's documented precedence (or config order, marked as assumed); the other copies are listed as overridden. Tool filters in the configs (Codex enabled_tools/disabled_tools, Gemini includeTools/excludeTools, Factory enabledTools/disabledTools, Copilot tools, Kiro, Roo and Windsurf disabledTools) are applied.
Counting the tool definitions needs the servers running, so it is opt-in:
npx turntax --mcp
--mcp starts each stdio server with the command from its config (in the repository folder; environment variables are expanded into commands, URLs and headers the repository config defines, as the agents themselves do) and connects to streamable HTTP servers, asks for tools/list, and counts the definitions as JSON with o200k. A server several agents share is started once. Environment variables in the config (${VAR}, ${VAR:-default}, ${env:VAR}, {env:VAR}, ${workspaceFolder}) are expanded; servers that need a VS Code ${input:...} prompt, legacy SSE and WebSocket servers and servers that fail or time out (--mcp-timeout, default 30 s) are listed with the reason and not counted.
Claude Code defers MCP tool definitions by default (tool search): only the tool names are in context until a tool is used, so its row counts the names and shows the full size separately. A server with alwaysLoad: true, or a tool marked _meta["anthropic/alwaysLoad"], is counted in full. Server instructions load at the start of every session and are counted for Claude Code (cut at 4,096 characters, as Claude Code does), Gemini CLI, Codex and Kilo Code, whose docs say they reach the context.
MCP tokens are an o200k estimate and are not included in the model cost columns.
User-level files
Agents also read instruction files from your home directory in every project. --include-user adds them in a separate user/turn column and a total:
npx turntax --include-user
It reads only the locations the agents document (the full list, per agent, is in docs/how-it-counts.md): for example ~/.claude/, ~/.codex/AGENTS.md, ~/.agents/, ~/.gemini/, ~/.copilot/, ~/.cursor/skills, Windsurf's and Devin's global_rules.md and ~/.config/devin/, Cline's global rules, ~/.roo/, ~/.kiro/, ~/.junie/, ~/.config/goose/, ~/.config/amp/, ~/.config/opencode/, ~/.config/zed/AGENTS.md, ~/.factory/, ~/.augment/, ~/.config/kilo/, ~/.warp/ and ~/.trae/skills, plus the user MCP configs above. Contradictions and duplicates between user-level and repository files are reported. User-level files never count toward the badge or --max-tokens, so the result does not depend on who runs it.
Comparing with a baseline
npx turntax --compare origin/main # instruction files at a git ref, read with git show
npx turntax --json --out before.json # or save a report ...
npx turntax --baseline before.json # ... and compare with it later
npx turntax --compare origin/main --max-increase 200 # exit 1 when any agent grows by more than 200 tokens
The comparison covers repository instruction files (o200k), per agent and per file, and lists MCP servers that were added or removed. It never changes the working tree.
GitHub Action
The repository is also an Action, listed on the GitHub Marketplace; npx turntax init writes this workflow and a turntax.config.json for you. On pull requests it compares with the base branch, posts one comment (updated on every push), writes the report to the job summary and marks findings on the lines they are about in the pull request's changed files (GitHub shows up to 10 warnings and 10 notices per step):
name: turntax
on: pull_request
permissions:
contents: read
pull-requests: write
jobs:
turntax:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: TorutDev/turntax@v0.11.0
with:
max-increase: 500 # optional: fail when an agent grows by more than 500 tokens per turn
# max-tokens: 8000 # optional: absolute budget
# args: --tools claude-code,cursor
# annotations: false # optional: no findings on the changed lines
The comment opens with a table of the change per agent and per file. When --fix has safe fixes, it says how many and how many tokens they save, with the diff folded; the full report is folded below. A turntax.config.json in the repository is read as well. Pull requests from forks get a read-only token, so the comment step is skipped there; the job summary still has the report.
pre-commit
The repository is also a pre-commit hook, which fails a commit when an agent goes over a budget. Set the budget with args, or with maxTokens in turntax.config.json; without one the hook always passes. It runs npx turntax@<version>, so it needs Node.js 22 or later on your PATH, and it does not run on pre-commit.ci, which has no system hooks.
repos:
- repo: https://github.com/TorutDev/turntax
rev: v0.11.0
hooks:
- id: turntax
args: [--max-tokens, '8000']
Options
turntax [path]
--tools <ids> agents to report (default: every agent that reads a file); see --help
--models <ids> see --list-models (default: claude-sonnet-5.5, gpt-6.1-sol, gemini-3.8-flash)
--turns <n> cost projection (default 100)
--json | --md | --badge output format (default: terminal table)
--pr-comment Markdown for a pull request comment (change first, fixes and full report folded)
--annotations GitHub Actions annotations, one per finding (--path-prefix <dir> for a subfolder)
--out <file> write the output to a file
--max-tokens <n> exit 1 when any tool loads more than n o200k tokens per turn (CI gate)
--include-user add user-level files and MCP servers from your home directory
--mcp start the configured MCP servers and count their tool definitions
--mcp-timeout <s> seconds to wait for each MCP server (default 30)
--baseline <file.json> compare with an earlier --json report
--compare <git-ref> compare with the instruction files at a git ref
--max-increase <n> exit 1 when any tool grows by more than n tokens per turn vs the baseline
--claude-api exact Claude counts (ANTHROPIC_API_KEY)
--gemini-api Gemini counts (GEMINI_API_KEY)
--english <file=en> measure a language multiplier against your English version
--translate opt-in Claude translation for that measurement (needs --claude-api)
--prices <file.json> your own price table
--section-tokens <n> threshold for oversized sections (default 600)
--fix print a diff of the safe fixes (--tools limits the agents whose context is kept)
--write with --fix, apply the changes
--config <file> read defaults from this file (default: turntax.config.json, if any)
When a selected model's price was checked more than 90 days ago, turntax says so on stderr; check the source or pass --prices.
turntax init [path] add .github/workflows/turntax.yml and turntax.config.json (--tools, --max-increase,
--force, --dry-run); existing files are kept unless --force
turntax mcp run turntax as an MCP server over stdio (see below)
Agents and MCP
turntax mcp (MCP Registry: io.github.TorutDev/turntax) is a read-only MCP server with two tools: audit (the report for a folder) and fix_preview (the --fix diff, never written). It reads turntax.config.json like the CLI and does not start MCP servers or call vendor APIs.
claude mcp add turntax -- npx -y turntax mcp
For Cursor and clients with an mcpServers map, add { "mcpServers": { "turntax": { "command": "npx", "args": ["-y", "turntax", "mcp"] } } } to their MCP config (VS Code's .vscode/mcp.json calls the map servers). On native Windows, run it through cmd /c npx -y turntax mcp if your client cannot start npx directly.
This repository is also a Claude Code plugin marketplace. The plugin adds the server and a /turntax:context-tax command:
/plugin marketplace add TorutDev/turntax
/plugin install turntax@turntax
Perguntas sobre o MCP turntax
Como adiciono o MCP turntax ao Claude Code?
Execute claude mcp add turntax -- npx -y turntax no seu terminal. Adicione --scope user para torná-lo disponível em todos os projetos.
Como adiciono o MCP turntax ao Cursor?
Abra ~/.cursor/mcp.json e adicione o servidor em mcpServers, usando a configuração do Cursor mostrada na seção de instalação acima.
O que o turntax mede?
Ele mede o custo fixo de tokens por turno de um repositório para cada agente que lê arquivos de instrução como AGENTS.md e CLAUDE.md.
Como posso corrigir os problemas encontrados pelo turntax?
Você pode usar o comando --fix para ver um diff de correções seguras ou usar --fix --write para aplicá-las diretamente aos seus arquivos.