costwright — agent budget analysis
Static worst-case token-budget analysis for LLM-agent workflows + signed budget certificates.
Installation
Ajoutez ceci à la configuration MCP de votre client (Claude Desktop : claude_desktop_config.json ; Cursor : .cursor/mcp.json ; VS Code et les autres utilisent la même forme « mcpServers »).
costwright-mcpclaude mcp add costwright-agent-budget-analysis -e 'COSTWRIGHT_API_KEY=<your costwright_api_key>' -- npx -y costwright-mcp@0.1.1
{
"mcpServers": {
"costwright-agent-budget-analysis": {
"command": "npx",
"args": [
"-y",
"costwright-mcp@0.1.1"
],
"env": {
"COSTWRIGHT_API_KEY": "<your costwright_api_key>"
}
}
}
}
Variables d'environnement
COSTWRIGHT_API_KEYsecret API key for costwright (RapidAPI key or direct Bearer). Only needed for check/certify; verify/pubkey are public.
Documentation
Tirée du README du projet sur GitHub, actualisée chaque semaine. Les liens ouvrent GitHub.
costwright — MCP server
Static worst-case token-budget analysis for LLM-agent workflows. Point it at a Python repo using LangGraph / CrewAI / OpenAI-Agents-SDK and it reports — by pure AST analysis, without running the code — the worst-case budget ceiling of every workflow graph: which units are certifiable / default-dependent / non-certifiable / runaway, and which LLM calls have no token cap. Optionally issues an Ed25519-signed budget certificate logged to a public transparency log. Wraps the hosted costwright API; backed by a Lean 4 cost-soundness theorem.
Use it before deploying an agent workflow to catch missing token caps and
while True:runaway drivers — the budget version of a type check.
Tools
| Tool | What it does | Key? |
|---|---|---|
costwright_check(repo_path, policy?) | Static budget analysis of a local repo. Returns pass/fail + counts of certifiable/default-dependent/non-certifiable/runaway units. | yes |
costwright_certify(repo_path, policy?, label?) | Issues a signed, logged budget certificate. Returns cert_id + signature + verify_url. | yes |
costwright_verify(cert_id) | Verify a certificate by id (valid/expired/revoked, signature check). | public |
costwright_pubkey() | Active Ed25519 public keys for offline verification. | public |
Setup
{
"mcpServers": {
"costwright": {
"command": "npx",
"args": ["-y", "costwright-mcp"],
"env": { "COSTWRIGHT_API_KEY": "your_rapidapi_key" }
}
}
}
The key is sent as X-RapidAPI-Key (RapidAPI channel) by default; set COSTWRIGHT_DIRECT=1 to send
it as Authorization: Bearer for the direct channel. verify and pubkey work with no key.
check/certify build a .py-only gzip archive of repo_path client-side (excluding venv,
node_modules, tests, etc.) and send it for analysis — your source is uploaded to the hosted API.
See https://eleata.io/privacy/. MIT licensed.
Questions fréquentes
Qu'est-ce que costwright — agent budget analysis ?
Static worst-case token-budget analysis for LLM-agent workflows + signed budget certificates.
Comment installer costwright — agent budget analysis ?
Il s'exécute sur votre machine. Dans Claude Code : claude mcp add costwright-agent-budget-analysis -e 'COSTWRIGHT_API_KEY=<your costwright_api_key>' -- npx -y costwright-mcp@0.1.1. Pour les autres clients, collez la configuration JSON de cette page dans leurs réglages MCP.
Faut-il une clé API pour costwright — agent budget analysis ?
Oui. Il attend COSTWRIGHT_API_KEY, à renseigner dans sa configuration.
costwright — agent budget analysis est-il open source ?
Son code est public sur GitHub, mais le dépôt ne déclare pas de licence standard.
Qui maintient costwright — agent budget analysis ?
Il est publié par hernaninverso. AI.tn le référence sans le maintenir ni le recommander.
Issu du registre MCP officiel. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données.