HefestoAI

artvepa80/agents-hefesto

A pre-commit guardian that catches drift between what your codebase declares and what it actually does. Exposes analyze, pr-review, and ask endpoints over JSON-RPC at hefestoai.narapallc.com. Designed for AI-generated code where linters miss cross-file inconsistencies: imports not in pyproject.toml, CLI scripts absent from docs, version mismatches between CHANGELOG and badges, GitHub Action inputs that aren't consumed. Runs 22 language parsers including Python AST and TreeSitter for TypeScript, Go, Rust. The pr-review mode diffs changed lines only and returns findings with SHA256 dedup keys so CI reruns don't spam duplicate comments. Reach for this when Copilot or Claude ships code faster than humans can verify packaging correctness.

tools: 4
transport: HTTP
last updated: Oct 24, 2026

View on GitHub

Install

From registry metadata

$ npx add-mcp https://hefestoai.narapallc.com/api/mcp-protocol --name hefestoai

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http hefestoai https://hefestoai.narapallc.com/api/mcp-protocol

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 4 tools

Verified live against the running server on Nov 6, 2026.

analyzeRuns the open-source hefesto-ai engine (`hefesto analyze --no-config`, free tier) on the files you send to the hosted analyzer and returns its findings: rule id, severity, file, line, message and the SARIF hefestoFingerprint/v1 fingerprint (format "sarif" adds the full SARIF 2...6 params

Runs the open-source hefesto-ai engine (`hefesto analyze --no-config`, free tier) on the files you send to the hosted analyzer and returns its findings: rule id, severity, file, line, message and the SARIF hefestoFingerprint/v1 fingerprint (format "sarif" adds the full SARIF 2...

Parameters* required

codestring

Contents of one file or snippet, used when files is omitted. At most 100 KB. This is the only argument a first call needs.

filesarray

Several files to analyze. Used instead of code when present. path: relative POSIX, at most 200 characters and 8 levels; each segment is letters, digits, "_", "." or "-" and must not start with "-";...

formatstring

Optional. json (default): findings only; sarif: also the full SARIF 2.1.0 log.one of json · sarif

languagestring

Optional language of code. Ignored when files or path is set. When omitted it is inferred from the content (python if unsure). An unknown language is rejected; send path or files instead.one of python · py · cobol · yaml · yml · dockerfile

pathstring

Optional file name for code, e.g. "app/run.py" or "Dockerfile". The extension picks the language. Same rules as files[].path. Ignored when files is set.

severitystring

Optional minimum severity to report (default LOW).one of LOW · MEDIUM · HIGH · CRITICAL

pricingReturn current HefestoAI prices (Free $0, PRO $8/month per user, OMEGA $19/month). Use it when the user asks what HefestoAI costs. Static text. Does not look up or change a subscription. No parameters: call it with {}.

Return current HefestoAI prices (Free $0, PRO $8/month per user, OMEGA $19/month). Use it when the user asks what HefestoAI costs. Static text. Does not look up or change a subscription. No parameters: call it with {}.

No parameters. Call it with no arguments.

installReturn install commands for the open-source package (pip install hefesto-ai, Python 3.11+). Use it when the user wants to run HefestoAI locally, in a pre-commit hook or on a whole repository. Does not install anything on the caller's machine. No parameters: call it with {}.

Return install commands for the open-source package (pip install hefesto-ai, Python 3.11+). Use it when the user wants to run HefestoAI locally, in a pre-commit hook or on a whole repository. Does not install anything on the caller's machine. No parameters: call it with {}.

No parameters. Call it with no arguments.

compareReturn a short static comparison of HefestoAI with one named tool. Use it when the user asks how HefestoAI differs from another scanner. No live lookup and no code is inspected. All arguments are optional: {} compares with sonarqube. Known values: sonarqube (the default when t...1 params

Return a short static comparison of HefestoAI with one named tool. Use it when the user asks how HefestoAI differs from another scanner. No live lookup and no code is inspected. All arguments are optional: {} compares with sonarqube. Known values: sonarqube (the default when t...

Parameters* required

toolstring

Optional. Tool to compare with: sonarqube (default), snyk, github-advanced-security, semgrep, claude-code-security, coderabbit, or qodo.

Readme

HefestoAI — release truth engine for AI-generated code

English | 简体中文 | 日本語

Hefesto Demo

HefestoAI runs after your AI assistant writes the code and before it ships. It checks that what your project declares (dependencies, configs, install artifacts) matches what it actually does, and it runs security and complexity checks on the code itself.

Quick start (GitHub Action)

Deterministic pass/fail check for agent-written code. It compares what your repo declares (dependencies, README, pyproject.toml, CHANGELOG, action.yml, CI) with what it actually does, and flags secrets and risky IaC. Same input, same result.

View the full README on GitHub

Details

Repository: github.com/artvepa80/agents-hefesto
Website: hefestoai.narapallc.com
Transport: HTTP
Registry: MCP registry, active
Resources: 2
Prompts: 2
Tools verified: Nov 6, 2026