MCP servers · abduljabbarbxr

HEIDES: deterministic code analysis MCP server for AI coding agents

An MCP server that builds a persistent local map of a codebase and returns findings and a pass/fail gate for AI agents before a patch is applied.

This text was machine-translated from the publisher's own information and has not been checked by a human editor. The publisher's original text is the reference.

This resource was imported automatically from the sources listed below and has not been reviewed by the AI Gate team yet. The description is the publisher's own, as published. Check the repository before installing.

What it does

HEIDES builds a persistent graph of a codebase in one embedded SQLite file, recording files, symbols with their doc comments, call edges and import edges. Local checks report findings with a guard, severity, file and line. These cover taint flows from user input into SQL, shell, filesystem and prompt sinks, committed credentials by value shape, unwrap and index patterns that can panic, foreign key cycles, missing primary keys, PII on read paths, and credentials in .env, Dockerfile, Terraform and manifest files.

It is intended for use before an AI agent writes a change, to check who calls a function, which imports a file actually uses, and whether a patch conflicts with the existing graph. In CI, the check command exits non-zero when it finds a blocker or critical issue, and a stricter threshold can be set. Over MCP, the harmony.check and harmony.report tools return findings together with security_gate, security_posture and a coverage receipt, so a client can see how much of the tree was inspected.

HEIDES ships as a single binary with no cloud service, model or account, and runs on a laptop, a server, in CI or on a phone under Termux. The same tree produces the same verdict offline. Dependency and CVE checks were removed from HEIDES; those are handled by GRIM, a separate public project, and the heides deps command points there.

Limitations and requirements

Dependency version and CVE checks are not performed by HEIDES; they are handled by the separate GRIM project. Taint tracking stops reporting flows past a configured hop cap. Findings cover only the files the tool reads, and the coverage receipt should be checked for how much was inspected.

Safety

Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.

  • Runs code or changes an assistant's behaviour

Sources

  • Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
    HEIDES

    Deterministic code analysis harness giving AI agents senses, memory and judgment for code.

    v0.13.1
    As shown on registry.modelcontextprotocol.io when we last read it
MCP servers
cloudflare

Cloudflare MCP servers

Cloudflare's hosted MCP servers for its products: documentation search, sandbox containers, browser rendering, Radar internet data, logs and analytics, Workers and more.

4.5K GitHub starsCloud & DevOpsSoftware development
Updated 18 Nov 2026
MCP servers
neondatabase

Neon MCP Server (Postgres)

Neon's MCP server for managing Neon Postgres in plain language: create projects and branches, run queries and prepare schema migrations from your editor.

663 GitHub starsData & databasesSoftware development
Updated 18 Nov 2026
MCP servers
microsoft

Playwright MCP (browser automation)

Microsoft's MCP server that lets an AI assistant open web pages, click, type and read them through a real browser, using the page structure instead of screenshots.

39.6K GitHub starsTesting & QAWeb, search & browser
Updated 18 Nov 2026
MCP servers
supabase-community

Supabase MCP Server

Supabase's MCP server that connects an AI assistant to your Supabase project to design tables, run queries, read configuration and look up documentation.

Data & databasesSoftware development
Updated 18 Nov 2026
HEIDES: deterministic code analysis MCP server for AI coding agents | AI Gate Discover