Open MCP Server

🤖 AI code quality gate for AI-generated code. Detects hallucinated packages, phantom dependencies, stale APIs, and more. MCP Server + CLI + CI/CD

Remote serverstreamable-httpPython

What is the Open MCP server?

Open MCP server is a hosted integration for AI assistants that speak the Model Context Protocol. 🤖 AI code quality gate for AI-generated code. Detects hallucinated packages, phantom dependencies, stale APIs, and more. MCP Server + CLI + CI/CD Action.

What you get

AI coding assistants (Copilot, Cursor, Claude) generate code with defects that traditional tools miss entirely:

Setting it up

Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.

What the assistant can call

Once Open is connected, these are the calls the assistant has available:

  • uses — actions/checkout@v4
  • Open — source maintainers** — Review AI-generated PRs for hallucinated imports, stale APIs, and security anti-patterns before merging
  • Security — conscious teams** — Run everything locally (Ollama), keep your code on your machines
  • Defect — Example
  • Language — Specific Detectors
  • Java — System.out.println leaks, deprecated Date/Calendar, hallucinated imports (Maven)
  • Kotlin — !! abuse, println leaks, null-safety anti-patterns
  • PriceFree
  • Self-hosted — ✅
  • Multi-Language — ✅ 6 langs
  • Configuration — The Configuration tool exposed by this server

Configuration and credentials

You will need 2 environment variables: YOUR_KEY, GITHUB_TOKEN. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Before you rely on it

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 11 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Open.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the open mcp server does with a few real requests.

Choosing this one

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Open's toolset — uses, Open, Security and 8 more — is a fair guide to whether it matches your workflow. It is maintained by raye-deng; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Available tools

ToolWhat it does
usesactions/checkout@v4
Opensource maintainers** — Review AI-generated PRs for hallucinated imports, stale APIs, and security anti-patterns before merging
Securityconscious teams** — Run everything locally (Ollama), keep your code on your machines
DefectExample
LanguageSpecific Detectors
JavaSystem.out.println leaks, deprecated Date/Calendar, hallucinated imports (Maven)
Kotlin!! abuse, println leaks, null-safety anti-patterns
Price**Free**
Self-hosted
Multi-Language✅ 6 langs
ConfigurationThe Configuration tool exposed by this server.

How to install the Open MCP server

{
  "mcpServers": {
    "open-code-review": {
      "command": "npx",
      "args": ["-y", "@opencodereview/cli"],
      "env": {
        "YOUR_KEY": "your-value",
        "GITHUB_TOKEN": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
YOUR_KEYCredential the server authenticates with.Yes
GITHUB_TOKENCredential the server authenticates with.Yes

Example prompts to try

  • Use Open to uses.
  • Use Open to Open.
  • Use Open to Security.

Frequently asked questions

The MCP server exposes the same detection engine as a set of tools for AI IDEs, whereas the CLI tool (`ocr`) runs scans directly in a terminal or CI pipeline. Both share the same core analysis, but the MCP server enables in‑IDE review and auto‑fix without leaving the editor.