Skip to content
MCP server

DevReady

Read-only check that your machine meets a project's declared Node, Python and Git versions

Runs locallyStatus and history
Install
Pricing
Open source
Platforms
CLI, macOS, Windows
Runs
Locally
Version
1.3.0
Listing updated
3 days ago

About DevReady

DevReady is an open-source MCP server for developer tools. It runs locally on your machine and is started by your AI client.

DevReady answers the "works on my machine" question before an install fails. Run it in a project folder and it reads the version pins the project declares, then compares them with what is installed and prints PASS, WARN or FAIL for each item with the fix. A check that is skipped or errors is reported as not evaluated rather than as OK.

The files it reads are .nvmrc, .node-version, .python-version, .tool-versions, the engines field in package.json and requires-python in pyproject.toml. It also compares .env.example with .env by variable name only, and never reads or prints values. It installs nothing, edits nothing, makes no network requests and sends no telemetry. Output holds only parsed versions and fixed text, so a hostile package.json cannot slip instructions to an agent, according to the README.

Over MCP it exposes a single read-only tool, check_environment, started with the devready mcp command. A Claude Code plugin adds a skill and a /devready:doctor command. For CI, devready check --format json gives a versioned report and exits 1 when a requirement is unmet. It is a zero-dependency Python 3.10+ package, MIT licensed, from Evalogical.

Install

Run in a terminal

claude mcp add devready -- uvx devready-cli

Add to claude_desktop_config.json

{
  "mcpServers": {
    "devready": {
      "command": "uvx",
      "args": [
        "devready-cli"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "devready": {
      "command": "uvx",
      "args": [
        "devready-cli"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "devready": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "devready-cli"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "devready": {
      "command": "uvx",
      "args": [
        "devready-cli"
      ]
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "devready": {
      "command": "uvx",
      "args": [
        "devready-cli"
      ]
    }
  }
}

Tools this server provides (1)

Taken from the project documentation; the running server may differ.

check_environment
Read-only check that installed tool and runtime versions meet the project's declared requirements.

What it does

Project-aware checks
Compares installed Node, Python, Git and npm with the versions the project itself pins.
Read-only by design
Never installs, edits or deletes, makes no network calls and sends no telemetry.
Plain-language fixes
Reports PASS, WARN or FAIL per item, and the explain command describes any check.
Versioned JSON output
Gives a stable JSON report and exit code 1 on unmet requirements for CI.
Env name comparison
Compares .env.example with .env by variable name only, never values.
Claude Code plugin
Adds a skill, a /devready:doctor command and the MCP server in one install.

Good for

  • Check a fresh clone against its required Node and Python versions
  • Add a preflight step to CI that fails on environment mismatches
  • Have a coding agent verify the environment before builds or tests
  • Help new teammates or students see exactly what to fix

Pricing

Open source

Free and open source (MIT)

Prices change. Check devready-ten.vercel.app before you buy.

DevReady FAQ

Does DevReady change my system?

No. It is read-only and never installs, edits or deletes anything.

Which files does it read?

.nvmrc, .node-version, .python-version, .tool-versions, package.json engines, pyproject.toml requires-python, and .env.example compared with .env by variable name only.

How do I install it?

Run pipx install devready-cli, or try it once with uvx --from devready-cli devready check. It needs Python 3.10 or newer.

Can it run in CI?

Yes. devready check --format json prints a versioned report and the exit code is 1 when a requirement is unmet.

What MCP tool does it expose?

One read-only tool named check_environment.

Is DevReady free?

Yes. DevReady is open source, so you can use and self-host it for free.

How do I add DevReady to Claude Code?

Run this command in your terminal: claude mcp add devready -- uvx devready-cli

What are the best alternatives to DevReady?

The closest alternatives to DevReady are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to DevReady

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools