Skip to content
MCP server

OuterSpace Apizr

Read-only analysis of Python projects and experiment history for MCP clients

Runs locallyStatus and history
Install
Pricing
Open source
Platforms
CLI, self-hosted
Runs
Locally
Version
0.4.6
Listing updated
2 days ago

About OuterSpace Apizr

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

Apizr's plugin lets an assistant look at a Python project without running any of its functions. You pick one project through an apizr.toml file, a readiness policy and an exposure policy, and the server freezes those values at startup; edits only apply after a restart.

Access is granted explicitly. An operator policy file lists grants such as source.analyze, and reading recorded experiments needs a separate history.read grant with experiments.read. Tool arguments cannot point at another root, store or authority, and the project root is anchored by filesystem identity so symlinks cannot redirect a calculation.

Version 0.4.6 adds three experiment tools that read the project's .apizr/experiments/v1 store and compare runs without inferring causality. It needs matching Apizr core and plugin versions, and is released under GPL-3.0-or-later for Python 3.11 to 3.15.

Install

Run in a terminal

claude mcp add outerspace-apizr -- uvx outerspace-apizr-mcp

Add to claude_desktop_config.json

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

Add to ~/.cursor/mcp.json

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

Add to .vscode/mcp.json

{
  "servers": {
    "outerspace-apizr": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "outerspace-apizr-mcp"
      ]
    }
  }
}

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

{
  "mcpServers": {
    "outerspace-apizr": {
      "command": "uvx",
      "args": [
        "outerspace-apizr-mcp"
      ]
    }
  }
}

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

{
  "mcpServers": {
    "outerspace-apizr": {
      "command": "uvx",
      "args": [
        "outerspace-apizr-mcp"
      ]
    }
  }
}

Tools this server provides (3)

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

apizr_experiment_list
Lists recorded experiments from the project's .apizr/experiments/v1 store.
apizr_experiment_show
Shows one recorded experiment from the history store.
apizr_experiment_diff
Compares recorded experiments without inferring causality.

What it does

Read-only source analysis
Inspects a Python project and reports which functions are ready to expose, without executing them.
Exposure planning
Prepares a plan for the functions you select in the exposure policy, for REST and MCP interfaces.
Experiment history
Lists, shows and diffs recorded experiments from the project's local store.
Explicit permission grants
Analysis and history reads each need their own grant in the operator policy.
Frozen configuration
Project config and policies are fixed at startup and change only on restart.
Bounded history validation
Every history read validates the whole bounded store, so filters never hide corruption.

Good for

  • Let an assistant review which Python functions are safe to expose as an API
  • Compare recorded experiment runs from inside an MCP client
  • Plan which functions to publish before generating REST or MCP interfaces
  • Audit a codebase with an assistant that cannot execute project code

Pricing

Open source

GPL-3.0-or-later; prices not published

Prices change. Check apizr.outerspace.sh before you buy.

OuterSpace Apizr FAQ

Does it run my project's functions?

No. By default it is read-only and analyses source without executing functions.

How is experiment history access controlled?

It needs an exact history.read grant with experiments.read, in addition to source.analyze. Installing the plugin or granting analysis alone gives no history access.

Which Python versions are supported?

The README lists Python 3.11 to 3.15, with Apizr 0.4.6 and the matching plugin version.

What licence is it under?

GPL-3.0-or-later, according to the README.

Is OuterSpace Apizr free?

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

How do I add OuterSpace Apizr to Claude Code?

Run this command in your terminal: claude mcp add outerspace-apizr -- uvx outerspace-apizr-mcp

What are the best alternatives to OuterSpace Apizr?

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

Alternatives to OuterSpace Apizr

  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