okareo-mcp 0.0.24

Okareo MCP server for AI model evaluation

Okareo MCP Server

The Okareo MCP server exposes Okareo's evaluation capabilities as MCP tools, allowing AI coding assistants to create and manage scenarios, register models, run evaluations, and execute multi-turn simulations directly from your editor.

For detailed documentation, see the Okareo MCP docs.

Prerequisites

• An Okareo API key from app.okareo.com
• A copilot that supports MCP servers (Claude Code, Cursor, or VS Code)
• Python 3.10–3.12 (for local install modes)

---

Quick Setup (Recommended)

The fastest way to get started. Run the setup command in your project directory:

uvx okareo-mcp-setup

The setup command will:

1. Prompt for your Okareo API key
2. Detect your copilot (Claude Code, Cursor)
3. Write the correct MCP server configuration into your copilot's config file

Then restart your copilot. Done.

Already have okareo-mcp installed? You can also run okareo-mcp-setup directly.

---

Mode 1: Developer Local Build (stdio)

For developers contributing to the okareo-mcp project. Code changes take effect on server restart without reinstalling.

Step 1: Clone and Install

git clone https://github.com/okareo-ai/okareo-mcp-beta.git
cd okareo-mcp-beta
pip install -e .

Step 2: Set Your API Key

export OKAREO_API_KEY="your-api-key"

Step 3: Configure Your Copilot

Claude Code

Add to .mcp.json in your project root:

{
  "mcpServers": {
    "okareo": {
      "command": "okareo-mcp",
      "env": {
        "OKAREO_API_KEY": "${OKAREO_API_KEY}"
      }
    }
  }
}

Cursor

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "okareo": {
      "command": "okareo-mcp"
    }
  }
}

Cursor inherits OKAREO_API_KEY from your shell environment.

Step 4: Verify

Restart your copilot. The Okareo MCP tools should appear. Try asking it to list your scenarios.

Note: Code changes take effect immediately on server restart — no reinstall needed.

---

Mode 2: PyPI Install (stdio)

For end users who want to use okareo-mcp without cloning the repo.

Step 1: Set Your API Key

export OKAREO_API_KEY="your-api-key"

Add this to your ~/.zshrc or ~/.bash_profile for persistence.

Step 2: Configure Your Copilot

Claude Code

Add to .mcp.json:

{
  "mcpServers": {
    "okareo": {
      "command": "uvx",
      "args": ["okareo-mcp"],
      "env": {
        "OKAREO_API_KEY": "${OKAREO_API_KEY}"
      }
    }
  }
}

No pre-install needed — uvx handles it automatically.

Cursor

Add to .cursor/mcp.json:

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

Cursor inherits OKAREO_API_KEY from your shell environment.

Alternative: pip install

If you don't have uv installed:

pip install okareo-mcp

Then use "command": "okareo-mcp" instead of "command": "uvx".

Step 3: Verify

Restart your copilot. The Okareo MCP tools should appear.

---

Mode 3: Enterprise Docker/SSE

For organizations that need centralized deployment with a shared API key.

Step 1: Set Your API Key

export OKAREO_API_KEY="your-org-api-key"

Step 2: Start the Container

docker compose up --build

The server starts on http://localhost:8000 using SSE transport.

Optional: customize the port:

PORT=9000 docker compose up --build

Step 3: Configure Developer Copilots

Distribute this configuration to developers in the organization:

Claude Code

{
  "mcpServers": {
    "okareo": {
      "url": "http://your-mcp-server:8000/sse"
    }
  }
}

Cursor

{
  "mcpServers": {
    "okareo": {
      "url": "http://your-mcp-server:8000/sse"
    }
  }
}

Step 4: Verify

curl -s http://localhost:8000/sse
# Should see an open SSE stream

---

Configuration Reference

Variable	Default	Description
OKAREO_API_KEY	(required)	Your Okareo API key
OKAREO_BASE_URL	https://api.okareo.com	Override for on-prem Okareo backend
TRANSPORT	stdio	Transport: stdio (local) or sse (Docker)
PORT	8000	Port for SSE transport

---

Available Tools

Scenarios

Tool	Description
save_scenario	Save a named scenario from rows of input/result data (idempotent)
list_scenarios	List all scenarios in the project with names, IDs, and row counts
get_scenario	Retrieve a scenario's metadata and all data rows by name or ID
create_scenario_version	Create a new version of an existing scenario with updated data
preview_delete_scenario	Preview what will be deleted before removing a scenario
delete_scenario	Permanently delete a scenario and all related test data

Generation Models

Tool	Description
list_available_llms	Browse available LLMs from the Okareo registry
register_generation_model	Register a generation model for testing by selecting an LLM from the registry
list_generation_models	List all registered generation models in the project
get_generation_model	Read detailed information about a registered generation model
update_generation_model	Change the LLM a registered generation model points to
delete_generation_model	Remove a registered generation model and all its related test data

Tests & Evaluations

Tool	Description
list_checks	List available quality checks (built-in and custom) for evaluating model outputs
run_test	Run a quality test that evaluates a model against a scenario using specified checks
list_test_runs	List past test runs with optional filters (model, scenario, simulation-only)
get_test_run_results	Load detailed per-row results of a test run or simulation by ID or name

Simulations (Multi-Turn)

Tool	Description
create_or_update_target	Create or update a Target — generation model, custom endpoint, or voice (OpenAI, Deepgram, Twilio)
get_target	Retrieve a Target's configuration by name (all types)
list_targets	List all simulation targets (voice and custom_endpoint) in the project
delete_target	Remove a simulation target and all its related test data
create_or_update_driver	Define a simulated user persona that will interact with your target
get_driver	Retrieve a Driver's full configuration including the persona prompt
list_drivers	List all Driver personas in the project
run_simulation	Run a multi-turn conversation evaluation (or rerun a previous one with overrides)
list_simulations	List past simulation runs with optional filters (target, scenario, limit)

Documentation & Templates

Tool	Description
get_docs	Query the Okareo documentation system for conceptual or user-legible explanations
get_templates	Retrieve prompt templates for common Okareo patterns (works offline)

---

Troubleshooting

Symptom	Cause	Fix
okareo-mcp: command not found	Not installed or not in PATH	Run pip install -e . (dev) or use uvx okareo-mcp (user)
Server exits with API key error	OKAREO_API_KEY not set	Export it: export OKAREO_API_KEY="..."
pip install fails on Python 3.13+	Okareo SDK requires Python <3.13	Use Python 3.10–3.12
Copilot can't connect (Docker)	Wrong URL	Ensure URL ends with /sse and port matches
Cursor doesn't pick up API key	Cursor launched from Dock, not terminal	Launch Cursor from terminal: cursor .