Okareo MCP Server
OfficialClick on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Okareo MCP Serverrun evaluation on my latest model"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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 account at app.okareo.com
A copilot that supports MCP servers (Claude Code, Cursor, or VS Code)
Python 3.10–3.12 (only for the local install modes; not needed for remote)
Related MCP server: vsc-mcp
Remote MCP (hosted) — recommended
The fastest way to get started. No local install, no Python, no API key in .mcp.json. Browser sign-in handles auth on first connect.
Recommended (OAuth — Claude Code, Claude Desktop, Cursor, VS Code 1.101+)
Add to your copilot's MCP config (typically .mcp.json):
{
"mcpServers": {
"okareo": {
"type": "http",
"url": "https://tools.okareo.com/mcp"
}
}
}Reload the copilot. It will open a browser to Okareo sign-in once; thereafter the copilot stores the token itself. Your .mcp.json contains no secrets.
Fallback (Bearer header — older clients or headless / CI)
For clients that haven't shipped the MCP OAuth flow yet, paste your API key as a bearer header. Prefer the env-var form over an inline literal:
{
"mcpServers": {
"okareo": {
"type": "http",
"url": "https://tools.okareo.com/mcp",
"headers": {
"Authorization": "Bearer ${env:OKAREO_API_KEY}"
}
}
}
}Working across multiple Okareo organizations
If you have access to more than one Okareo account, simply Clear Authentication and then re-authenticate with the account you want to work in. You can always ask which account your are in and have acccess to.
Local install (alternative)
Run the MCP server on your own machine. Useful for offline / airgapped environments and for development.
Prefer the Remote MCP section above unless you have a specific reason to install locally (airgapped, custom build, development on this repo). The remote endpoint requires no install and stays current automatically.
For multi-org users, the remote endpoint also exposes tenant management tools (list_tenants, switch_tenant).
Step 1: Set Your API Key
export OKAREO_API_KEY="your-api-key"Add this to your ~/.zshrc or ~/.bash_profile for persistence.
Step 2: Configure Your Copilot
Claude Code
Add to .mcp.json:
{
"mcpServers": {
"okareo": {
"command": "uvx",
"args": ["okareo-mcp"],
"env": {
"OKAREO_API_KEY": "${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-mcpThen use "command": "okareo-mcp" instead of "command": "uvx" with "args": ["okareo-mcp"].
Configuration Reference
Variable | Default | Description |
| (required) | Your Okareo API key |
|
| Override for on-prem Okareo backend |
|
| Transport: |
|
| Port for SSE transport |
Available Tools
Scenarios
Tool | Description |
| Save a named scenario from rows of input/result data (idempotent) |
| List all scenarios in the project with names, IDs, and row counts |
| Retrieve a scenario's metadata and all data rows by name or ID |
| Create a new version of an existing scenario with updated data |
| Preview what will be deleted before removing a scenario |
| Permanently delete a scenario and all related test data |
Generation Models
Tool | Description |
| Browse available LLMs from the Okareo registry |
| Register a generation model for testing by selecting an LLM from the registry |
| List all registered generation models in the project |
| Read detailed information about a registered generation model |
| Change the LLM a registered generation model points to |
| Remove a registered generation model and all its related test data |
Tests & Checks
Tool | Description |
| List available quality checks (built-in and custom) for evaluating model outputs |
| Run a quality test that evaluates a model against a scenario using specified checks |
| List past test runs with optional filters (model, scenario, simulation-only) |
| Load detailed per-row results of a test run or simulation by ID or name |
| Retrieve the full conversation transcript for a single data point |
| Re-score a completed test run against a (possibly different) set of checks |
| Create or update a quality check by name — model-based, code-based, or audio (upsert) |
| Generate a check from a natural-language description, then save it |
| Retrieve a check's full configuration, including its prompt template or code |
| Permanently delete a check by name |
Simulations (Multi-Turn)
Tool | Description |
| Create or update a Target — generation model, custom endpoint, or voice (OpenAI, Deepgram, Twilio) |
| Retrieve a Target's configuration by name (all types) |
| List all simulation targets (voice and custom_endpoint) in the project |
| Remove a simulation target and all its related test data |
| Define a simulated user persona that will interact with your target |
| Retrieve a Driver's full configuration including the persona prompt |
| List all Driver personas in the project |
| Discover the voices, voice profiles, and languages available for voice drivers |
| Run a multi-turn conversation evaluation (or rerun a previous one with overrides) |
| List past simulation runs with optional filters (target, scenario, limit) |
Voice Monitoring
Tool | Description |
| Submit completed voice conversations to Okareo for monitoring |
| Connect a voice provider so its traffic flows into Okareo monitoring |
| List the voice provider integrations in your project |
| Retrieve a voice provider integration by ID, including its status |
| Update a voice provider integration's metadata |
| Rotate a voice provider integration's secrets |
| Delete a voice provider integration by ID |
| Get the inbound webhook endpoint for a voice provider |
Analytics & Dashboards
Tool | Description |
| Query Okareo's product analytics to understand evaluation trends |
| List the analytics dashboards in your project |
| Retrieve a dashboard's full configuration by name |
| Create or update an analytics dashboard by name (upsert) |
| Set the display order of dashboards |
| Delete a dashboard by name |
Tenant Management (remote MCP only)
Tool | Description |
| List every Okareo organization you have access to in this MCP session |
| Change which Okareo organization subsequent tool calls operate against |
Documentation & Templates
Tool | Description |
| Query the Okareo documentation system for conceptual or user-legible explanations |
| Retrieve prompt templates for common Okareo patterns (works offline) |
| Serve REPS agent-evaluation baseline material (scenario banks, drivers, checks, eval configs) from the latest tagged okareo-tools release |
Troubleshooting
Symptom | Cause | Fix |
| Not installed or not in PATH | Run |
Server exits with API key error |
| Export it: |
| Okareo SDK requires Python <3.13 | Use Python 3.10–3.12 |
Copilot can't connect (Docker) | Wrong URL | Ensure URL ends with |
Cursor doesn't pick up API key | Cursor launched from Dock, not terminal | Launch Cursor from terminal: |
Contributing
This repository is a curated public mirror; the canonical source is maintained by Okareo. We welcome issues and consider community pull requests — see CONTRIBUTING.md for how proposed changes are reviewed and ported.
License & Trademarks
The Okareo MCP server source code is licensed under the Apache License 2.0 (see also NOTICE).
"Okareo", the Okareo logo, and Okareo product names are trademarks of Okareo, Inc. and are not covered by the Apache 2.0 license. See TRADEMARK.md for permitted use.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Flicense-qualityDmaintenanceExposes a set of CLI tools (test generation, documentation generation, linting, test running, code search) to AI assistants via MCP, allowing them to perform these tasks through natural language.Last updated3
- Alicense-qualityDmaintenanceExposes Language Server Protocol (LSP) functionality as Model Context Protocol (MCP) tools, enabling AI clients to programmatically analyze and edit code in any language supported by VS Code.Last updated3332MIT

Patronus MCP Serverofficial
Alicense-qualityDmaintenanceEnables running LLM evaluations, experiments, and custom evaluators through a standardized MCP interface.Last updated16Apache 2.0- Flicense-qualityDmaintenanceEnables LLM-powered code analysis, generation, debugging, and context management through MCP integration with IDEs like Cursor and Claude Desktop.Last updated
Related MCP Connectors
MCP server providing access to the Scorecard API to evaluate and optimize LLM systems.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
User-owned memory for AI agents, Copilot, Claude, IDEs, CLIs, and chat apps over remote MCP.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/okareo-ai/okareo-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server