Skip to main content
Cursor is an AI-first code editor built for pair programming with AI. Connect the Orq MCP server to access the Orq.ai workspace from Cursor’s chat interface, and route Cursor’s chat model calls through the AI Gateway.

MCP Integration

Access the Orq.ai workspace directly from Cursor. Manage experiments, query traces, and configure agents using natural language.

AI Gateway

Route Cursor’s chat model calls through the AI Gateway for unified tracing and cost tracking.

​
MCP

With the Orq MCP integration, access the Orq.ai workspace directly from Cursor’s chat interface and coding environment.

​
Prerequisites

​
Installation

​
Add MCP Server

  1. Open Cursor Settings by clicking Cursor → Settings in the top-left menu
  2. Click Tools & MCP in the sidebar
  3. Click New MCP Server to open an empty mcp.json editor
  4. Paste the following configuration:
  1. Replace YOUR_ORQ_API_KEY with your actual API key from Workspace Settings → API Keys
  2. Save the configuration
The Orq MCP server should automatically connect and show a green indicator. All Orq.ai tools will be available immediately.

​
Verification

Open Cursor’s chat panel and ask:
If the integration is working, a list of AI models from the Orq.ai workspace will appear.
Cursor IDE showing the Orq MCP server connected with a green indicator in the Tools and MCP settings panel

Successfully connected Orq MCP in Cursor

​
Available Commands

Use natural language to ask Cursor to perform these operations:
  • Create an agent with custom instructions and tools
  • Get agent configuration for [agent-key]
  • Update agent [agent-key] with new instructions or model
  • Configure agent with evaluators and guardrails
  • Invoke agent [agent-key] with input [message]
  • Retrieve agent response [response-id]
  • Create a deployment called [deployment-key]
  • Get deployment configuration for [deployment-key]
  • Create a skill called [skill-key]
  • List all skills in my workspace
  • Get skill [skill-key]
  • Update skill [skill-key]
  • Delete skill [skill-key]
  • Get analytics overview for my workspace
  • Show me workspace metrics for the last 7 days
  • Query analytics filtered by deployment ID
  • Create a dataset called "customer-queries"
  • List all datapoints in dataset [dataset-key]
  • Add datapoints to dataset [dataset-key]
  • Update datapoint [datapoint-id]
  • Delete specific datapoints in dataset [dataset-key]
  • Delete dataset [dataset-key]
  • Create an experiment from dataset [dataset-key]
  • List all experiment runs
  • Export experiment run [run-id] as CSV
  • Run experiment and auto-evaluate results
  • Get evaluator configuration for [evaluator-key]
  • Create an LLM-as-a-Judge evaluator for tone
  • Create a Python evaluator to check response length
  • Add evaluator to experiment [experiment-key]
  • Update evaluator [evaluator-key] with a new prompt
  • Update Python evaluator [evaluator-key] with revised code
  • List traces from the last 24 hours
  • Show me traces with errors
  • Get span details for trace [trace-id]
  • Find the slowest traces from today
  • Show all traces for thread [thread-id]
  • List all available chat models
  • List all available embedding models
  • Invoke model [model-id] with prompt [message]
  • Search for datasets named "customer"
  • Find experiments in project [project-id]
  • List directories in project [project-id]
  • Search the Orq.ai docs for [topic]
  • Delete agent [agent-key]
  • Delete experiment [experiment-key]
  • Delete evaluator [evaluator-key]
  • Delete prompt [prompt-key]
  • Delete knowledge base [knowledge-base-key]
Use delete_dataset to delete a dataset along with all its datapoints.
See the MCP Quickstart for the full tool reference and examples.

​
Troubleshooting

  1. Check Cursor’s Orq MCP status in Settings
  2. Verify the API key is correct
  3. Restart Cursor
  4. Check the Developer Console (Help > Toggle Developer Tools)
  1. Confirm the API key is valid
  2. Ensure the API key has the necessary permissions
  3. Try regenerating the API key
  1. Verify the Orq MCP server is running in Settings
  2. Check network connectivity
  3. Review any error messages in the Developer Console

​
Skills

Orq Skills add pre-built agentic workflows to Cursor for the full Build, Evaluate, Optimize lifecycle.

​
Installation

Set an API key and connect the Orq MCP server first. Skills are then triggered by describing what is needed.

Orq Skills

The full catalogue of skills and slash commands.
Slash commands (/orq:quickstart, /orq:traces, and others) are only available in Claude Code.

​
AI Gateway

Route Cursor’s chat model calls through the Orq.ai AI Gateway by overriding the OpenAI base URL in Cursor Settings. Requests appear in Traces automatically.
Cursor Pro is required. Since 2026, Cursor Free plans can only use Auto and block custom models, even with a custom API key or base URL override. Upgrade to Cursor Pro or higher to route through the AI Gateway.
Only the chat panel (+L / Ctrl+L) routes through the custom endpoint. Composer, inline edit, and tab completion remain on Cursor’s backend. Setting a custom base URL also disables Cursor’s default model list; add models manually using provider-prefixed IDs.

​
Prerequisites

​
Setup

1

Open Cursor Settings and navigate to Models

Open Cursor Settings (+, / Ctrl+,) and select the Models tab.
2

Enter the API key

Enable the OpenAI API Key toggle and paste the Orq.ai API key in the field. Cursor sends this key to whatever base URL is configured below. It does not have to be an OpenAI key.
3

Set the base URL

In Override OpenAI Base URL, enter:
If the field is not visible, expand the advanced options under the OpenAI API Key toggle.
4

Add a model

In the Model Names field, enter a provider-prefixed model ID (e.g. openai/gpt-5.4 or anthropic/claude-sonnet-5), then click Verify. A green checkmark confirms the model is reachable. Click Save.Repeat for each model to add.

​
Verification

Send a message in the chat panel (+L / Ctrl+L). The response appears in Cursor and the trace appears in Orq.ai Traces with the model identifier (e.g. openai/gpt-5.4).

​
Troubleshooting

Confirm the API key is a valid Orq.ai API key and that the model ID is enabled in AI Gateway → Supported Models.
The model must use the provider-prefixed format (e.g. openai/gpt-5.4, not gpt-5.6-sol) and must be enabled in AI Gateway → Supported Models.
Confirm the base URL is set to https://my.orq.ai/v3/router and the request is sent from the chat panel (+L / Ctrl+L). Inline edit and tab completion bypass the custom endpoint.
Setting a custom base URL disables the default Cursor model list. Remove the base URL override in Cursor Settings → Models to restore default behavior, or add the required models manually using provider-prefixed IDs.