Skip to main content

​
Overview

Codex is an AI coding assistant that supports Model Context Protocol integrations. With Orq MCP, you can manage your AI workflows directly from Codex while writing code.

​
Prerequisites

​
Installation

​
Configure MCP Server

Add the Orq MCP server to your Codex configuration:
  1. Open or create ~/.codex/config.toml
  2. Add the Orq MCP server configuration:
[mcp_servers.orq]
url = "https://my.orq.ai/v2/mcp"
bearer_token_env_var = "ORQ_API_KEY"
  1. Set your API key as an environment variable:
export ORQ_API_KEY="your-api-key-here"
Alternatively, you can use inline headers: 
[mcp_servers.orq]
url = "https://my.orq.ai/v2/mcp"

[mcp_servers.orq.http_headers]
Authorization = "Bearer YOUR_ORQ_API_KEY"

​
Verify Installation

In Codex chat, type: 
List available models from Orq
If configured correctly, Codex will display your AI models.

​
Available Commands

Use natural language to ask Codex to perform these operations:
  • 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-id]
  • Add datapoints to dataset [dataset-id]
  • Update datapoint [datapoint-id]
  • Delete dataset [dataset-id]
  • Create an experiment from dataset [dataset-id]
  • List all experiment runs
  • Export experiment run [run-id] as CSV
  • Run experiment and auto-evaluate results
  • Create an LLM-as-a-Judge evaluator for tone
  • Create a Python evaluator to check response length
  • Add evaluator to experiment [experiment-id]
  • 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

​
Usage Examples

​
Chat Commands

Use natural language to interact with Orq: 
Create a dataset called "API Integration Tests" with 30 test cases
The assistant will:
  1. Generate 30 synthetic test case examples
  2. Use create_dataset to create a new dataset named “API Integration Tests”
  3. Use create_datapoints to add all test cases to the dataset
  4. Confirm creation with the dataset ID and summary
Show me errors from my traces in the last 24 hours
The assistant will:
  1. Calculate the time range for the last 24 hours
  2. Use list_traces with error status filter
  3. Display trace IDs, error messages, and timestamps
  4. Provide a summary of error types and frequency
Create an experiment comparing GPT-5.2 and Claude Sonnet 4.6 using the "user-feedback" dataset
The assistant will:
  1. Search for the “user-feedback” dataset using search_entities
  2. Use create_experiment with two configurations (one for GPT-5.2, one for Claude Sonnet 4.6)
  3. Run the experiment against all datapoints in the dataset
  4. Display the experiment ID and status

​
Code Context Integration

Codex can use Orq data while you’re coding: 
# Your code
def get_recommendations(user_query):
    response = orq.deployments.invoke(
        key="recommendation-engine",
        inputs={"query": user_query}
    )
    return response
Ask Codex: 
How has this recommendation engine performed over the last week? Check Orq analytics.
The assistant will:
  1. Use query_analytics with deployment key filter for “recommendation-engine”
  2. Set time range to the last 7 days
  3. Analyze metrics like request count, error rate, latency, and token usage
  4. Provide a summary report with trends and insights

​
Troubleshooting

  1. Verify the MCP endpoint URL
  2. Check your API key is valid
  3. Ensure network connectivity
  4. Review Codex logs for errors
  1. Confirm API key is valid
  2. Check API key permissions
  3. Try regenerating the API key
  4. Verify the Authorization header format
  1. Check the tool name is correct
  2. Verify required parameters are provided
  3. Review error messages in Codex
  4. Consult MCP tools list