Skip to main content
Warp is a modern terminal with AI capabilities and native MCP support. Route the Warp Agent’s model calls through the AI Gateway, connect the Orq MCP server, and install Orq skills for agentic workflows.

AI Gateway

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

MCP

Manage experiments, query traces, and configure agents using natural language.

Skills

Pre-built agentic workflows for the Build, Evaluate, Optimize lifecycle.

​
Prerequisites

​
AI Gateway

The AI Gateway exposes an OpenAI-compatible endpoint, so the Warp Agent can use it through Warp’s custom inference support. Every request routed this way appears in Traces.
  1. Open Warp Settings, then go to Agents → Warp Agent.
  2. Under Custom inference, click + Add custom model.
Warp Agent settings showing the Custom inference section with the Add custom model button

Custom inference settings in the Warp Agent panel

  1. In the Edit custom endpoint dialog, fill in:
  1. Under Model name, add models in provider/model_id format (for example anthropic/claude-sonnet-5 or openai/gpt-5.6-sol). Set an optional Model alias for the picker, and click + Add model for each additional model.
  2. Click Save.
Warp Edit custom endpoint dialog with the Orq endpoint name, the v3 router URL, and two models added

Adding the Orq.ai AI Gateway as a custom endpoint in Warp

Select a model from Warp’s model picker. Requests now route through the AI Gateway and appear in Traces.
Always use the provider/model_id format for model names (e.g. anthropic/claude-sonnet-5, not claude-sonnet-5). Bare IDs return a 400 invalid model format error.

​
Troubleshooting

The model name is missing the provider prefix. Change claude-sonnet-5 to anthropic/claude-sonnet-5, gpt-5.6-sol to openai/gpt-5.6-sol, and so on.
Verify the Endpoint URL is set to https://my.orq.ai/v3/router. Requests sent to a provider’s own endpoint bypass the AI Gateway and produce no Traces.

​
MCP

With the Orq MCP integration, access the Orq.ai workspace directly from Warp’s AI features.

​
Installation

  1. Open Warp Settings by clicking Warp in the top-left menu, then select Settings
  2. Click MCP Server in the sidebar
  3. Click the Add button
  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. All Orq.ai tools will be available immediately.

​
Verification

In Warp’s AI features, ask:
If the integration is working, a list of AI models from the Orq.ai workspace will appear.
Warp terminal showing the Orq MCP server connected and available in the AI features panel

Successfully connected Orq MCP in Warp

​
Available Commands

Use natural language in Warp 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 Warp’s Orq MCP status in Settings
  2. Verify the API key is correct
  3. Restart Warp
  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 Warp’s own diagnostic output or submit a bug report

​
Skills

Orq Skills add pre-built agentic workflows to Warp 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.