MCP
Skills
Natural language
Local-first
Field | Value |
|---|---|
Integration type | MCP server |
Setup time | Quick setup once Claude Code is installed and an Orq API key is configured. |
Auth | Orq.ai API key (workspace‑ or project‑level) configured via the ORQ_API_KEY environment variable |
Skills support | Claude Code can call Orq MCP tools when the server is configured. |
Local‑first | Claude Code runs locally in your terminal. MCP requests call Orq’s cloud APIs for workspace data. |
Multi‑workspace | Use different Orq API keys to point Claude Code at different Orq workspaces or environments |
Vendor | Anthropic |
Pricing | Included with supported Orq.ai workspaces. Confirm availability in your plan. |
Why Connect Claude Code to Orq.ai?
Setup
1: Install Claude Code
Follow the Claude Code install instructions for your OS so you can run claude from your terminal.
2: Create an Orq.ai API key
In Orq.ai, create an API key for the workspace or project you want Claude Code to access, then export it in your shell:
export ORQ_API_KEY="<your-orq-api-key>"
3: Add the Orq MCP server to Claude Code
Use Claude Code’s MCP command to register Orq as a remote MCP server, for example:
claude mcp add --transport http orq https://my.orq.ai/v2/mcp --header "Authorization: Bearer ${ORQ_API_KEY}"
Here, orq is the name Claude Code will use for this MCP server, https://my.orq.ai/v2/mcp is the Orq MCP endpoint, and the Authorization header passes your Orq API key from the ORQ_API_KEY environment variable.
Verify the connection with claude mcp list and confirm the Orq MCP server appears.
4: Start using Orq.ai tools from the terminal
In a project directory, start Claude Code and ask it to list available Orq tools, query traces, or run an experiment to confirm everything is wired up.
What Can You Do with Orq.ai + Claude Code
Claude Code direct vs with Orq.ai MCP
Capability | Claude Code alone | Claude Code + Orq.ai MCP |
|---|---|---|
Query production LLM traces | No built‑in view into Orq.ai’s observability data. | Ask Claude Code to list, filter, and group Orq.ai traces (failures, slow runs, agent tool calls, etc.). |
Run experiments on prompts | Can iterate on prompts manually, but no native experiment tracking in Orq.ai. | Create and run Orq.ai experiments comparing prompts, models, or configs against datasets, directly from the terminal. |
Generate synthetic eval data | You can prompt Claude Code to generate examples, then copy/paste them elsewhere. | Generate synthetic test cases and save them as reusable Orq.ai datasets for evals and experiments. |
Pull cost and usage analytics | No view into Orq router or deployment analytics. | Query Orq.ai’s cost, usage, and performance metrics for models and deployments via MCP tools. |
Run evaluators on datasets | No built‑in concept of Orq evaluators or datasets. | Work with Orq evaluators and datasets from Claude Code, depending on the MCP tools enabled. |
FAQs
Do I have to use Claude Code to get value from Orq.ai?
No. Orq.ai works on its own through the UI and API. Claude Code is an optional “terminal front‑end” for your workspace. You get the same experiments, evals, and observability in Orq; Claude Code simply lets you drive them from the CLI using natural language.
What can Claude Code see in my Orq.ai workspace, and how is access controlled?
Claude Code only sees what the Orq API key you configure is allowed to access. If you use a project‑level key scoped to a specific workspace or environment, Claude Code can only query traces, experiments, datasets, and deployments inside that scope. Rotate or revoke the key in Orq to instantly cut off access.
Can I point Claude Code at different Orq environments (dev, staging, prod)?
Yes. You can generate separate API keys for each Orq project or environment and switch which one Claude Code uses via environment variables or shell profiles. That way, you can run evals and inspect traces in dev or staging first. When ready, switch the same Claude Code setup to the production key.
