Roo Code
Use Roo Code as an IDE interface for your Orq.ai workspace. Query traces, run evals, inspect deployments, and debug production LLM behavior without leaving your editor, with the Orq.ai dashboard available for deeper drill‑down.
AI Gateway
Traces
Models
Field | Value |
|---|---|
Integration type | MCP server (remote Streamable HTTP / HTTP command) |
Setup time | Quick setup once Roo Code is installed/configured in your editor and an Orq API key is set. |
Auth | Orq.ai API key (workspace‑ or project‑level) passed as a bearer token via environment variables or Roo Code’s tool / MCP configuration, depending on how you register the server. |
Skills support | Roo Code can call Orq MCP tools when the Orq server is registered and enabled in its tool configuration. |
Cloud-based | Roo Code runs inside your editor, while MCP requests from the assistant call Orq’s cloud APIs for workspace data. |
Multi‑workspace | Define multiple Orq configurations (for example, different tool entries or env vars) with different API keys to point Roo Code at different Orq workspaces or environments. |
Vendor | Roo Code |
Pricing | Included with supported Orq.ai workspaces. Roo Code is open‑source; confirm availability of MCP‑style tool integrations in your Roo Code setup and Orq plan. |
Why Connect Roo Code to Orq.ai?
Setup
1: Install Roo Code
Install Roo Code in VS Code and sign in / configure your models.
Ensure the following:
Roo Code’s configuration file or settings for tools / MCP servers is accessible
You know where to define new tool / server entries
The environment where Roo Code runs can reach https://my.orq.ai over the network
2: Create an Orq.ai API key
In Orq.ai, create an API key for the workspace or project you want Roo Code to access. Keep this key handy; you’ll reference it in Roo’s MCP configuration or via an environment variable, for example: bash export ORQ_API_KEY=”<your-orq-api-key>“
Keep this key handy; you’ll reference it in Roo Code’s configuration or via an environment variable,
for example:
export ORQ_API_KEY="<your-orq-api-key>"
3: Add the Orq MCP server to Roo Code
Roo Code uses an MCP Servers panel with both global and project‑level JSON configs. Roo gives you two main ways to configure MCP: Option A – Via Roo Code’s MCP settings (UI) 1: In VS Code, open the Roo Code panel. 2: Click the MCP Servers icon in the Roo toolbar. 3: At the bottom of the MCP settings view, choose your configuration level:
A typical configuration pattern looks like:
Name: orq; Type / transport: HTTP or Streamable HTTP; URL / endpoint: https://my.orq.ai/v2/mcp; Auth: Authorization: Bearer <your-orq-api-key> (often provided via ORQ_API_KEY)
For example, if Roo Code expects a JSON config:
{ "servers": { "orq": { "url": "https://my.orq.ai/v2/mcp", "env": { "ORQ_API_KEY": "<your-orq-api-key>" } } } }
Or, if Roo Code expects explicit headers, you might define:
{ "servers": { "orq": { "url": "https://my.orq.ai/v2/mcp", "headers": { "Authorization": "Bearer ${ORQ_API_KEY}" } } } }
Restart Roo Code or reload your editor’s extension so the assistant picks up the new server.
4: A JSON editor will appear with a mcpServers object (similar to other MCP servers like Bright Data Web MCP).
5: Inside mcpServers, add an Orq entry: json { “mcpServers”: { “orq”: { “command”: “npx”, “args”: [ “orq-mcp-client” ], “env”: { “ORQ_API_KEY”: “<your-orq-api-key>“, “ORQ_MCP_URL”: “https://my.orq.ai/v2/mcp” } } } } This pattern mirrors how Roo Code starts other remote MCP servers with npx and env vars. The exact client command may differ depending on how you wrap Orq’s MCP endpoint (direct Streamable HTTP client vs a small node proxy), but the key pieces are the URL and ORQ_API_KEY. 6: Save the file. Back in the MCP settings view, ensure Enable MCP Servers is turned on and that orq appears in the list. 7: Toggle orq on to start it. Roo Code will prompt you the first time an Orq tool runs; approve the request to continue. Option B – Edit .roo/mcp.json directly You can also commit MCP configuration with your repo. At the project root, create .roo/mcp.json: json { “mcpServers”: { “orq”: { “command”: “npx”, “args”: [ “orq-mcp-client” ], “env”: { “ORQ_API_KEY”: “<your-orq-api-key>“, “ORQ_MCP_URL”: “https://my.orq.ai/v2/mcp” } } } } This project‑level config takes precedence over global settings for that workspace. After saving, open the Roo MCP settings and confirm orq is listed and enabled. 4: Start using Orq.ai tools from Cursor With Orq configured: If everything is configured correctly, Roo Code will start the orq MCP server and call Orq’s tools, showing results in your editor.
“What tools do you have access to?” or
“Use Orq to list yesterday’s failed agent runs grouped by error type.”
If configured correctly, Roo Code will call Orq’s MCP tools and show results inline in your IDE.
What Can You Do with Orq.ai + Roo Code
Roo Code Direct vs With Orq.ai MCP
Capability | Roo Code alone | Roo Code + Orq.ai MCP |
|---|---|---|
Query production LLM traces | No built‑in view into Orq.ai’s observability data. | Ask Roo Code to list, filter, and group Orq.ai traces (failures, slow runs, agent tool calls, etc.) from inside the IDE. |
Run experiments on prompts | Teams can iterate on prompts manually in chat, but no native experiment tracking in Orq.ai. | Create and run Orq.ai experiments comparing prompts, models, or configs against datasets, directly from your Roo Code sessions. |
Generate synthetic eval data | You can prompt Roo 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, then inspect them alongside your code in Roo Code |
Run evaluators on datasets | No built‑in concept of Orq evaluators or datasets. | Work with Orq evaluators and datasets from Roo Code, depending on the MCP tools enabled. |
FAQs
Do I have to use Roo Code to get value from Orq.ai?
No. Orq.ai works on its own through the UI and API. Roo Code is an optional IDE front‑end for your workspace. You get the same experiments, evals, and observability in Orq; Roo Code simply lets teams drive them from VS Code using natural language.
What can Roo Code see in my Orq.ai workspace, and how is access controlled?
Roo 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, Roo 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 Roo Code at different Orq environments (dev, staging, prod)?
Yes. You can create separate Orq entries in global mcp_settings.json and/or per‑project .roo/mcp.json, or use different API keys per project, then enable the one you need in the MCP Servers panel. That way, you can run evals and inspect traces in dev or staging first, then switch the same Roo Code setup to the production environment.
Does Roo Code connect to Orq directly from my machine?
Yes. Roo Code runs as a VS Code extension and connects to remote MCP servers over the network by starting MCP processes or HTTP clients. Your Orq MCP endpoint must be reachable over the public internet (or via your network/VPN), and Orq handles authentication and scoping via your API key.
