Use TRAE 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.
TRAE
Use TRAE 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.
Quick setup once TRAE 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 TRAE’s tool / MCP configuration, depending on how you register the server.
Skills support
TRAE can call Orq MCP tools when the Orq server is registered and enabled in its tool configuration.
Cloud-based
TRAE 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 TRAE at different Orq workspaces or environments.
Vendor
TRAE
Pricing
Included with supported Orq.ai workspaces. TRAE is open‑source; confirm availability of MCP‑style tool integrations in your TRAE setup and Orq plan.
Why Connect TRAE to Orq.ai?
Keep your team in one editor
Stop switching between TRAE, the Orq.ai dashboard, and separate eval scripts. Query traces, run experiments, and inspect deployments from the same AI‑native IDE your team already uses.
Ask operational questions in natural language
Ask questions like “Show me yesterday’s failed agent runs grouped by error type” and let TRAE’s agents turn that intent into Orq MCP tool calls. No SDKs to learn and no Orq API URLs to memorize.
Connect evals to your development workflow
Use Orq.ai inside your existing TRAE workflows. From TRAE’s Builder/Agent modes, pull trace data, design and run evals, and kick off experiments as part of your normal coding sessions.
Keep production behavior visible
Orq.ai gives teams visibility into MCP‑driven activity, including which tools ran, when they ran, and which key or workspace triggered them. TRAE brings that visibility into the same environment where you write and review code.
Keep your team in one editor
Stop switching between TRAE, the Orq.ai dashboard, and separate eval scripts. Query traces, run experiments, and inspect deployments from the same AI‑native IDE your team already uses.
Ask operational questions in natural language
Ask questions like “Show me yesterday’s failed agent runs grouped by error type” and let TRAE’s agents turn that intent into Orq MCP tool calls. No SDKs to learn and no Orq API URLs to memorize.
Connect evals to your development workflow
Use Orq.ai inside your existing TRAE workflows. From TRAE’s Builder/Agent modes, pull trace data, design and run evals, and kick off experiments as part of your normal coding sessions.
Keep production behavior visible
Orq.ai gives teams visibility into MCP‑driven activity, including which tools ran, when they ran, and which key or workspace triggered them. TRAE brings that visibility into the same environment where you write and review code.
Keep your team in one editor
Stop switching between TRAE, the Orq.ai dashboard, and separate eval scripts. Query traces, run experiments, and inspect deployments from the same AI‑native IDE your team already uses.
Ask operational questions in natural language
Ask questions like “Show me yesterday’s failed agent runs grouped by error type” and let TRAE’s agents turn that intent into Orq MCP tool calls. No SDKs to learn and no Orq API URLs to memorize.
Connect evals to your development workflow
Use Orq.ai inside your existing TRAE workflows. From TRAE’s Builder/Agent modes, pull trace data, design and run evals, and kick off experiments as part of your normal coding sessions.
Keep production behavior visible
Orq.ai gives teams visibility into MCP‑driven activity, including which tools ran, when they ran, and which key or workspace triggered them. TRAE brings that visibility into the same environment where you write and review code.
Keep your team in one editor
Stop switching between TRAE, the Orq.ai dashboard, and separate eval scripts. Query traces, run experiments, and inspect deployments from the same AI‑native IDE your team already uses.
Ask operational questions in natural language
Ask questions like “Show me yesterday’s failed agent runs grouped by error type” and let TRAE’s agents turn that intent into Orq MCP tool calls. No SDKs to learn and no Orq API URLs to memorize.
Connect evals to your development workflow
Use Orq.ai inside your existing TRAE workflows. From TRAE’s Builder/Agent modes, pull trace data, design and run evals, and kick off experiments as part of your normal coding sessions.
Keep production behavior visible
Orq.ai gives teams visibility into MCP‑driven activity, including which tools ran, when they ran, and which key or workspace triggered them. TRAE brings that visibility into the same environment where you write and review code.
Setup
1: Install TRAE
Download and install TRAE from the official site, then open a project folder in the IDE. Once installed:
Ensure the following:
TRAE’s configuration file or settings for tools / MCP servers is accessible
You know where to define new tool / server entries
The environment where TRAE 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 TRAE to access. You can either: bash export ORQ_API_KEY=”<your-orq-api-key>“
Keep this key handy; you’ll reference it in TRAE’s configuration or via an environment variable,
for example:
export ORQ_API_KEY="<your-orq-api-key>"
3: Add the Orq MCP server to TRAE
TRAE supports MCP servers via: Option A - Add Orq from TRAE’s MCP marketplace If Orq appears in TRAE’s MCP marketplace: 1. In TRAE, open the AI / agent panel. 2. Click the gear icon in the upper‑right corner and choose MCP. 3. In the MCP page, click Add to open the marketplace. 4. Find the Orq MCP server in the list and click the + button. 5. Paste your Orq API key into the token / key field if prompted (similar to how TRAE configures MCP servers like GitHub or CustomGPT). 6. Confirm and save. TRAE will store the configuration and make Orq’s tools available to your agents. Option B – Add Orq as a custom MCP server (manual JSON) If Orq is not in the marketplace or you want a custom setup: 1. Open TRAE. 2. Press Ctrl + U / Command + U to open the chat box. 3. Click the gear icon in the upper‑right corner and select MCP. 4. Click Add Custom MCP to open the configuration editor. 5. Paste a JSON configuration that defines Orq as a remote MCP server, using a Streamable HTTP / SSE client or bridge pointing at Orq’s MCP endpoint. Conceptually: json { “name”: “orq”, “type”: “remote”, “transport”: “streamable-http”, “url”: “https://my.orq.ai/v2/mcp”, “env”: { “ORQ_API_KEY”: “<your-orq-api-key>“ } } This follows the pattern TRAE uses for other remote MCP servers (for example, SeekDB or CustomGPT): a name, a remote URL, and env‑based auth. 6: Click OK to save the configuration. 7: Ensure the Orq entry is enabled for the agent / workspace you’re using.
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)
Restart TRAE or reload your editor’s extension so the assistant picks up the new server.
4: Start using Orq.ai tools from TRAE
With the Orq MCP server configured: 1. Open your project in TRAE. 2. Press Ctrl + U / Command + U to open the chat panel. 3. In the agent prompt, try: If configuration is correct, TRAE will route those tool calls to Orq’s MCP server and show the results inline in your IDE.
“What tools do you have access to?” or
“Use Orq to list yesterday’s failed agent runs grouped by error type.”
If configured correctly, TRAE will call Orq’s MCP tools and show results inline in your IDE.
What Can You Do with Orq.ai + TRAE
Query observability data in natural language
Use TRAE to “talk” to your Orq.ai traces. Ask for failed agent runs, slowest requests over the last 24 hours, or errors grouped by model, then apply those insights directly in your editor.
Design and run evaluations
Describe the behavior you want to test, let TRAE and Orq.ai scaffold evaluators and datasets, then run evals against your deployments without moving into a separate tool.
Compare prompts, models, and configs
From TRAE, create experiments that compare prompts, models, or configurations, run them on real or synthetic datasets, and inspect results in Orq.ai when you need more detail.
Generate reusable synthetic datasets
Ask TRAE’s agents to create challenging synthetic test cases for workflows such as contract analysis or support tickets, and save them as reusable Orq.ai datasets.
Debug production regressions as a team
When something breaks, stay in TRAE. Pull recent traces for a deployment via Orq, filter by failure pattern, and use those examples to guide prompt or model changes backed by experiments and evals
Query observability data in natural language
Use TRAE to “talk” to your Orq.ai traces. Ask for failed agent runs, slowest requests over the last 24 hours, or errors grouped by model, then apply those insights directly in your editor.
Design and run evaluations
Describe the behavior you want to test, let TRAE and Orq.ai scaffold evaluators and datasets, then run evals against your deployments without moving into a separate tool.
Compare prompts, models, and configs
From TRAE, create experiments that compare prompts, models, or configurations, run them on real or synthetic datasets, and inspect results in Orq.ai when you need more detail.
Generate reusable synthetic datasets
Ask TRAE’s agents to create challenging synthetic test cases for workflows such as contract analysis or support tickets, and save them as reusable Orq.ai datasets.
Debug production regressions as a team
When something breaks, stay in TRAE. Pull recent traces for a deployment via Orq, filter by failure pattern, and use those examples to guide prompt or model changes backed by experiments and evals
Query observability data in natural language
Use TRAE to “talk” to your Orq.ai traces. Ask for failed agent runs, slowest requests over the last 24 hours, or errors grouped by model, then apply those insights directly in your editor.
Design and run evaluations
Describe the behavior you want to test, let TRAE and Orq.ai scaffold evaluators and datasets, then run evals against your deployments without moving into a separate tool.
Compare prompts, models, and configs
From TRAE, create experiments that compare prompts, models, or configurations, run them on real or synthetic datasets, and inspect results in Orq.ai when you need more detail.
Generate reusable synthetic datasets
Ask TRAE’s agents to create challenging synthetic test cases for workflows such as contract analysis or support tickets, and save them as reusable Orq.ai datasets.
Debug production regressions as a team
When something breaks, stay in TRAE. Pull recent traces for a deployment via Orq, filter by failure pattern, and use those examples to guide prompt or model changes backed by experiments and evals
Query observability data in natural language
Use TRAE to “talk” to your Orq.ai traces. Ask for failed agent runs, slowest requests over the last 24 hours, or errors grouped by model, then apply those insights directly in your editor.
Design and run evaluations
Describe the behavior you want to test, let TRAE and Orq.ai scaffold evaluators and datasets, then run evals against your deployments without moving into a separate tool.
Compare prompts, models, and configs
From TRAE, create experiments that compare prompts, models, or configurations, run them on real or synthetic datasets, and inspect results in Orq.ai when you need more detail.
Generate reusable synthetic datasets
Ask TRAE’s agents to create challenging synthetic test cases for workflows such as contract analysis or support tickets, and save them as reusable Orq.ai datasets.
Debug production regressions as a team
When something breaks, stay in TRAE. Pull recent traces for a deployment via Orq, filter by failure pattern, and use those examples to guide prompt or model changes backed by experiments and evals
TRAE Direct vs With Orq.ai MCP
Capability
TRAE alone
TRAE + Orq.ai MCP
Query production LLM traces
No built‑in view into Orq.ai’s observability data.
Ask TRAE 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 TRAE sessions.
Generate synthetic eval data
You can prompt TRAE 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 TRAE.
Run evaluators on datasets
No built‑in concept of Orq evaluators or datasets.
Work with Orq evaluators and datasets from TRAE depending on the MCP tools enabled.
FAQs
Do I have to use TRAE to get value from Orq.ai?
No. Orq.ai works on its own through the UI and API. TRAE is an optional IDE front‑end for your workspace. You get the same experiments, evals, and observability in Orq; TRAE simply lets teams drive them from a ByteDance‑built AI code editor using natural language.
What can TRAE see in my Orq.ai workspace, and how is access controlled?
TRAE 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, TRAE 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 TRAE at different Orq environments (dev, staging, prod)?
Yes. You can create separate Orq MCP entries in TRAE’s MCP settings (for example, “Orq (dev)”, “Orq (staging)”, “Orq (prod)”) with different API keys or URLs, then enable the one you need per project or agent. That way, you can run evals and inspect traces in dev or staging first, then switch the same TRAE setup to the production environment.
Does TRAE connect to Orq directly from my machine?
Yes. TRAE runs on your local machine and connects to remote MCP servers over the network, either via built‑in hosted connectors or a lightweight local bridge. 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.
