Use Zed 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.
Zed
Use Zed 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.
MCP context server (remote HTTP / Streamable HTTP via bridge)
Setup time
Quick setup once Zed 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 Zed’s tool / MCP configuration, depending on how you register the server.
Skills support
Zed can call Orq MCP tools when the Orq server is registered and enabled in its tool configuration.
Cloud-based
Zed 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 Zed at different Orq workspaces or environments.
Vendor
Zed
Pricing
Included with supported Orq.ai workspaces. Zed is open‑source; confirm availability of MCP‑style tool integrations in your Zed setup and Orq plan.
Why Connect Zed to Orq.ai?
Keep your team in one editor
Stop switching between Zed, the Orq.ai dashboard, and separate eval scripts. Query traces, run experiments, and inspect deployments from the same AI‑native editor 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 Zed’s assistant route that intent to Orq via an MCP context server. No SDKs to learn and no Orq API URLs to memorize.
Connect evals to your development workflow
Use Orq.ai inside your existing Zed workflows. From the assistant panel, pull trace data, design and run evals, and kick off experiments as part of normal coding sessions and multi‑player editing.
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. Zed brings that visibility into the same environment where you write, review, and debug code.
Keep your team in one editor
Stop switching between Zed, the Orq.ai dashboard, and separate eval scripts. Query traces, run experiments, and inspect deployments from the same AI‑native editor 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 Zed’s assistant route that intent to Orq via an MCP context server. No SDKs to learn and no Orq API URLs to memorize.
Connect evals to your development workflow
Use Orq.ai inside your existing Zed workflows. From the assistant panel, pull trace data, design and run evals, and kick off experiments as part of normal coding sessions and multi‑player editing.
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. Zed brings that visibility into the same environment where you write, review, and debug code.
Keep your team in one editor
Stop switching between Zed, the Orq.ai dashboard, and separate eval scripts. Query traces, run experiments, and inspect deployments from the same AI‑native editor 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 Zed’s assistant route that intent to Orq via an MCP context server. No SDKs to learn and no Orq API URLs to memorize.
Connect evals to your development workflow
Use Orq.ai inside your existing Zed workflows. From the assistant panel, pull trace data, design and run evals, and kick off experiments as part of normal coding sessions and multi‑player editing.
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. Zed brings that visibility into the same environment where you write, review, and debug code.
Keep your team in one editor
Stop switching between Zed, the Orq.ai dashboard, and separate eval scripts. Query traces, run experiments, and inspect deployments from the same AI‑native editor 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 Zed’s assistant route that intent to Orq via an MCP context server. No SDKs to learn and no Orq API URLs to memorize.
Connect evals to your development workflow
Use Orq.ai inside your existing Zed workflows. From the assistant panel, pull trace data, design and run evals, and kick off experiments as part of normal coding sessions and multi‑player editing.
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. Zed brings that visibility into the same environment where you write, review, and debug code.
Setup
1: Install Zed
Install Zed on your OS and open it with a project folder.
Ensure the following:
Zed’s configuration file or settings for tools / MCP servers is accessible
You know where to define new tool / server entries
The environment where Zed 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 Zed to access. You can either: bash export ORQ_API_KEY=”<your-orq-api-key>“
Keep this key handy; you’ll reference it in Zed’s configuration or via an environment variable,
for example:
export ORQ_API_KEY="<your-orq-api-key>"
3: Add the Orq MCP server to Zed
Zed connects to MCP servers via context servers configured in its settings.json file. Depending on your version, the key is usually context_servers (older builds sometimes used experimental.context_servers). 1. Open Zed’s settings file: This opens settings.json for your user profile. 2. Locate or add a context_servers object. 3. Add an Orq entry. There are two common patterns: Example: Using supergateway (SSE bridge to Orq MCP) If Orq is exposed as a remote HTTP/SSE MCP server (for example https://my.orq.ai/v2/mcp), Zed typically reaches it via a small bridge such as mcp-remote or supergateway, as described in other Zed + MCP integrations. Example using mcp-remote: json { “context_servers”: { “orq”: { “command”: { “path”: “mcp-remote”, “args”: [ “https://my.orq.ai/v2/mcp” ], “env”: { “ORQ_API_KEY”: “<your-orq-api-key>“ } }, “settings”: {} } } } Example using supergateway with SSE: json { “context_servers”: { “orq”: { “command”: { “path”: “supergateway”, “args”: [ “--sse”, “https://my.orq.ai/v2/mcp” ], “env”: { “ORQ_API_KEY”: “<your-orq-api-key>“ } }, “settings”: {} } } } This mirrors how Zed connects to other HTTP MCP servers like Pieces or ToolPiper via a bridge. 4. Save settings.json. Zed will reload context servers automatically when the file changes. 5. If needed, restart Zed to ensure the assistant sees the new context server.
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 Zed or reload your editor’s extension so the assistant picks up the new server.
4: Start using Orq.ai tools from Zed
With the Orq context server configured: 1. Open your project in Zed. 2. Open the assistant panel. 3. Type / to see available slash commands, or ask: If everything is configured correctly, Zed’s assistant will call tools from the orq context server and surface Orq results inline.
“What tools do you have access to?” or
“Use Orq to list yesterday’s failed agent runs grouped by error type.”
If configured correctly, Zed will call Orq’s MCP tools and show results inline in your IDE.
What Can You Do with Orq.ai + Zed
Query observability data in natural language
Use Zed’s assistant 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 Zed and Orq.ai scaffold evaluators and datasets, then run evals against your deployments without leaving Zed.
Compare prompts, models, and configs
From Zed, 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 Zed’s assistant 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 Zed. 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 Zed’s assistant 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 Zed and Orq.ai scaffold evaluators and datasets, then run evals against your deployments without leaving Zed.
Compare prompts, models, and configs
From Zed, 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 Zed’s assistant 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 Zed. 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 Zed’s assistant 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 Zed and Orq.ai scaffold evaluators and datasets, then run evals against your deployments without leaving Zed.
Compare prompts, models, and configs
From Zed, 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 Zed’s assistant 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 Zed. 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 Zed’s assistant 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 Zed and Orq.ai scaffold evaluators and datasets, then run evals against your deployments without leaving Zed.
Compare prompts, models, and configs
From Zed, 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 Zed’s assistant 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 Zed. 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.
Zed Direct vs With Orq.ai MCP
Capability
Zed alone
Zed + Orq.ai MCP
Query production LLM traces
No built‑in view into Orq.ai’s observability data.
Ask Zed’s assistant (via the orq context server) to list, filter, and group Orq.ai traces (failures, slow runs, agent tool calls, etc.) from inside the editor.
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 Zed sessions.
Generate synthetic eval data
You can prompt Zed’s assistant 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 Zed.
Run evaluators on datasets
No built‑in concept of Orq evaluators or datasets.
Work with Orq evaluators and datasets from Zed, depending on the MCP tools enabled.
FAQs
Do I have to use Zed to get value from Orq.ai?
No. Orq.ai works on its own through the UI and API. Zed is an optional IDE front‑end for your workspace. You get the same experiments, evals, and observability in Orq; Zed simply lets teams drive them from a Rust‑native, AI‑accelerated editor using natural language.
What can Zed see in my Orq.ai workspace, and how is access controlled?
Zed only sees what the Orq API key you configure is allowed to access. If you use a key scoped to a specific workspace or environment, Zed 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 Zed at different Orq environments (dev, staging, prod)?
Yes. You can create separate context servers in settings.json (for example orq-dev, orq-staging, orq-prod) with different URLs or API keys, then use the appropriate one per profile or project. That way, you can run evals and inspect traces in dev or staging first, then switch the same Zed setup to the production environment.
Does Zed connect to Orq directly from my machine?
Yes. Zed runs on your local machine and connects to MCP servers via context servers defined in settings.json. For remote HTTP/SSE servers like Orq’s, it typically calls a small bridge command (mcp-remote or supergateway) that talks to Orq over the network. 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.
