Use Warp as a terminal and agent interface for your Orq.ai workspace. Query traces, run evals, inspect deployments, and debug production LLM behavior without leaving your terminal, with the Orq.ai dashboard available for deeper drill‑down.
Warp
Use Warp as a terminal and agent interface for your Orq.ai workspace. Query traces, run evals, inspect deployments, and debug production LLM behavior without leaving your terminal, with the Orq.ai dashboard available for deeper drill‑down.
Quick setup once Warp 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 Warp’s tool / MCP configuration, depending on how you register the server.
Skills support
Warp can call Orq MCP tools when the Orq server is registered and enabled in its tool configuration.
Cloud-based
Warp 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 Warp at different Orq workspaces or environments.
Vendor
Warp
Pricing
Included with supported Orq.ai workspaces. Warp is open‑source; confirm availability of MCP‑style tool integrations in your Warp setup and Orq plan.
Why Connect Warp to Orq.ai?
Keep your team in one terminal
Stop switching between Warp, the Orq.ai dashboard, and separate eval scripts. Query traces, run experiments, and inspect deployments from the same terminal your team already uses for builds, logs, and ops.
Ask operational questions in natural language
Use Orq.ai inside your existing Warp workflows. From Warp’s Agent Mode, pull trace data, design and run evals, and kick off experiments as part of everyday shell work, scripts, and sessions.
Connect evals to your development workflow
Use Orq.ai inside your existing Warp workflows. From Warp’s Agent Mode, pull trace data, design and run evals, and kick off experiments as part of everyday shell work, scripts, and 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. Warp brings that visibility into the same environment where developers run services, tail logs, and investigate incidents.
Keep your team in one terminal
Stop switching between Warp, the Orq.ai dashboard, and separate eval scripts. Query traces, run experiments, and inspect deployments from the same terminal your team already uses for builds, logs, and ops.
Ask operational questions in natural language
Use Orq.ai inside your existing Warp workflows. From Warp’s Agent Mode, pull trace data, design and run evals, and kick off experiments as part of everyday shell work, scripts, and sessions.
Connect evals to your development workflow
Use Orq.ai inside your existing Warp workflows. From Warp’s Agent Mode, pull trace data, design and run evals, and kick off experiments as part of everyday shell work, scripts, and 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. Warp brings that visibility into the same environment where developers run services, tail logs, and investigate incidents.
Keep your team in one terminal
Stop switching between Warp, the Orq.ai dashboard, and separate eval scripts. Query traces, run experiments, and inspect deployments from the same terminal your team already uses for builds, logs, and ops.
Ask operational questions in natural language
Use Orq.ai inside your existing Warp workflows. From Warp’s Agent Mode, pull trace data, design and run evals, and kick off experiments as part of everyday shell work, scripts, and sessions.
Connect evals to your development workflow
Use Orq.ai inside your existing Warp workflows. From Warp’s Agent Mode, pull trace data, design and run evals, and kick off experiments as part of everyday shell work, scripts, and 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. Warp brings that visibility into the same environment where developers run services, tail logs, and investigate incidents.
Keep your team in one terminal
Stop switching between Warp, the Orq.ai dashboard, and separate eval scripts. Query traces, run experiments, and inspect deployments from the same terminal your team already uses for builds, logs, and ops.
Ask operational questions in natural language
Use Orq.ai inside your existing Warp workflows. From Warp’s Agent Mode, pull trace data, design and run evals, and kick off experiments as part of everyday shell work, scripts, and sessions.
Connect evals to your development workflow
Use Orq.ai inside your existing Warp workflows. From Warp’s Agent Mode, pull trace data, design and run evals, and kick off experiments as part of everyday shell work, scripts, and 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. Warp brings that visibility into the same environment where developers run services, tail logs, and investigate incidents.
Setup
1: Install Warp
Install Warp on your machine and sign in with your Warp account. To access MCP: Alternatively, you can go to Settings → AI → MCP Servers to manage servers from the settings view.
Ensure the following:
Warp’s configuration file or settings for tools / MCP servers is accessible
You know where to define new tool / server entries
The environment where Warp 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 Warp to access. You can either: export ORQ_API_KEY=”<your-orq-api-key>“
Keep this key handy; you’ll reference it in Warp’s configuration or via an environment variable,
for example:
export ORQ_API_KEY="<your-orq-api-key>"
3: Add the Orq MCP server to Warp
Warp supports three ways to add MCP servers: shared/team servers, curated servers, and custom JSON configs. For Orq, you’ll typically use a custom JSON config unless Orq is listed in Warp’s curated MCP list. 1. In Warp, open the MCP Servers panel from Warp Drive or Settings → AI → MCP Servers. 2. Click Add Server. 3. Choose the Custom JSON option if prompted. 4. Warp will show a JSON template. Add an Orq server entry pointing to Orq’s MCP endpoint and referencing your API key. Conceptually, it will look similar to other remote MCP servers: { “name”: “orq”, “type”: “remote”, “transport”: “http”, “url”: “https://my.orq.ai/v2/mcp”, “env”: { “ORQ_API_KEY”: “<your-orq-api-key>“ } } This mirrors how Warp configures other remote MCP servers (GitHub, Neo4j, Figma, etc.): a name, a url or command, and env for tokens. 5. Save the configuration. You should now see orq listed under MCP Servers in Warp. 6. Ensure the Orq server is enabled for your current Warp workspace.
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 Warp or reload your editor’s extension so the assistant picks up the new server.
4: Start using Orq.ai tools from Warp
With Orq configured: 1. Open Warp in your project directory. 2. Press Cmd + K (or your Agent Mode shortcut) to open Agent Mode. 3. In the agent input, ask: Warp will route these requests through the Orq MCP server and surface results in your terminal session.
“What tools do you have access to?” or
“Use Orq to list yesterday’s failed agent runs grouped by error type.”
If configured correctly, Warp will call Orq’s MCP tools and show results inline in your IDE.
What Can You Do with Orq.ai + Warp
Query observability data in natural language
Use Warp’s Agent Mode 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 act on those insights in the same terminal session.
Design and run evaluations
Describe the behavior you want to test, let Warp and Orq.ai scaffold evaluators and datasets, then run evals against your deployments without leaving the terminal.
Compare prompts, models, and configs
From Warp, create experiments that compare prompts, models, or configurations, run them on real or synthetic datasets, and inspect the results in Orq.ai when you need more detail.
Generate reusable synthetic datasets
Ask Warp’s agent 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 Warp. 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 Warp’s Agent Mode 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 act on those insights in the same terminal session.
Design and run evaluations
Describe the behavior you want to test, let Warp and Orq.ai scaffold evaluators and datasets, then run evals against your deployments without leaving the terminal.
Compare prompts, models, and configs
From Warp, create experiments that compare prompts, models, or configurations, run them on real or synthetic datasets, and inspect the results in Orq.ai when you need more detail.
Generate reusable synthetic datasets
Ask Warp’s agent 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 Warp. 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 Warp’s Agent Mode 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 act on those insights in the same terminal session.
Design and run evaluations
Describe the behavior you want to test, let Warp and Orq.ai scaffold evaluators and datasets, then run evals against your deployments without leaving the terminal.
Compare prompts, models, and configs
From Warp, create experiments that compare prompts, models, or configurations, run them on real or synthetic datasets, and inspect the results in Orq.ai when you need more detail.
Generate reusable synthetic datasets
Ask Warp’s agent 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 Warp. 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 Warp’s Agent Mode 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 act on those insights in the same terminal session.
Design and run evaluations
Describe the behavior you want to test, let Warp and Orq.ai scaffold evaluators and datasets, then run evals against your deployments without leaving the terminal.
Compare prompts, models, and configs
From Warp, create experiments that compare prompts, models, or configurations, run them on real or synthetic datasets, and inspect the results in Orq.ai when you need more detail.
Generate reusable synthetic datasets
Ask Warp’s agent 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 Warp. 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.
Warp Direct vs With Orq.ai MCP
Capability
Warp alone
Warp + Orq.ai MCP
Query production LLM traces
No built‑in view into Orq.ai’s observability data.
Ask Warp’s Agent Mode to list, filter, and group Orq.ai traces (failures, slow runs, agent tool calls, etc.) from inside the terminal.
Run experiments on prompts
You can iterate on prompts manually in Warp’s agent, but no native experiment tracking in Orq.ai.
Create and run Orq.ai experiments comparing prompts, models, or configs against datasets, directly from your Warp sessions.
Generate synthetic eval data
You can prompt Warp’s agent 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 logs and commands in Warp.
Run evaluators on datasets
No built‑in concept of Orq evaluators or datasets.
Work with Orq evaluators and datasets from Warp, depending on the MCP tools enabled.
FAQs
Do I have to use Warp to get value from Orq.ai?
No. Orq.ai works on its own through the UI and API. Warp is an optional IDE front‑end for your workspace. You get the same experiments, evals, and observability in Orq; Warp simply lets teams drive them from their editor using natural language.
What can Warp see in my Orq.ai workspace, and how is access controlled?
Warp 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, Warp 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 Warp at different Orq environments (dev, staging, prod)?
Yes. You can create separate Orq configurations (different server names or env vars) per environment, then select or enable the one you need per project. That way, you can run evals and inspect traces in dev or staging first, then switch the same Warp setup to the production environment.
Does Warp connect to Orq directly from my machine?
Yes. Warp runs as a desktop terminal and connects to remote MCP servers over the network using its built‑in MCP client. 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.
