Use Droid as a terminal‑first coding agent for your Orq.ai workspace. Query traces, run evals, inspect deployments, and debug production LLM behavior from the Droid CLI or its IDE integrations, with the Orq.ai dashboard available for deeper drill‑down.
Droid
Use Droid as a terminal‑first coding agent for your Orq.ai workspace. Query traces, run evals, inspect deployments, and debug production LLM behavior from the Droid CLI or its IDE integrations, with the Orq.ai dashboard available for deeper drill‑down.
MCP server (remote command / Streamable HTTP via Droid MCP client)
Setup time
Quick setup once Droid 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 Droid’s tool / MCP configuration, depending on how you register the server.
Skills support
Droid can call Orq MCP tools when the Orq server is registered and enabled in its tool configuration.
Cloud-based
Droid 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 Droid at different Orq workspaces or environments.
Vendor
Droid
Pricing
Included with supported Orq.ai workspaces. Droid is open‑source; confirm availability of MCP‑style tool integrations in your Droid setup and Orq plan.
Why Connect Droid to Orq.ai?
Keep your team in one editor
Stop switching between Droid, the Orq.ai dashboard, and separate eval scripts. Query traces, run experiments, and inspect deployments from the same full‑screen terminal agent you already use for coding, testing, and deployment.
Ask operational questions in natural language
Ask questions like “Show me yesterday’s failed agent runs grouped by error type” and let Droid 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 Droid workflows. From the Droid CLI or Droid Exec in CI, pull trace data, design and run evals, and kick off experiments as part of missions, scripts, or automation.
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. Droid brings that visibility into the same environment that’s already making and reviewing code changes.
Keep your team in one editor
Stop switching between Droid, the Orq.ai dashboard, and separate eval scripts. Query traces, run experiments, and inspect deployments from the same full‑screen terminal agent you already use for coding, testing, and deployment.
Ask operational questions in natural language
Ask questions like “Show me yesterday’s failed agent runs grouped by error type” and let Droid 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 Droid workflows. From the Droid CLI or Droid Exec in CI, pull trace data, design and run evals, and kick off experiments as part of missions, scripts, or automation.
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. Droid brings that visibility into the same environment that’s already making and reviewing code changes.
Keep your team in one editor
Stop switching between Droid, the Orq.ai dashboard, and separate eval scripts. Query traces, run experiments, and inspect deployments from the same full‑screen terminal agent you already use for coding, testing, and deployment.
Ask operational questions in natural language
Ask questions like “Show me yesterday’s failed agent runs grouped by error type” and let Droid 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 Droid workflows. From the Droid CLI or Droid Exec in CI, pull trace data, design and run evals, and kick off experiments as part of missions, scripts, or automation.
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. Droid brings that visibility into the same environment that’s already making and reviewing code changes.
Keep your team in one editor
Stop switching between Droid, the Orq.ai dashboard, and separate eval scripts. Query traces, run experiments, and inspect deployments from the same full‑screen terminal agent you already use for coding, testing, and deployment.
Ask operational questions in natural language
Ask questions like “Show me yesterday’s failed agent runs grouped by error type” and let Droid 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 Droid workflows. From the Droid CLI or Droid Exec in CI, pull trace data, design and run evals, and kick off experiments as part of missions, scripts, or automation.
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. Droid brings that visibility into the same environment that’s already making and reviewing code changes.
Setup
1: Install Droid
Install the Factory Droid CLI in your terminal. For example: curl -fsSL https://app.factory.ai/cli | sh Then navigate to your project and start Droid: cd /path/to/your/project droid On first launch, sign in via your browser when prompted to connect to the Factory platform.
Ensure the following:
Droid’s configuration file or settings for tools / MCP servers is accessible
You know where to define new tool / server entries
The environment where Droid 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 Droid to access. Export it in your shell so Droid can reference it: export ORQ_API_KEY=”<your-orq-api-key>“ You can also use different env vars (for example, ORQ_API_KEY_DEV, ORQ_API_KEY_PROD) if you want separate keys per environment.
Keep this key handy; you’ll reference it in Droid’s configuration or via an environment variable,
for example:
export ORQ_API_KEY="<your-orq-api-key>"
3: Add the Orq MCP server to Droid
Droid exposes an MCP manager both as an interactive interface and as CLI commands. Option A – Use the interactive /mcp manager Inside a running Droid session, type: text /mcp From the MCP manager you can: Browse existing servers Add a new MCP server Configure env vars and transports Add a new server named orq with the Orq MCP endpoint: Name: orq Command / transport: a Streamable HTTP client or proxy pointing at https://my.orq.ai/v2/mcp Auth: reference ORQ_API_KEY for the bearer token Save and exit. The Orq server should now appear in the /mcp server list. Option B – Use droid mcp add from the CLI You can also configure MCP servers from the command line. For example, other MCP servers (like Playwright or Obsidian) are registered like this: droid mcp add kobsidian “npx -y kobsidian-mcp” \ --env OBSIDIAN_VAULT_PATH=/absolute/path/to/vault Following the same pattern, you can add an Orq MCP client command or proxy that connects to https://my.orq.ai/v2/mcp and passes your API key via ORQ_API_KEY. The exact command depends on whether you’re using a direct HTTP client, a Streamable HTTP proxy, or a shared MCP launcher in your stack. After adding, use: droid mcp list to confirm the orq server appears and is available.
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 Droid or reload your editor’s extension so the assistant picks up the new server.
4: Start using Orq.ai tools from Droid
Once the Orq server is configured: “Use Orq to list yesterday’s failed agent runs grouped by error type.” “Use Orq to run evals on this new agent configuration.” Droid will call Orq’s MCP tools when needed and surface results in your terminal.
“What tools do you have access to?” or
“Use Orq to list yesterday’s failed agent runs grouped by error type.”
If configured correctly, Droid will call Orq’s MCP tools and show results inline in your IDE.
What Can You Do with Orq.ai + Droid
Query observability data in natural language
Use Droid 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 keep that context in the same session where you’re editing and running code.
Design and run evaluations
Describe the behavior you want to test, let Droid and Orq.ai scaffold evaluators and datasets, then run evals against your deployments without leaving the Droid CLI or Factory App.
Compare prompts, models, and configs
From Droid, create experiments that compare prompts, models, or configurations, run them on real or synthetic datasets, and inspect results in Orq.ai when you need deeper drill‑down.
Generate reusable synthetic datasets
Ask Droid to create challenging synthetic test cases for workflows such as contract analysis or support tickets, then save them as reusable Orq.ai datasets to drive future evals and experiments.
Debug production regressions as a team
When something breaks, stay in Droid. 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 Droid 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 keep that context in the same session where you’re editing and running code.
Design and run evaluations
Describe the behavior you want to test, let Droid and Orq.ai scaffold evaluators and datasets, then run evals against your deployments without leaving the Droid CLI or Factory App.
Compare prompts, models, and configs
From Droid, create experiments that compare prompts, models, or configurations, run them on real or synthetic datasets, and inspect results in Orq.ai when you need deeper drill‑down.
Generate reusable synthetic datasets
Ask Droid to create challenging synthetic test cases for workflows such as contract analysis or support tickets, then save them as reusable Orq.ai datasets to drive future evals and experiments.
Debug production regressions as a team
When something breaks, stay in Droid. 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 Droid 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 keep that context in the same session where you’re editing and running code.
Design and run evaluations
Describe the behavior you want to test, let Droid and Orq.ai scaffold evaluators and datasets, then run evals against your deployments without leaving the Droid CLI or Factory App.
Compare prompts, models, and configs
From Droid, create experiments that compare prompts, models, or configurations, run them on real or synthetic datasets, and inspect results in Orq.ai when you need deeper drill‑down.
Generate reusable synthetic datasets
Ask Droid to create challenging synthetic test cases for workflows such as contract analysis or support tickets, then save them as reusable Orq.ai datasets to drive future evals and experiments.
Debug production regressions as a team
When something breaks, stay in Droid. 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 Droid 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 keep that context in the same session where you’re editing and running code.
Design and run evaluations
Describe the behavior you want to test, let Droid and Orq.ai scaffold evaluators and datasets, then run evals against your deployments without leaving the Droid CLI or Factory App.
Compare prompts, models, and configs
From Droid, create experiments that compare prompts, models, or configurations, run them on real or synthetic datasets, and inspect results in Orq.ai when you need deeper drill‑down.
Generate reusable synthetic datasets
Ask Droid to create challenging synthetic test cases for workflows such as contract analysis or support tickets, then save them as reusable Orq.ai datasets to drive future evals and experiments.
Debug production regressions as a team
When something breaks, stay in Droid. 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.
Droid Direct vs With Orq.ai MCP
Capability
Droid alone
Droid + Orq.ai MCP
Query production LLM traces
No built‑in view into Orq.ai’s observability data.
Ask Droid to list, filter, and group Orq.ai traces (failures, slow runs, agent tool calls, etc.) from your terminal session.
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 Droid sessions and missions.
Generate synthetic eval data
You can prompt Droid 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 bring those numbers into your Droid workflows and dashboards.
Run evaluators on datasets
No built‑in concept of Orq evaluators or datasets.
Work with Orq evaluators and datasets from Droid, depending on the MCP tools enabled.
FAQs
Do I have to use Droid to get value from Orq.ai?
No. Orq.ai works on its own through the UI and API. Droid is an optional IDE front‑end for your workspace. You get the same experiments, evals, and observability in Orq; Droid simply lets teams drive them from their editor using natural language.
What can Droid see in my Orq.ai workspace, and how is access controlled?
Droid 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, Droid 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 Droid 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 Droid setup to the production environment.
Does Droid connect to Orq directly from my machine?
Yes. Droid runs from your local terminal or connected machines and connects to remote MCP servers over the network. Your Orq MCP endpoint must be reachable over the public internet (or via your VPN / private network), and Orq handles authentication and scoping via your API key.
