Claude Cowork

Use Claude Cowork as a shared chat interface for your Orq.ai workspace. Query traces, run evals, inspect deployments, and debug production LLM behavior from a collaborative space your team already uses, with the Orq.ai dashboard available for deeper drill‑down.

Claude Cowork

Use Claude Cowork as a shared chat interface for your Orq.ai workspace. Query traces, run evals, inspect deployments, and debug production LLM behavior from a collaborative space your team already uses, with the Orq.ai dashboard available for deeper drill‑down.

MCP

Skills

Natural language

Local-first

Get your API key

View setup docs

Field

Value

Integration type

MCP server (remote custom connector)

Setup time

Quick setup once Claude Cowork is available in your Anthropic account and an Orq API key is configured.

Auth

Orq.ai API key (workspace‑ or project‑level) added as an Authorization header when registering the Orq MCP URL in Claude Desktop’s Connectors settings.

Skills support

Claude Cowork can call Orq MCP tools when the Orq connector is enabled in a shared conversation or workspace.

Cloud-based

Claude Cowork runs in Anthropic’s cloud. MCP requests from Cowork sessions are brokered through Anthropic’s infrastructure and call Orq’s APIs for workspace data.

Multi‑workspace

Create separate Orq connectors with different API keys to point Claude Cowork at different Orq workspaces or environments, then enable the one you need per channel or project space.

Vendor

Anthropic

Pricing

Included with supported Orq.ai workspaces. Custom connectors are available on Claude Cowork for eligible Anthropic plans; confirm availability in both your Claude and Orq plans.

Why Connect Claude Cowork to Orq.ai?

Keep your team in one shared workspace

Stop switching between Claude Cowork, the Orq.ai dashboard, and separate eval scripts. Query traces, run experiments, and inspect deployments from the same collaborative chat 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 Claude Cowork turn that intent into Orq MCP tool calls. No SDKs to learn and no API URLs to memorize.

Connect evals to your development workflow

Use Orq.ai inside your existing team workflows. From Claude Cowork, pull trace data, design and run evals, and kick off experiments as part of shared channels, incident rooms, or project spaces.

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. Cowork makes that visibility available right where teams discuss, debug, and decide what to ship.

Keep your team in one shared workspace

Stop switching between Claude Cowork, the Orq.ai dashboard, and separate eval scripts. Query traces, run experiments, and inspect deployments from the same collaborative chat 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 Claude Cowork turn that intent into Orq MCP tool calls. No SDKs to learn and no API URLs to memorize.

Connect evals to your development workflow

Use Orq.ai inside your existing team workflows. From Claude Cowork, pull trace data, design and run evals, and kick off experiments as part of shared channels, incident rooms, or project spaces.

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. Cowork makes that visibility available right where teams discuss, debug, and decide what to ship.

Keep your team in one shared workspace

Stop switching between Claude Cowork, the Orq.ai dashboard, and separate eval scripts. Query traces, run experiments, and inspect deployments from the same collaborative chat 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 Claude Cowork turn that intent into Orq MCP tool calls. No SDKs to learn and no API URLs to memorize.

Connect evals to your development workflow

Use Orq.ai inside your existing team workflows. From Claude Cowork, pull trace data, design and run evals, and kick off experiments as part of shared channels, incident rooms, or project spaces.

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. Cowork makes that visibility available right where teams discuss, debug, and decide what to ship.

Keep your team in one shared workspace

Stop switching between Claude Cowork, the Orq.ai dashboard, and separate eval scripts. Query traces, run experiments, and inspect deployments from the same collaborative chat 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 Claude Cowork turn that intent into Orq MCP tool calls. No SDKs to learn and no API URLs to memorize.

Connect evals to your development workflow

Use Orq.ai inside your existing team workflows. From Claude Cowork, pull trace data, design and run evals, and kick off experiments as part of shared channels, incident rooms, or project spaces.

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. Cowork makes that visibility available right where teams discuss, debug, and decide what to ship.

Setup

1: Install Claude Desktop

Install Claude Desktop for your OS from claude.ai and sign in so you can start new chats from your desktop.

2: Create an Orq.ai API key

In Orq.ai, create an API key for the workspace or project you want Claude Desktop to access. 

Keep this key handy as you’ll paste it when you add the connector.

3: Add the Orq MCP server to Claude Desktop

In Claude Desktop, add Orq as a custom connector backed by a remote MCP server:

  1. Open Settings → Connectors (or Customize → Connectors in the app sidebar)

  2. Click “Add custom connector”

  3. Set the connector URL to: https://my.orq.ai/v2/mcp

  4. In the advanced or headers section, add: Authorization: Bearer <your-orq-api-key>

  5. Save the connector and, if needed, give it a name like “Orq (prod)” or “Orq (staging)”

On Team and Enterprise plans, org owners can add the connector in organization settings and members can then connect to it from their own Connectors panel.

4: Enable Orq in a conversation

In a Claude Desktop chat, use the connectors menu (the “+” / tools menu) to enable the Orq connector for that conversation. Claude Desktop will discover the Orq MCP tools and make them available in the chat.

5: Start using Orq.ai tools from Claude Desktop

Ask Claude to list available Orq tools, query traces, or run an experiment to confirm everything is wired up.

What Can You Do with Orq.ai + Claude Desktop

Query observability data in natural language

Use Claude Desktop to “talk” to your Orq.ai traces. Ask for failed agent runs, slowest requests over the last 24 hours, or errors grouped by model.

Design and run evaluations

Describe the behavior you want to test, let Claude Desktop scaffold evaluators and datasets, then run evals against your deployments without moving into a separate tool.

Compare prompts, models, and configs

From Claude Desktop, 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 Claude Desktop to create challenging synthetic test cases for a workflow, such as contract analysis or support tickets, and prepare them for use as reusable Orq.ai datasets. Then reuse them across evals and experiments.

Debug production regressions

When something breaks, stay in Claude Desktop. Pull recent traces for a deployment, 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 Claude Desktop to “talk” to your Orq.ai traces. Ask for failed agent runs, slowest requests over the last 24 hours, or errors grouped by model.

Design and run evaluations

Describe the behavior you want to test, let Claude Desktop scaffold evaluators and datasets, then run evals against your deployments without moving into a separate tool.

Compare prompts, models, and configs

From Claude Desktop, 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 Claude Desktop to create challenging synthetic test cases for a workflow, such as contract analysis or support tickets, and prepare them for use as reusable Orq.ai datasets. Then reuse them across evals and experiments.

Debug production regressions

When something breaks, stay in Claude Desktop. Pull recent traces for a deployment, 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 Claude Desktop to “talk” to your Orq.ai traces. Ask for failed agent runs, slowest requests over the last 24 hours, or errors grouped by model.

Design and run evaluations

Describe the behavior you want to test, let Claude Desktop scaffold evaluators and datasets, then run evals against your deployments without moving into a separate tool.

Compare prompts, models, and configs

From Claude Desktop, 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 Claude Desktop to create challenging synthetic test cases for a workflow, such as contract analysis or support tickets, and prepare them for use as reusable Orq.ai datasets. Then reuse them across evals and experiments.

Debug production regressions

When something breaks, stay in Claude Desktop. Pull recent traces for a deployment, 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 Claude Desktop to “talk” to your Orq.ai traces. Ask for failed agent runs, slowest requests over the last 24 hours, or errors grouped by model.

Design and run evaluations

Describe the behavior you want to test, let Claude Desktop scaffold evaluators and datasets, then run evals against your deployments without moving into a separate tool.

Compare prompts, models, and configs

From Claude Desktop, 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 Claude Desktop to create challenging synthetic test cases for a workflow, such as contract analysis or support tickets, and prepare them for use as reusable Orq.ai datasets. Then reuse them across evals and experiments.

Debug production regressions

When something breaks, stay in Claude Desktop. Pull recent traces for a deployment, filter by failure pattern, and use those examples to guide prompt or model changes backed by experiments and evals.

Claude Code direct vs with Orq.ai MCP

Capability

Claude Desktop alone

Claude Desktop + Orq.ai MCP

Query production LLM traces

No built‑in view into Orq.ai’s observability data.

Ask Claude Desktop to list, filter, and group Orq.ai traces (failures, slow runs, agent tool calls, etc.).

Run experiments on prompts

Can iterate on prompts manually, but no native experiment tracking in Orq.ai.

Create and run Orq.ai experiments comparing prompts, models, or configs against datasets, directly from the desktop app.

Generate synthetic eval data

You can prompt Claude Desktop 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. 

Run evaluators on datasets

No built‑in concept of Orq evaluators or datasets.

Work with Orq evaluators and datasets from Claude Desktop, depending on the MCP tools enabled.


FAQs

Do I have to use Claude Desktop to get value from Orq.ai?

No. Orq.ai works on its own through the UI and API. Claude Desktop is an optional “chat front‑end” for your workspace. You get the same experiments, evals, and observability in Orq; Claude Desktop simply lets you drive them from a GUI using natural language.

What can Claude Desktop see in my Orq.ai workspace, and how is access controlled?

Claude Desktop 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, Claude Desktop 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 Claude Desktop at different Orq environments (dev, staging, prod)?

Yes. You can create separate Orq connectors for each project or environment using different API keys, then enable the one you need per conversation. That way, you can run evals and inspect traces in dev or staging first, then switch the same Claude Desktop setup to the production connector.

Does Claude Desktop connect to Orq directly from my machine?

No. Custom connectors in Claude Desktop use Anthropic’s cloud to reach remote MCP servers. Your Orq MCP endpoint must be reachable over the public internet, and Orq handles authentication and scoping via your API key.

Create an account and start building today.

Book a demo

Explore docs

Create an account and start building today.

Book a demo

Explore docs

Create an account and start building today.

Book a demo

Explore docs

Create an account and start building today.

Book a demo

Explore docs