> ## Documentation Index
> Fetch the complete documentation index at: /docs/llms.txt
> Use this file to discover all available pages before exploring further.

# MCP Server

> Connect AI assistants to BugRadar for docs and test management

Connect your AI coding assistant to BugRadar for seamless documentation access and test flow management directly from your IDE.

## Configuration

Connect BugRadar with your existing account using browser sign-in. Devin currently uses the API-key setup described below.

> [tab] Claude Code
>
> If you added BugRadar from the [Claude connector directory](https://claude.ai/directory/BugRadar) and sign in to Claude Code with your Claude account, it already appears in `/mcp`.
>
> Otherwise, run in your project directory:
>
> ```bash theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
> claude mcp add --transport http BugRadar https://mcp.usebugradar.com/mcp
> ```
>
> Open Claude Code, run `/mcp`, select BugRadar, and follow the browser sign-in prompt.

> [tab] Claude Desktop
>
> Open [BugRadar in the Claude connector directory](https://claude.ai/directory/BugRadar), choose **Connect**, and sign in through your browser.
>
> Or add it manually: in Claude, open **Customize → Connectors → Add custom connector**. Enter **BugRadar** as the name and this server URL:
>
> ```text theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
> https://mcp.usebugradar.com/mcp
> ```
>
> Choose **Connect** and sign in through your browser. Your Claude account must support custom connectors; if the option is disabled, ask your workspace administrator or use another supported client.

> [tab] Cursor
>
> Add BugRadar to `~/.cursor/mcp.json`, preserving any existing servers:
>
> ```json theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
> {
>   "mcpServers": {
>     "BugRadar": {
>       "url": "https://mcp.usebugradar.com/mcp"
>     }
>   }
> }
> ```
>
> Open Cursor's MCP settings and click **Authenticate** beside BugRadar.

> [tab] Gemini CLI
>
> Run:
>
> ```bash theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
> gemini mcp add --transport http BugRadar https://mcp.usebugradar.com/mcp
> ```
>
> In Gemini CLI, run `/mcp auth BugRadar` and follow the browser sign-in prompt.

> [tab] Codex
>
> Run:
>
> ```bash theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
> codex mcp add BugRadar --url https://mcp.usebugradar.com/mcp
> codex mcp login BugRadar
> ```
>
> If you configure Codex manually, add the following to `~/.codex/config.toml`, then run `codex mcp login BugRadar`:
>
> ```toml theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
> [mcp_servers.BugRadar]
> url = "https://mcp.usebugradar.com/mcp"
> ```

> [tab] Dots
>
> A dot uses plugins installed in ChatGPT. In ChatGPT on the web, open **Settings → Security and login** and turn on **Developer mode** (Plus, Pro, Business, Enterprise, or Edu). Then open **ChatGPT Plugins**, select **+**, and create an app named **BugRadar** with this server URL:
>
> ```text theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
> https://mcp.usebugradar.com/mcp
> ```
>
> Choose **OAuth** and approve access in your browser. Do not use an API key. In a chat, open **+**, choose **Developer mode**, and select **BugRadar**. This connects the app in ChatGPT. It does not add a separate control inside the dot.
>
> Full walkthrough: [Dots](/docs/dots.md).

> [tab] Grok Bot
>
> Grok Bot has no Settings form for a custom MCP URL, and BugRadar is not in the marketplace. Send this in a Grok Bot chat:
>
> ```
> Add a custom MCP called BugRadar at https://mcp.usebugradar.com/mcp
> ```
>
> Approve the confirm card. When Grok Bot shows a sign-in link, open it and approve access. No API key is needed. Next message: `@` BugRadar and ask it to list or run a flow. Adding MCP in Cursor does not set up Grok Bot.
>
> Full walkthrough: [Grok Bot](/docs/grok-bot.md).

> [tab] Devin
>
> In Devin, open **Customize → MCPs → Add a custom MCP**. Choose **HTTP**, not STDIO. Open **[Settings → Integrations → Devin](https://usebugradar.com/settings?tab=integrations\&integration=devin)** to create a key, then fill in:
>
> ```
> Server name: BugRadar
> Transport: HTTP
> Server URL: https://mcp.usebugradar.com/mcp
> Authentication: Auth Header
> Header key: x-api-key
> Header value: <YOUR_API_KEY>
> ```
>
> Save, then use **Test listing tools**. Adding MCP in Cursor does not set up Devin.
>
> Full walkthrough: [Devin](/docs/devin.md).

> [tab] Hermes Agent
>
> Add this under `mcp_servers` in `~/.hermes/config.yaml` (keep any other servers). Hermes opens a browser the first time it connects:
>
> ```yaml theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
> mcp_servers:
>   BugRadar:
>     url: "https://mcp.usebugradar.com/mcp"
>     auth: oauth
> ```
>
> Or run `hermes mcp add --url https://mcp.usebugradar.com/mcp --auth oauth BugRadar`. Do not use `--auth header` — that writes `Authorization: Bearer`. Adding MCP in Cursor does not set up Hermes Agent.
>
> Full walkthrough: [Hermes Agent](/docs/hermes-agent.md).

> [tab] OpenClaw
>
> Run:
>
> ```bash theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
> openclaw mcp set BugRadar '{"url":"https://mcp.usebugradar.com/mcp","transport":"streamable-http","auth":"oauth"}'
> openclaw mcp login BugRadar
> ```
>
> Follow the browser sign-in prompt.

In the browser, sign in to BugRadar, check the agent name and company, and click **Connect**. The agent can work in any workspace you can access in that company. Return to your agent and ask it to list your BugRadar flows.

If the authorization session ends before you approve, start a fresh connection from your agent. Do not reuse the old browser tab.

Existing API-key connections continue to work. To switch one to browser sign-in, remove its `x-api-key` header and reconnect. Keep the key until the new connection works; revoke it only if no other integrations use it.

You may need to restart your agent for the changes to take effect.

***

## Verify the Connection

Once configured, test the server:

```
List all my BugRadar flows
```

```
How do suites work in BugRadar?
```

If the connection is successful, you'll receive responses from both questions.

***

## Available Tools

The BugRadar MCP server provides comprehensive test management, debugging, and documentation access.

### Flow Management

| Tool | Description |
| - | - |
| `flows_list` | List all flows in your organization, optionally filtered by suite |
| `flows_read` | Get details of a specific flow by ID |
| `flows_create` | Create a new test flow with name, instructions, and optional suite |
| `flows_update` | Update an existing flow's name or instructions |
| `flows_delete` | Delete one or more flows (supports batch deletion) |
| `flows_run` | Execute flows, with optional browser and extension loadout overrides |

### Suite Management

| Tool | Description |
| - | - |
| `suites_list` | List all test suites in your organization |
| `suites_read` | Get details of a specific suite by ID |
| `suites_create` | Create a new suite with flows and optional authentication |
| `suites_update` | Update a suite's name, description, or authentication setup |
| `suites_delete` | Delete one or more suites (supports batch deletion) |
| `suites_run` | Execute a suite with optional browser and extension loadout overrides |
| `suites_list_auth_flows` | List the reusable sign-in setup flows attached to your suites |

### Folder Management

| Tool | Description |
| - | - |
| `folders_list` | List your folders with each one's path and ID |
| `folders_run` | Run everything in one or more folders and their subfolders (cloud runs only) |

### Hook Management

| Tool | Description |
| - | - |
| `hooks_list` | List all hooks in your organization, optionally filtered by flow |
| `hooks_read` | Get details of a specific hook by ID |
| `hooks_create` | Create a new hook with a script (cURL, Python, JS, Shell) |
| `hooks_update` | Update an existing hook's name, script, type, or description |
| `hooks_delete` | Delete one or more hooks (supports batch deletion) |
| `hooks_run` | Execute a hook and wait for results |

To attach a [built-in hook](/docs/guides-otp-testing.md) such as **Lease email address**, pass `{"type": "builtin", "builtin_key": "lease_email_inbox", "hook_type": "setup"}` in the `hooks` list of `flows_create`, `flows_update`, `suites_create`, or `suites_update`. It's added to your organization automatically if it isn't there yet.

### Apps & Environments

| Tool | Description |
| - | - |
| `apps_list` | List active apps, optionally filtered by platform |
| `apps_read` | Get app details, recent builds, and attached dependencies |
| `apps_register` | Register an iOS, Android, web, or Chrome extension app |
| `builds_upload` | Upload a build from your computer ([details](/docs/upload-build.md)) |
| `devices_list` | List supported cloud device and OS permutations |
| `environments_list` | List all environments for your organization |

Filter `apps_list` with `platform: "chrome-extension"` to discover extension
apps and their UUIDs.

Use `devices_list` to choose a model and OS. Set `model` or `os_version` to
`"latest"` for explicit rolling resolution, or omit `device` to use the newest
supported default for both.

Both `flows_run` and `suites_run` accept `dependencies` as a JSON array string
for web runs:

```json theme={null}
["extension-app-uuid", {
  "app_id": "another-extension-app-uuid",
  "app_build_id": "exact-extension-build-uuid"
}]
```

Omit `dependencies` to use the web app's attached defaults. Pass `"[]"` to
explicitly run without extensions. An app UUID uses that extension's active
build; an object with `app_build_id` pins the exact build. Extension-enabled
runs use Chrome by default or Chromium, and one suite run uses the same
extension loadout for every flow in its shared browser session.

Run and automation tools accept `locale` (such as `"de-DE"`) to open the app in that language, and most accept `location` (such as `"MX"`) to send traffic from that country. [Language & region](/docs/language-and-region.md#with-mcp) and [Proxy location](/docs/run-location.md) list which tools take each one.

Run responses from `flows_run`, `suites_run`, and `labels_run` include a **Batch** link for viewing or sharing all runs launched together.

To run [code-managed tests](/docs/code-managed-flows.md) as they are on a branch, pass `repo_full_name` and `branch_name` to `labels_run`, `suites_run`, or `folders_run`. The run uses that branch's `.BugRadar/` files, including tests that exist only on the branch, and the newest build uploaded for the branch. A suite that exists only on the branch has no ID yet, so pass `suite_key` (its folder path under `.BugRadar/`) to `suites_run` instead of `suite_id`. For a folder that exists only on the branch, pass `folder_paths` (for example `Auth/Onboarding`) to `folders_run` instead of `folder_ids`. Without a branch, runs use the default branch's tests.

If the branch has an open pull request, a branch run shows its results on that pull request, for that commit only. A later push does not run those tests again.

### Workspaces

| Tool | Description |
| - | - |
| `workspaces_list` | List the workspaces in your company and show which one is active |
| `workspaces_switch` | Switch the active workspace to another one in your company |

Every other tool acts in your active workspace. These two tools need a browser sign-in connection. An API key always acts in the workspace it was created in.

Switching applies to your whole BugRadar login, not just one agent. The dashboard and any other agent signed in as you switch too.

### Results & Debugging

| Tool | Description |
| - | - |
| `list_suite_runs` | List recent suite run results with optional date filters |
| `list_flow_runs` | List recent flow run results with optional date filters |
| `list_hook_runs` | List recent hook run results with optional date filters |
| `read_suite_run` | Read detailed suite run info showing which flows passed/failed |
| `read_flow_run` | Read run details, recording link, actions, review, hooks, and extension build provenance |
| `read_hook_run` | Read detailed hook run info including status and output |

`read_flow_run` reports the exact dependency build IDs and available extension
metadata such as app/build IDs, app name, platform, source, branch, commit, and
upload time. It also returns a public link to the run's screen recording (MP4),
one per device for a two-device run.

### Labels, Automations & Environment Variables

| Tool | Description |
| - | - |
| `labels_list` | List the labels on your flows and suites |
| `labels_create` | Create a label |
| `labels_update` | Rename or recolor a label |
| `labels_delete` | Delete labels and detach them from flows, suites, and runs |
| `labels_run` | Run every suite and flow that carries the given labels |
| `automations_list` | List scheduled runs, optionally filtered by app |
| `automations_read` | Read an automation's schedule, targets, and last and next run |
| `automations_create` | Schedule flow or suite runs |
| `automations_update` | Change an automation's schedule or targets |
| `automations_delete` | Turn off automations |
| `env_vars_read` | Read an environment variable. Secret values stay masked |
| `env_vars_create` | Add a variable or secret to an environment |
| `env_vars_update` | Change a variable or secret |
| `env_vars_delete` | Delete variables and secrets |

### Issues & Pull Requests

| Tool | Description |
| - | - |
| `issues_list` | List grouped issues found in your runs |
| `issues_read` | Read an issue with its affected flows and occurrences |
| `issues_update_state` | Dismiss, close, or restore an issue |
| `pr_get_status` | Show a pull request's attached flows and their results |
| `pr_attach_flow` | Run existing flows on a pull request |
| `pr_detach_flow` | Stop running a flow on a pull request |
| `pr_commit_flow_as_code` | Commit a passing flow to the pull request's branch as a file |
| `runs_terminate` | Stop in-progress runs |

### Account & Documentation

| Tool | Description |
| - | - |
| `onboard` | Get a step-by-step setup guide for a new workspace |
| `whoami` | Show the connected workspace and company |
| `agent_feedback` | Send a bug report or suggestion to the BugRadar team |
| `search_BugRadar` | Search the BugRadar documentation |
| `query_docs_filesystem_BugRadar` | Read BugRadar documentation pages |

***

## Example Usage

#### Generate E2E tests from your codebase

```
Crawl my repo, come up with an E2E testing strategy, and create flows in BugRadar
```

#### Increase test coverage from a PR

```
Look at this PR and get us to 80% E2E coverage by writing flows in BugRadar
```

#### Debug failing tests

```
My login suite is failing. Help me figure out what's wrong and fix it.
```

#### Create hooks for backend setup

```
Create a setup hook that resets the test database before each flow runs
```

#### Check test run history

```
Show me the last 10 runs of my checkout flow and their success rates
```

#### Identify coverage gaps

```
Look at my BugRadar coverage and see where we are missing tests
```

***

## Permissions and Data

The server acts in your workspace with your access. An API key acts in the workspace where it was created. Secret values are never returned.

* **Reads and changes** your BugRadar data: flows, suites, apps, run results and settings.
* **Commits** passing flows to your linked GitHub repo with `pr_commit_flow_as_code`.
* **Starts runs** that count toward your plan's usage.
* **Labels every tool** as read-only or able to change data, so your assistant can ask before making changes.

To disconnect, remove BugRadar from your assistant's MCP settings. See our [Privacy Policy](https://app.termly.io/policy-viewer/policy.html?policyUUID=744ff463-b779-49e4-92e5-91e31733b1e3) and [Terms of Service](https://app.termly.io/policy-viewer/policy.html?policyUUID=337d36f5-945d-42a9-b472-b82de4a978a8), or email [founders@usebugradar.com](mailto:founders@usebugradar.com).

***

## Resources

* [MCP Protocol Specification](https://modelcontextprotocol.io)
* [Claude Code](https://docs.anthropic.com/en/docs/claude-code/mcp)
* [Claude Desktop](https://modelcontextprotocol.io/quickstart/user)
* [Cursor](https://docs.cursor.com/context/model-context-protocol)
* [Gemini CLI](https://google-gemini.github.io/gemini-cli/docs/tools/mcp-server.html)
* [Codex](https://developers.openai.com/codex/mcp/)
* [Dots](/docs/dots.md)
* [Grok Bot](/docs/grok-bot.md)
* [Devin](/docs/devin.md)
* [Hermes Agent](/docs/hermes-agent.md)
* [OpenClaw](https://docs.openclaw.ai/gateway/configuration)
* [Report an Issue](https://github.com/BugRadar/BugRadar/issues)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.