MagicPod

by Magic-Pod

5 stars

140 downloads

Not rated

GitHub

Description

# magicpod-mcp-server An MCP (Model Context Protocol) server that integrates your AI agents with MagicPod ## Getting Started [Cursor](https://cursor.com), [Claude](https://claude.ai/), and many other AI-powered coding tools support MCP servers. You can refer to their official…

About

Details

Author: Magic-Pod
GitHub stars: 5
Downloads: 140
Categories: Developer Tools, Automation, AI, Other

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below

Plugin Name MagicPod

Command (node, npx, python, etc.)

Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "magicpod": {
            "magicpod-mcp-server": {
                "command": "npx",
                "args": [
                    "-y",
                    "magicpod-mcp-server",
                    "--api-token=YOUR-API-TOKEN"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "magicpod": {
            "magicpod-mcp-server": {
                "command": "npx",
                "args": [
                    "-y",
                    "magicpod-mcp-server",
                    "--api-token=YOUR-API-TOKEN"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "magicpod": {
            "magicpod-mcp-server": {
                "command": "npx",
                "args": [
                    "-y",
                    "magicpod-mcp-server",
                    "--api-token=YOUR-API-TOKEN"
                ]
            }
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "magicpod": {
            "magicpod-mcp-server": {
                "command": "npx",
                "args": [
                    "-y",
                    "magicpod-mcp-server",
                    "--api-token=YOUR-API-TOKEN"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "magicpod": {
            "magicpod-mcp-server": {
                "command": "npx",
                "args": [
                    "-y",
                    "magicpod-mcp-server",
                    "--api-token=YOUR-API-TOKEN"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "magicpod": {
            "magicpod-mcp-server": {
                "command": "npx",
                "args": [
                    "-y",
                    "magicpod-mcp-server",
                    "--api-token=YOUR-API-TOKEN"
                ]
            }
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "magicpod": {
            "magicpod-mcp-server": {
                "command": "npx",
                "args": [
                    "-y",
                    "magicpod-mcp-server",
                    "--api-token=YOUR-API-TOKEN"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "magicpod": {
            "magicpod-mcp-server": {
                "command": "npx",
                "args": [
                    "-y",
                    "magicpod-mcp-server",
                    "--api-token=YOUR-API-TOKEN"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "magicpod": {
            "magicpod-mcp-server": {
                "command": "npx",
                "args": [
                    "-y",
                    "magicpod-mcp-server",
                    "--api-token=YOUR-API-TOKEN"
                ]
            }
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "magicpod": {
            "magicpod-mcp-server": {
                "command": "npx",
                "args": [
                    "-y",
                    "magicpod-mcp-server",
                    "--api-token=YOUR-API-TOKEN"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "magicpod": {
            "magicpod-mcp-server": {
                "command": "npx",
                "args": [
                    "-y",
                    "magicpod-mcp-server",
                    "--api-token=YOUR-API-TOKEN"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "magicpod": {
            "magicpod-mcp-server": {
                "command": "npx",
                "args": [
                    "-y",
                    "magicpod-mcp-server",
                    "--api-token=YOUR-API-TOKEN"
                ]
            }
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "magicpod": {
            "magicpod-mcp-server": {
                "command": "npx",
                "args": [
                    "-y",
                    "magicpod-mcp-server",
                    "--api-token=YOUR-API-TOKEN"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "magicpod": {
            "magicpod-mcp-server": {
                "command": "npx",
                "args": [
                    "-y",
                    "magicpod-mcp-server",
                    "--api-token=YOUR-API-TOKEN"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "magicpod": {
            "magicpod-mcp-server": {
                "command": "npx",
                "args": [
                    "-y",
                    "magicpod-mcp-server",
                    "--api-token=YOUR-API-TOKEN"
                ]
            }
        }
    }
}

From the repository

Using An Environment Variable Instead Of Api Token

Passing the token via--api-tokenputs it in plain text in the process's argument list (visible viaps,/proc/<pid>/cmdline, monitoring tools, etc.), which can be a concern on shared or monitored hosts. As an alternative, you can set theMAGICPOD_API_TOKENenvironment variable instead, using theenvfield supported by most MCP clients:

{ "mcpServers": { "magicpod-mcp-server": { "command": "npx", "args": ](https://app.magicpod.com/accounts/api-token/)["-y", "magicpod-mcp-server"], "env": { "MAGICPOD_API_TOKEN": "YOUR-API-TOKEN" } } } }

If both--api-tokenandMAGICPOD_API_TOKENare set,--api-tokentakes precedence.

Configuring Tool Permissions in Claude Code

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

An AI-powered system that converts Acceptance Criteria (AC) from QA specifications into automated browser testing workflows.

Playwriter Session Cloud is a paid remote MCP endpoint for AI agent browser MCP session. It exposes structured JSON tools, a public server card, token-based access, usage receipts, and audit

A browser-agent QA swarm with an MCP interface for testing AI-generated websites.

MCP server for the Computer-Use Agent (CUA), allowing you to run CUA through Claude Desktop or other MCP clients.

Bring agent evaluations, observability, and synthetic test set generation directly into your IDE for free with Galileo's new MCP server

Browser automation via MCP for Chrome and Firefox

Bring the full power of BrowserStack’s Test Platform to your AI tools, making testing faster and easier for every developer and tester on your team.

Official Chrome DevTools MCP server for controlling and inspecting a live Chrome browser from coding agents such as Gemini, Claude, Cursor, and Copilot.

Equip AI agents with evaluation and self-improvement capabilities with Root Signals.

`API-delete_users`

Remove an organization-specific user from MagicPod Error Responses: 400: Validation error

`API-get_available_cloud_device`

Get the number of currently available cloud device for an organization Error Responses: 400: Validation error

`API-get_organization_members`

Get members of the organization. Email addresses are available only for organization-exclusive users. Error Responses: 400: Validation error

`API-remove_member_from_organization`

Remove a user from an organization members Error Responses: 400: Validation error

`API-get_projects`

It returns all projects that the requesting user can view. To get all projects of an organization, you need to use the API token for the organization owner. Error Responses: 400: Validation error

`API-get_project_batch_run_schedules`

Get batch run schedules of the project. Error Responses: 400: Validation error

`API-start_batch_run`

Start batch test run on cloud. For desktop browser testing, please see request parameters generated on the project batch run page (Setting -> Menu -> Copy as curl). Error Responses: 400: Validation error

`API-get_batch_run`

Get individual batch run information Error Responses: 400: Validation error

`API-get_crash_log`

Get crash log of test case run by curl "https://app.magicpod.com/api/v1.0/{organization_name}/{project_name}/batch-run/{batch_run_number}/{pattern_number}/{run_number_in_batch_run}/{data_pattern_number}/crash-log/" -H "Authorization: Token {apikey}" --output {filename}.log or get it with recommended file name by curl "https://app.magicpod.com/api/v1.0/{organization_name}/{project_name}/batch-run/{batch_run_number}/{pattern_number}/{run_number_in_batch_run}/{data_pattern_number}/crash-log/" -H "Authorization: Token {apikey}" -J -O Error Responses: 400: Validation error 404: Not Found

`API-get_device_log`

Get device log of test case run by curl "https://app.magicpod.com/api/v1.0/{organization_name}/{project_name}/batch-run/{batch_run_number}/{pattern_number}/{run_number_in_batch_run}/{data_pattern_number}/device-log/" -H "Authorization: Token {apikey}" --output {filename}.log or get it with recommended file name by curl "https://app.magicpod.com/api/v1.0/{organization_name}/{project_name}/batch-run/{batch_run_number}/{pattern_number}/{run_number_in_batch_run}/{data_pattern_number}/device-log/" -H "Authorization: Token {apikey}" -J -O Error Responses: 400: Validation error 404: Not Found

`API-get_failure_analysis`

Get the latest AI failure analysis result for a test case run. Returns {} (200) when no analysis exists yet or the result is not yet available. Error Responses: 400: Validation error 404: Not Found

`API-get_test_engine_log`

Get test engine log of test case run by curl "https://app.magicpod.com/api/v1.0/{organization_name}/{project_name}/batch-run/{batch_run_number}/{pattern_number}/{run_number_in_batch_run}/{data_pattern_number}/test-engine-log/" -H "Authorization: Token {apikey}" --output {filename}.log or get it with recommended file name by curl "https://app.magicpod.com/api/v1.0/{organization_name}/{project_name}/batch-run/{batch_run_number}/{pattern_number}/{run_number_in_batch_run}/{data_pattern_number}/test-engine-log/" -H "Authorization: Token {apikey}" -J -O Error Responses: 400: Validation error 404: Not Found

`API-get_test_run_log`

Get test run log of test case run by curl "https://app.magicpod.com/api/v1.0/{organization_name}/{project_name}/batch-run/{batch_run_number}/{pattern_number}/{run_number_in_batch_run}/{data_pattern_number}/test-run-log/" -H "Authorization: Token {apikey}" --output {filename}.log or get it with recommended file name by curl "https://app.magicpod.com/api/v1.0/{organization_name}/{project_name}/batch-run/{batch_run_number}/{pattern_number}/{run_number_in_batch_run}/{data_pattern_number}/test-run-log/" -H "Authorization: Token {apikey}" -J -O Error Responses: 400: Validation error 404: Not Found

`API-get_batch_runs`

Get the batch runs information in the most recent first order. Error Responses: 400: Validation error

`API-get_batch_task_result`

Get a batch task's status. Error Responses: 400: Validation error

`API-start_cross_batch_run`

Start cross variation batch test run on cloud. Or you can start a batch run by specifying already defined test condition number. Error Responses: 400: Validation error

`API-delete_file`

Delete an app file (.app, .ipa, .apk or .aab) in MagicPod cloud Error Responses: 400: Validation error

`API-get_health_score`

Get the daily/weekly/monthly health score of the specified project. The score is aggregated on the MagicPod server periodically based on UTC date/week/month. Error Responses: 400: Validation error

`API-list_files`

Get list of app files (.app, .ipa, .apk or .aab) in MagicPod cloud. If no app files uploaded, `app_files` parameter in response will have an empty array. Error Responses: 400: Validation error

`API-get_project_members`

Get members of the project. Email addresses are available only for organization-exclusive users. Error Responses: 400: Validation error

`API-get_shared_steps`

Get the shared steps in ascending order by their numbers. The "shared_step.number" may change without notification in the future, potentially breaking backward compatibility. This API retrieves only the first 300 characters of the "description". Error Responses: 400: Validation error

`API-get_shared_step`

Get the information of the shared step for the specified shared step number. The "shared_step.number" may change without notification in the future, potentially breaking backward compatibility. Error Responses: 400: Validation error

`API-get_test_cases`

Get the test cases in ascending order by their numbers. This API retrieves only the first 300 characters of the "description". Error Responses: 400: Validation error

`API-get_test_case`

Get the information of the test case for the specified test case number. Human-readable text in the response is not intended to be used for other purposes than reading by human such as parsing by program, and its format could be changed without notice. Error Responses: 400: Validation error

`API-v1_0_upload-file_create`

Upload target app files (.ipa, .apk, .aab, or zipped .app) to MagicPod cloud

`API-v1_0_upload-data-patterns_create`

Upload data pattern CSV to test case and wait for completion. This operation runs synchronously and will wait for the upload to finish before returning.

`API-v1_0_list-test-settings`

Retrieve available test settings for a project. Test settings define test configurations (device type, browser version, screen size, etc.) and are needed when creating Autopilot tasks. If the user tries to create an Autopilot task without specifying a test setting, you should use this tool automatically to pick a valid setting. Only settings with the 'Cloud' environment are valid for Autopilot tasks. If the desired configuration cannot be found with includePrivate=false, use this tool again with includePrivate=true. Returns test settings with their names, numbers, and associated test patterns.

`search-magicpod-articles`

This tool searches the list of articles on MagicPod help center by specified keywords. You must use this tool whenever you mention MagicPod's specification since it has always been updated.

`read-magicpod-article`

Read a specified article on MagicPod help center

`API-v1_0_create-autopilot-tasks`

Create Autopilot tasks for test case creation and/or editing. Autopilot is an AI agent that can generate/edit E2E tests for mobile apps and web apps in MagicPod style. Use the list projects tool first to check the project platform type. Provide testCaseCreateTasks to create new test cases, and/or testCaseEditTasks to edit existing ones. At least one of the task arrays must be provided.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "magicpod": {
            "magicpod-mcp-server": {
                "command": "npx",
                "args": [
                    "-y",
                    "magicpod-mcp-server",
                    "--api-token=YOUR-API-TOKEN"
                ]
            }
        }
    }
}

McpServers

{
    "magicpod-mcp-server": {
        "command": "npx",
        "args": [
            "-y",
            "magicpod-mcp-server",
            "--api-token=YOUR-API-TOKEN"
        ]
    }
}

[!IMPORTANT]This repository is deprecatedin favor of the newMagicPod MCP Server. It will only receive bug fixes and security fixes for a limited support period, and will be archived once that period ends. The exact end date has not been finalized yet and will be announced here soon.

Please migrate to the new MagicPod MCP Server — see the setup instructionsfor details.

An MCP (Model Context Protocol) server that integrates your AI agents with MagicPod

Cursor,Claude, and many other AI-powered coding tools support MCP servers. You can refer to their official documents on how to configure MCP servers. For example, if you use Claude Desktop, what you have to do to integrate with MagicPod is only to add the following lines in yourclaude_desktop_config.json.

{ "mcpServers": { "magicpod-mcp-server": { "command": "npx", "args": ["-y", "magicpod-mcp-server", "--api-token=YOUR-API-TOKEN"] } } }

{ "mcpServers": { "magicpod-mcp-server": { "command": "cmd", "args": ["/c", "npx", "-y", "magicpod-mcp-server", "--api-token=YOUR-API-TOKEN"] } } }

Make sure that you replaceYOUR-API-TOKENwith your actual MagicPod API token. You can retrieve it on theintegrationsscreen.

Using an environment variable instead of`--api-token`

{ "mcpServers": { "magicpod-mcp-server": { "command": "npx", "args": ["-y", "magicpod-mcp-server"], "env": { "MAGICPOD_API_TOKEN": "YOUR-API-TOKEN" } } } }

If both--api-tokenandMAGICPOD_API_TOKENare set,--api-tokentakes precedence.

Configuring Tool Permissions in Claude Code

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

An AI-powered system that converts Acceptance Criteria (AC) from QA specifications into automated browser testing workflows.

Playwriter Session Cloud is a paid remote MCP endpoint for AI agent browser MCP session. It exposes structured JSON tools, a public server card, token-based access, usage receipts, and audit

A browser-agent QA swarm with an MCP interface for testing AI-generated websites.

MCP server for the Computer-Use Agent (CUA), allowing you to run CUA through Claude Desktop or other MCP clients.

Bring agent evaluations, observability, and synthetic test set generation directly into your IDE for free with Galileo's new MCP server

Browser automation via MCP for Chrome and Firefox

Bring the full power of BrowserStack’s Test Platform to your AI tools, making testing faster and easier for every developer and tester on your team.

Official Chrome DevTools MCP server for controlling and inspecting a live Chrome browser from coding agents such as Gemini, Claude, Cursor, and Copilot.

Equip AI agents with evaluation and self-improvement capabilities with Root Signals.

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

Description

About

Details

Jump to

Setting up with Highlight

From the repository

Using An Environment Variable Instead Of Api Token

API-delete_users

API-get_available_cloud_device

API-get_organization_members

API-remove_member_from_organization

API-get_projects

API-get_project_batch_run_schedules

API-start_batch_run

API-get_batch_run

API-get_crash_log

API-get_device_log

API-get_failure_analysis

API-get_test_engine_log

API-get_test_run_log

API-get_batch_runs

API-get_batch_task_result

API-start_cross_batch_run

API-delete_file

API-get_health_score

API-list_files

API-get_project_members

API-get_shared_steps

API-get_shared_step

API-get_test_cases

API-get_test_case

API-v1_0_upload-file_create

API-v1_0_upload-data-patterns_create

API-v1_0_list-test-settings

search-magicpod-articles

read-magicpod-article

API-v1_0_create-autopilot-tasks

Claude Desktop / Cursor

McpServers

Using an environment variable instead of--api-token

Install

More like this

@mendableai/firecrawl Mcp Server

Umut Naci

Playwright

Sentry

Github

Fetch

`API-delete_users`

`API-get_available_cloud_device`

`API-get_organization_members`

`API-remove_member_from_organization`

`API-get_projects`

`API-get_project_batch_run_schedules`

`API-start_batch_run`

`API-get_batch_run`

`API-get_crash_log`

`API-get_device_log`

`API-get_failure_analysis`

`API-get_test_engine_log`

`API-get_test_run_log`

`API-get_batch_runs`

`API-get_batch_task_result`

`API-start_cross_batch_run`

`API-delete_file`

`API-get_health_score`

`API-list_files`

`API-get_project_members`

`API-get_shared_steps`

`API-get_shared_step`

`API-get_test_cases`

`API-get_test_case`

`API-v1_0_upload-file_create`

`API-v1_0_upload-data-patterns_create`

`API-v1_0_list-test-settings`

`search-magicpod-articles`

`read-magicpod-article`

`API-v1_0_create-autopilot-tasks`

Using an environment variable instead of`--api-token`