idb-mcp
An MCP server that uses Facebook IDB to automate iOS simulators, providing device control, input actions, and screenshots over HTTP, SSE, or stdio.
IDB-MCP
An open-source MCP server and Python library that wraps Facebook IDB to control iOS simulators for automation. Built by AskUI.
This project is based on the Facebook IDB CLI (fb-idb). See the GitHub repository (facebook/idb) and the Python package (fb-idb on PyPI).
What it is
- MCP server: Exposes a set of iOS automation tools (list/select device, screenshot, tap, swipe, type, etc.) over MCP transports (HTTP, SSE or stdio) using
fastmcp. - Python module: Import to manage and control iOS simulators programmatically.
Table of contents
Key features
- Device management 🔧: list devices, select by UDID or name, boot/shutdown, kill IDB.
- Input control 👆: tap, swipe, type text, tap keys, tap buttons.
- Screen utilities 🖼️: capture screenshots, query screen size, get view description.
- Image/coord scaling 📐: optional scaling to a target viewport for consistent coordinates.
Limitations
⚠️ Only iOS simulators are supported for UI control. Due to iOS security constraints, idb cannot interact with or automate the UI on real, physical devices. AskUI offers a solution for real-device UI automation—contact [email protected] for more information.
Requirements
-
Runs on macOS only.
-
Python >= 3.10
-
Xcode with iOS Simulators installed and configured.
-
Verify simulators are visible:
xcrun xctrace list devices
-
-
Facebook IDB companion (using
brew):brew tap facebook/fb brew install idb-companion
Install
pip install idb-mcp
Quick start (CLI)
Why MCP?
Using MCP lets your favorite AI tools connect to idb-mcp seamlessly. The client handles launching and communicating with the server, so you can ask for screenshots, taps, swipes, and more—without leaving your workflow. ✨
Start MCP server
The package installs an idb-mcp command.
# Start MCP server over HTTP (default host/port managed by fastmcp)
idb-mcp start http
# Or start over SSE
idb-mcp start sse
# Or start over stdio
idb-mcp start stdio
# Optionally scale images/coordinates to a given target viewport (width height)
idb-mcp start http --target-screen-size 1280 800
# Discover available options
idb-mcp --help
idb-mcp start --help
Programmatic usage (Python)
from idb_mcp import IDBController, IOSDevice
# Initialize the IDB controller
controller = IDBController()
# Select the device by name
selected_device: IOSDevice = controller.select_device_by_name("iPhone 17 Pro Max")
# Boot the selected device
selected_device.boot()
# Get the current view description of the selected device
current_view_description: str = selected_device.get_current_view_description()
print(current_view_description)
# Shutdown the selected device
selected_device.shutdown()
Add to your favorite tools
You can use idb-mcp in any MCP-compatible client (e.g., Cursor, Claude Desktop) by adding a server entry to your client's MCP config. The client will launch the server on demand.
Steps:
- Open your client's MCP configuration file (location varies by client).
- Add an entry named
askui-idb-mcpthat starts the server over STDIO and sets a recommended target screen size.
Example configuration:
using uv (Make sure you have uv installed):
{
"mcpServers": {
"askui-idb-mcp": {
"command": "uvx",
"args": [
"idb-mcp@latest",
"start",
"stdio",
"--target-screen-size",
"1280",
"800"
]
}
}
}
Alternative (if idb-mcp is directly on your PATH without uv):
{
"mcpServers": {
"askui-idb-mcp": {
"command": "idb-mcp",
"args": [
"start",
"stdio",
"--target-screen-size",
"1280",
"800"
]
}
}
}
Notes:
- The
--target-screen-size 1280 800setting improves coordinate reliability, especially for models like Claude.
Configuration
- Target screen size 📐: You can scale screenshots and coordinate inputs to a target viewport when starting the MCP server via CLI (
--target-screen-size W H) or programmatically (target_screen_size=(W, H)). - Mode 📐: You can start the MCP server in
stdio,http, orssemode. - Port 📐: You can start the MCP server on a specific port via CLI (
--port PORT) or programmatically (port=PORT).
Troubleshooting
-
Cannot see devices 🔍: Make sure you have an iOS simulator or device connected and running. Verify with:
xcrun xctrace list devicesExample output:
iPhone 17 Simulator (26.0) (32E2219C-ED40-452F-9A4D-XXXXXXX) iPhone 17 Pro Simulator (26.0) (764CCCB7-D84D-46EC-B62D-XXXXXXX) iPhone 17 Pro Max Simulator (26.0) (065382B5-56B4-4864-8174-XXXXXXX) -
High-resolution screenshots with some LLMs 🧠: Some LLM backends struggle to process very high-resolution images, resulting in poor coordinate detection or tapping errors. Use rescaling via
--target-screen-size(ortarget_screen_sizein Python) to downscale screenshots and coordinates. For Claude models, we recommend1280 800.
Development
This repository uses PDM and Ruff for dev tooling.
# Install dev deps
pip install pdm
pdm install --with dev
# Lint / Format
pdm run lint-check
pdm run format-check
# Type check
pdm run type-check
Contributing
Contributions are welcome! 🙌 Please open an issue or pull request on GitHub. Questions? Email us at [email protected].
License
MIT License
Links
- Homepage: https://github.com/askui/idb-mcp
- AskUI: https://www.askui.com
관련 서버
Alpha Vantage MCP Server
스폰서Access financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
BCMS MCP
Give me a one - two sentence description of the BCMS MCP # MCP The BCMS Model Context Protocol (MCP) integration enables AI assistants like Claude, Cursor, and other MCP-compatible tools to interact directly with your BCMS content. This allows you to create, read, and update content entries, manage media files, and explore your content structure—all through natural language conversations with AI. ## What is MCP? The [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) is an open standard developed by Anthropic that allows AI applications to securely connect to external data sources and tools. With BCMS MCP support, you can leverage AI assistants to: - Query and explore your content structure - Create new content entries with AI-generated content - Update existing entries - Manage your media library - Get intelligent suggestions based on your content model --- ## Getting Started ### Prerequisites 1. A BCMS account with an active instance 2. An MCP key with appropriate permissions 3. An MCP-compatible client (Claude Desktop, Cursor, or any MCP client) ### Step 1: Create an MCP Key 1. Navigate to your BCMS dashboard 2. Go to Settings → MCP 3. Click Create MCP Key 4. Configure the permissions for templates you want the AI to access:GET: Read entries 5. POST: Create entries 6. PUT: Update entries 7. DELETE: Delete entries Note: Right now, MCP only supports creating, reading and updating content. ### Step 2: Configure Your MCP Client You can find full instructions for integrating BCMS with your AI tools right inside BCMS, on the MCP page. But in general, installing BCMS MCP works in a standard way: ``` { "mcpServers": { "bcms": { "url": "https://app.thebcms.com/api/v3/mcp?mcpKey=YOUR_MCP_KEY" } } } ``` ## Available Tools Once connected, your AI assistant will have access to the following tools based on your MCP key permissions: ### Content Discovery #### list_templates_and_entries Lists all templates and their entries that you have access to. This is typically the first tool to call when exploring your BCMS content. Returns: - Template IDs, names, and slugs - Entry IDs with titles and slugs for each language Example prompt: "Show me all the templates and entries in my BCMS" --- ### Entry Management #### list_entries_for_{templateId} Retrieves all entries for a specific template with full content data. A separate tool is generated for each template you have access to. Returns: - Complete entry data including all meta fields - Content in all configured languages - Entry statuses Example prompt: "List all blog posts from my Blog template" --- #### create_entry_for_{templateId} Creates a new entry for a specific template. The input schema is dynamically generated based on your template's field structure. Input: - statuses: Array of status assignments per language - meta: Array of metadata for each language (title, slug, custom fields) - content: Array of content nodes for each language Example prompt: "Create a new blog post titled 'Getting Started with BCMS' with a brief introduction paragraph" --- #### update_entry_for_{templateId} Updates an existing entry for a specific language. Input: - entryId: The ID of the entry to update - lng: Language code (e.g., "en") - status: Optional status ID - meta: Updated metadata - content: Updated content nodes Example prompt: "Update the introduction paragraph of my 'Getting Started' blog post" --- ### Media Management #### list_all_media Lists all media files in your media library. Returns: - Media IDs, names, and types - File metadata (size, dimensions for images) - Parent directory information Example prompt: "Show me all images in my media library" --- #### list_media_dirs Lists the directory structure of your media library. Returns: - Hierarchical directory structure - Directory IDs and names Example prompt: "Show me the folder structure of my media library" --- #### create-media-directory Creates a new directory in your media library. Input: - name: Name of the directory - parentId: Optional parent directory ID (root if not specified) Example prompt: "Create a new folder called 'Blog Images' in my media library" --- #### request-upload-media-url Returns a URL you use to upload a file (for example via POST with multipart form data), which avoids pushing large binaries through the MCP tool payload. You still need a valid file name and MIME type when uploading, as described in the tool response. Availability: Only when the MCP key has Can mutate media enabled. Example prompt: “Give me an upload URL for a new hero image, then tell me how to upload it.” Input: - fileName: Name of the file with extension - fileData: Base64-encoded file data (with data URI prefix) - parentId: Optional parent directory ID Example prompt: "Upload this image to my Blog Images folder" --- ### Linking Tools #### get_entry_pointer_link Generates an internal BCMS link to an entry for use in content. Input: - entryId: The ID of the entry to link to Returns: - Internal link format: entry:{entryId}@*_{templateId}:entry Example prompt: "Get me the internal link for the 'About Us' page entry" --- #### get_media_pointer_link Generates an internal BCMS link to a media item for use in content. Input: - mediaId: The ID of the media item Returns: - Internal link format: media:{mediaId}@*_@*_:entry Example prompt: "Get the link for the hero image so I can use it in my blog post" --- ## Content Structure ### Entry Content Nodes When creating or updating entries, content is structured as an array of nodes. Supported node types include: Type Description paragraph Standard text paragraph heading Heading (h1-h6) bulletList Unordered list orderedList Numbered list listItem List item codeBlock Code block with syntax highlighting blockquote Quote block image Image node widget Custom widget with props ### Example Content Structure ``` { "content": [ { "lng": "en", "nodes": [ { "type": "heading", "attrs": { "level": 1 }, "content": [ { "type": "text", "text": "Welcome to BCMS" } ] }, { "type": "paragraph", "content": [ { "type": "text", "text": "This is your first paragraph." } ] } ] } ] } ``` ## Security & Permissions ### MCP Key Scopes Your MCP key controls what the AI can access: - Template Access: Only templates explicitly granted in the MCP key are visible - Operation Permissions: Each template can have independent GET/POST/PUT/DELETE permissions - Media Access: Media operations are controlled separately ### Best Practices 1. Principle of Least Privilege: Only grant the permissions needed for your use case 2. Separate Keys: Create different MCP keys for different purposes or team members 3. Regular Rotation: Periodically rotate your MCP keys ## Use Cases ### Content Creation Workflows Blog Post Creation "Create a new blog post about the benefits of headless CMS. Include an introduction, three main benefits with explanations, and a conclusion. Use the Blog template." Product Updates "Update the price field for all products in the Electronics category to apply a 10% discount" ### Content Exploration Content Audit "List all blog posts that don't have a featured image set" Translation Status "Show me which entries are missing German translations" ### Media Organization Library Cleanup "Show me all unused images in the media library" Folder Setup "Create folder structure for: Products > Categories > Electronics, Clothing, Home" ## Troubleshooting ### Common Issues #### "MCP key not found" - Verify your MCP key format: keyId.keySecret.instanceId - Ensure the MCP key hasn't been deleted or deactivated - Check that you're using the correct instance #### "MCP key does not have access to template" - Review your MCP key permissions in the dashboard - Ensure the required operation (GET/POST/PUT/DELETE) is enabled for the template #### Session Expired - MCP sessions may timeout after periods of inactivity - Simply start a new conversation to establish a fresh session ### Getting Help - Documentation: [thebcms.com/docs](https://thebcms.com/docs) - Support: [[email protected]](mailto:[email protected]) - Community: [Join BCMS Discord](https://discord.com/invite/SYBY89ccaR) for community support ## Technical Reference ### Endpoint POST https://app.thebcms.com/api/v3/mcp?mcpKey={MCP_KEY} ### Transport BCMS MCP uses the Streamable HTTP transport with session management. Sessions are maintained via the mcp-session-id header. ### Response Format All tools return structured JSON responses conforming to the MCP specification with: - content: Array of content blocks - structuredContent: Typed response data ## Rate Limits MCP requests are subject to the same rate limits as API requests: - Requests are tracked per MCP key - Contact support if you need higher limits for production workloads
MCP-scala
A Model Context Protocol server implementation written in Scala 3.
Figma
Interact with Figma files to view, comment on, and analyze designs.
Remote MCP Server (Authless)
An example of a remote MCP server deployable on Cloudflare Workers without authentication.
FileForge
Transforms raw code into polished solutions with optimized performance and vector embeddings support.
RenderLens
Visual verification MCP server — render code to screenshots, run WCAG accessibility audits, and pixel-diff UI changes. Free, no API key.
Starwind UI
A server providing tools for developers working with Starwind UI components.
MCP Script Runner
Execute developer-defined bash scripts in a Dockerized environment for coding agents.
MCP Test Utils
Desktop UI automation for AI agents: screenshots, window management, mouse, keyboard, UI Automation tree, OCR
Test Automator
An LLM-powered server for automating unit, integration, E2E, and API tests.