About
Expo Dev Assistant provides AI-driven management of Expo and React Native projects through the Expo Application Services (EAS) platform. It enables end-to-end mobile development workflows from initial project setup to production deployment across iOS and Android. Key features include: - Project scaffolding and configuration management with support for creating new projects, installing packages, validating app config, and generating native iOS/Android code via prebuild - Cloud-based CI/CD pipelines through EAS Build for compiling iOS and Android apps with real-time build status monitoring, log streaming, and cancellation controls - Over-the-air (OTA) update publishing to instantly deploy JavaScript changes to specific branches and channels without app store review delays - Automated app store submissions to Apple App Store Connect and Google Play Console through EAS Submit - Built-in diagnostics with health checks and configuration validation via `expo doctor` - LLM-optimized documentation access covering Expo CLI reference, EAS Build, EAS Update, and EAS Submit guides
README
Expo MCP Server
[](https://badge.fury.io/js/expo-mcp-server) [](https://opensource.org/licenses/MIT) [](https://modelcontextprotocol.io/)
Model Context Protocol server for Expo.dev — programmatically manage Expo projects and EAS services through AI assistants like Claude.
What It Does
This MCP server gives AI assistants full control over Expo/React Native development workflows:
| Category | Capabilities | |----------|-------------| | Project Setup | Initialize projects, install packages, configure apps, generate native code | | Cloud Builds | Trigger iOS/Android builds, monitor progress, view logs, cancel builds | | OTA Updates | Publish updates to branches, manage channels, instant deployments | | App Submission | Submit to App Store Connect and Google Play Console | | Diagnostics | Run health checks, validate configurations |
Quick Start
Install via Smithery
npx @smithery/cli install expo-mcp-server
Or Add to MCP Config
{
"mcpServers": {
"expo-dev": {
"command": "npx",
"args": ["-y", "expo-mcp-server"],
"env": {
"EXPO_TOKEN": "your_token_here"
}
}
}
}
Get your token at expo.dev/settings/access-tokens
Tools
Project Management
expo_init_project — Create new Expo projects with templatesexpo_install_packages — Install packages with version validationexpo_get_config — View and validate app configurationexpo_prebuild — Generate native iOS/Android directoriesEAS Build
eas_build_create — Trigger cloud builds (iOS, Android, or both)eas_build_list — List builds with filteringeas_build_status — Get build status and logseas_build_cancel — Cancel in-progress buildsEAS Update (OTA)
eas_update_publish — Publish over-the-air updateseas_update_list — List published updateseas_channel_create — Create update channelsEAS Submit
eas_submit_ios — Submit to App Store Connect/TestFlighteas_submit_android — Submit to Google Play ConsoleUtilities
expo_doctor — Run project diagnosticsexpo_whoami — Check authentication statuseas_project_info — Get EAS project metadataResources
The server exposes documentation as MCP resources:
expo://docs/llms # Complete Expo docs (LLM-optimized)
expo://docs/eas-build # EAS Build guide
expo://docs/eas-update # EAS Update guide
expo://docs/eas-submit # EAS Submit guide
expo://docs/cli-reference # Expo CLI reference
Example Workflows
"Build my app for both platforms"
→ eas_build_create(platform: "all", profile: "production")
"Push a hotfix to production"
→ eas_update_publish(branch: "production", message: "Fix auth bug")
"Submit the latest build to TestFlight"
→ eas_submit_ios(buildId: "abc-123")
Output Formats
All tools support:
markdown (default) — Human-readable tablesjson — Structured data for processingDevelopment
git clone https://github.com/CaullenOmdahl/expo-mcp-server
cd expo-mcp-server
npm install
npm run build
npm run dev # Run with Smithery playground
Architecture
src/
├── index.ts # Server entry point
├── types.ts # Shared schemas
├── resources/ # Documentation resources
├── tools/ # Tool implementations
│ ├── project.ts # Project management
│ ├── build.ts # EAS Build
│ ├── update.ts # EAS Update
│ └── submit.ts # EAS Submit
└── utils/ # CLI execution, formatting
Built with TypeScript, MCP SDK, and Zod validation.
Requirements
Links
License
MIT
Related MCP Servers
AI Research Assistant
hamid-vakilzadeh
AI Research Assistant provides comprehensive access to millions of academic papers through the Semantic Scholar and arXiv databases. This MCP server enables AI coding assistants to perform intelligent literature searches, citation network analysis, and paper content extraction without requiring an API key. Key features include: - Advanced paper search with multi-filter support by year ranges, citation thresholds, field of study, and publication type - Title matching with confidence scoring for finding specific papers - Batch operations supporting up to 500 papers per request - Citation analysis and network exploration for understanding research relationships - Full-text PDF extraction from arXiv and Wiley open-access content (Wiley TDM token required for institutional access) - Rate limits of 100 requests per 5 minutes with options to request higher limits through Semantic Scholar
Linkup
LinkupPlatform
Linkup is a real-time web search and content extraction service that enables AI assistants to search the web and retrieve information from trusted sources. It provides source-backed answers with citations, making it ideal for fact-checking, news gathering, and research tasks. Key features of Linkup: - Real-time web search using natural language queries to find current information, news, and data - Page fetching to extract and read content from any webpage URL - Search depth modes: Standard for direct-answer queries and Deep for complex research across multiple sources - Source-backed results with citations and context from relevant, trustworthy websites - JavaScript rendering support for accessing dynamic content on JavaScript-heavy pages
Math-MCP
EthanHenrickson
Math-MCP is a computation server that enables Large Language Models (LLMs) to perform accurate numerical calculations through the Model Context Protocol. It provides precise mathematical operations via a simple API to overcome LLM limitations in arithmetic and statistical reasoning. Key features of Math-MCP: - Basic arithmetic operations: addition, subtraction, multiplication, division, modulo, and bulk summation - Statistical analysis functions: mean, median, mode, minimum, and maximum calculations - Rounding utilities: floor, ceiling, and nearest integer rounding - Trigonometric functions: sine, cosine, tangent, and their inverses with degrees and radians conversion support