Typescript MCP
T

Typescript MCP

An MCP server for TypeScript type checking and code navigation, providing real - time type checking and code navigation functions for AI programming agents through the LSP of tsgo
2.5 points
7.0K

What is the TypeScript MCP Server?

The TypeScript MCP Server is a bridge that connects AI programming assistants (such as Claude Code) with the TypeScript language server. It allows AI assistants to perform TypeScript code analysis like professional developers, including type checking, jumping to definitions, finding references, renaming symbols, and other functions. This server is written in Go and communicates with AI assistants through the Model Context Protocol (MCP). It calls the LSP server of Microsoft's tsgo (TypeScript native Go compiler) for actual code analysis at the underlying level.

How to use the TypeScript MCP Server?

Using the TypeScript MCP Server is very simple: 1. Install Go 1.24+ and tsgo. 2. Install or build the typescript-mcp binary file. 3. Add the server to the MCP configuration of AI assistants such as Claude Code. 4. The AI assistant can then perform TypeScript code analysis through tool calls. After installation, the AI assistant can request code diagnostics, jump to definitions, view type information, etc., just like working in an IDE.

Applicable scenarios

The TypeScript MCP Server is particularly suitable for the following scenarios: - When an AI assistant helps write or modify TypeScript code. - When it is necessary to accurately understand the structure of an existing TypeScript codebase. - When performing code refactoring (such as renaming variables or functions). - When debugging TypeScript type errors. - When exploring an unfamiliar TypeScript project. Whether it is a small script or a large enterprise-level TypeScript project, this server can provide accurate code analysis.

Main features

TypeScript error checking
Get TypeScript compilation errors and warnings in a file, including type errors, syntax issues, etc. AI assistants can check code like a compiler to ensure that the modified code has no type errors.
Jump to definition
Quickly jump to the definition location of a symbol (variable, function, class, etc.). AI assistants can view the implementation of a function, the definition of an interface, or the declaration of a variable.
View type information
Get the type signature and documentation of a symbol. AI assistants can view the parameter types, return value types of a function, or the specific type of a variable.
Find all references
Find all places in the project where a symbol is used. This is very useful for understanding the scope of code influence or performing refactoring.
File symbol outline
Get the structured outline of a file, including all functions, classes, interfaces, and variables. AI assistants can quickly understand the organizational structure and content of a file.
Safe renaming
Rename a symbol and automatically update all references. This is an atomic operation that will automatically roll back in case of failure to ensure code consistency.
Project configuration information
Get the configuration information of a TypeScript project, including the path to tsconfig.json and the project root directory. Helps AI assistants understand the project structure.
Advantages
Accurate type checking: Based on the official TypeScript compiler, it provides the same accuracy as an IDE.
Complete code navigation: Supports complete IDE functions such as jumping, finding references, and outline views.
Safe renaming: Atomic operation ensures safe refactoring and automatically rolls back in case of failure.
High performance: Uses Go language and the native TypeScript compiler, with fast response.
Easy to integrate: Standard MCP protocol, can be integrated with any AI assistant that supports MCP.
Cross - platform support: Supports Windows, macOS, and Linux systems.
Limitations
Requires installation of dependencies: Requires Go 1.24+ and tsgo, increasing the complexity of initial configuration.
Only supports TypeScript: Specifically designed for TypeScript and does not support other languages.
Requires file system access: Needs to access the actual file path for analysis.
Memory usage: Large projects may require more memory.
Configuration requirements: Requires correct configuration of tsconfig.json to achieve the best results.

How to use

Install pre - dependencies
First, you need to install Go 1.24 or a higher version, as well as tsgo (TypeScript native compiler). tsgo can be installed globally via npm or run using npx.
Install the TypeScript MCP Server
Install typescript - mcp through the Go installation command or build it from the source code. After installation, ensure that the binary file is in the PATH or know its full path.
Configure the AI assistant
In AI assistants such as Claude Code or other MCP - supported ones, add the typescript - mcp server configuration. You need to specify the command path and parameters.
Start using
After configuration, the AI assistant can use the TypeScript analysis tools. It can request code diagnostics, jump to definitions, view type information, and other functions.

Usage examples

Edit - check - fix cycle
After modifying TypeScript code, use ts_diagnostics to check for type errors, fix the problems, and then verify again. This is a typical development workflow.
Code exploration and understanding
When an AI assistant needs to understand an unfamiliar codebase, it can use the symbol outline, jump to definitions, and view type information to quickly grasp the code structure.
Safe refactoring
When it is necessary to rename a widely used variable or function, using the ts_rename tool can ensure that all references are correctly updated, avoiding errors caused by manual modification.
Type information query
When writing code, an AI assistant may need to know the specific type of a function or variable in order to use them correctly.

Frequently Asked Questions

Why do I need to install tsgo? Can't typescript - mcp directly analyze TypeScript code?
Does this server support JavaScript files?
Will the ts_rename tool directly modify my files?
How to handle large TypeScript projects?
Can I use this server without Claude Code?
How to debug server issues?

Related resources

GitHub repository
Source code, issue tracking, and latest version of typescript - mcp
Model Context Protocol official website
Official documentation and specifications of the MCP protocol
tsgo project
Microsoft's TypeScript native Go compiler, the core dependency of typescript - mcp
TypeScript official website
Official documentation and tutorials of the TypeScript language
Claude Code documentation
Official documentation of the Claude Code AI programming assistant

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "typescript": {
      "command": "typescript-mcp",
      "args": []
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

V
Vestige
Vestige is an AI memory engine based on cognitive science. By implementing 29 neuroscience modules such as prediction error gating, FSRS - 6 spaced repetition, and memory dreaming, it provides long - term memory capabilities for AI. It includes a 3D visualization dashboard and 21 MCP tools, runs completely locally, and does not require the cloud.
Rust
10.7K
4.5 points
M
Moltbrain
MoltBrain is a long-term memory layer plugin designed for OpenClaw, MoltBook, and Claude Code, capable of automatically learning and recalling project context, providing intelligent search, observation recording, analysis statistics, and persistent storage functions.
TypeScript
9.2K
4.5 points
B
Bm.md
A feature-rich Markdown typesetting tool that supports multiple style themes and platform adaptation, providing real-time editing preview, image export, and API integration capabilities
TypeScript
15.1K
5 points
S
Security Detections MCP
Security Detections MCP is a server based on the Model Context Protocol that allows LLMs to query a unified security detection rule database covering Sigma, Splunk ESCU, Elastic, and KQL formats. The latest version 3.0 is upgraded to an autonomous detection engineering platform that can automatically extract TTPs from threat intelligence, analyze coverage gaps, generate SIEM-native format detection rules, run tests, and verify. The project includes over 71 tools, 11 pre-built workflow prompts, and a knowledge graph system, supporting multiple SIEM platforms.
TypeScript
8.9K
4 points
P
Paperbanana
Python
10.1K
5 points
B
Better Icons
An MCP server and CLI tool that provides search and retrieval of over 200,000 icons, supports more than 150 icon libraries, and helps AI assistants and developers quickly obtain and use icons.
TypeScript
9.8K
4.5 points
A
Assistant Ui
assistant - ui is an open - source TypeScript/React library for quickly building production - grade AI chat interfaces, providing composable UI components, streaming responses, accessibility, etc., and supporting multiple AI backends and models.
TypeScript
10.1K
5 points
A
Apify MCP Server
The Apify MCP Server is a tool based on the Model Context Protocol (MCP) that allows AI assistants to extract data from websites such as social media, search engines, and e-commerce through thousands of ready-to-use crawlers, scrapers, and automation tools (Apify Actors). It supports OAuth and Skyfire proxy payment and can be integrated into MCP clients such as Claude and VS Code through HTTPS endpoints or local stdio.
TypeScript
10.2K
5 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
39.4K
5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
28.7K
4.3 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
82.4K
4.3 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
24.2K
4.5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
38.6K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
71.2K
4.5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
24.2K
4.5 points
C
Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
108.3K
4.7 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase