Provides integration with Git for version control and project distribution through repository cloning
Hosts the project repository on GitHub, allowing for easy access and contribution to the codebase
Leverages Node.js as the runtime environment for the MCP server, enabling communication with client applications over standard input/output
Integrates with Nodemon for development mode, enabling automatic server restarts when code changes are detected for efficient tool testing
Uses npm for package management and provides scripts for building and running the server in different modes
Provides a server implementation in TypeScript for the Model Context Protocol, featuring strict type checking and well-documented code structure
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@TypeScript MCP Server calculate 15 * 3 + 7"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
This project is a simple Model Context Protocol (MCP) server built with TypeScript. It is designed to be a starting point for creating your own MCP servers and includes a basic calculator tool as an example.
The server is configured to communicate with a client application (like Cursor) over standard input/output (stdio).
MCP Server: Implements the Model Context Protocol standard via stdio.
Calculator Tool: A safe calculator tool that evaluates mathematical expressions.
TypeScript: Fully written in TypeScript with strict type checking.
Well-Documented: Code is documented, and a full SETUP.md is included.
Ready to Run: Includes npm scripts and a batch file for easy building and execution.
Related MCP server: MCP Montano Server
Clone the repository:
git clone https://github.com/KyleAnthonyMcAdam/Typescript-mcp.git
cd Typescript-mcpInstall dependencies: Run the following command in the project root to install all required packages.
npm installFor development, you can run the server using nodemon, which will automatically restart the server whenever you make changes to the source code. This is useful for testing tools without needing to connect to a full client.
npm run devFor the server to be used by a client application (like Cursor), you must first build the project.
Build the project:
This command compiles all TypeScript files from the src directory into JavaScript files in the dist directory.
npm run buildRun the server from a client: The server is not meant to be run directly by the user in the terminal. Instead, it must be started by an MCP client application.
To connect this server with a client like Cursor, you must add it to the client's configuration file (e.g., a global mcp.json). This configuration tells the client how to launch your server.
Crucially, the command or args in the configuration must use an absolute path to the launch script or server file. This path will be different on every machine.
For detailed instructions on how to set up the project from scratch and configure a client, please see the SETUP.md file.
run-server.batThis project includes a run-server.bat file which simplifies the process of running the server from a client on Windows. It ensures that the Node.js server starts with the correct settings.
Once the client is configured and connected, it can call the calculator tool with a request like this:
{
"jsonrpc": "2.0",
"method": "tool/run",
"params": {
"name": "calculator",
"arguments": {
"expression": "2 * (10 + 5)"
}
},
"id": "request-1"
}The server will respond with the calculated result.
A safe calculator that can evaluate mathematical expressions.
| Name | Required | Description | Default |
|---|---|---|---|
| expression | Yes | A mathematical expression to evaluate. Example: "2 * (3 + 4)" |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions 'safe' but doesn't elaborate on what that entails (e.g., error handling, security, or limitations). This leaves gaps in understanding the tool's behavior, such as how it handles invalid inputs or its operational constraints.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that directly states the tool's purpose without unnecessary words. It is front-loaded and appropriately sized, making it easy to understand quickly with zero waste.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's low complexity (one parameter, no annotations, no output schema), the description is minimally adequate. It covers the basic purpose but lacks details on behavior, usage context, or output format, which could be helpful for an AI agent to use it effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, with the parameter 'expression' documented as 'A mathematical expression to evaluate' and an example provided. The description adds no additional meaning beyond this, so it meets the baseline for adequate but not enhanced parameter semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose as 'evaluate mathematical expressions' with the verb 'evaluate' and resource 'mathematical expressions', making it specific and understandable. However, since there are no sibling tools mentioned, there's no explicit differentiation from alternatives, preventing a perfect score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, such as other calculation methods or tools. It lacks context about scenarios where it's appropriate, prerequisites, or exclusions, leaving usage unclear beyond the basic purpose.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.0.0calculatorWith only one tool, there is no possibility of ambiguity or overlap between tools. The single tool has a clear and distinct purpose, making it impossible for an agent to misselect between tools.
Since there is only one tool, naming consistency is inherently perfect. The tool name 'calculator' follows a clear noun-based pattern, which is appropriate for its function, and there are no other tools to compare it against for inconsistency.
A single tool is generally too few for a server's purpose, as it limits functionality and scope. While the tool is well-defined, the server likely lacks coverage for broader TypeScript-related tasks, making the count inappropriate for the implied domain.
The server is severely incomplete for a TypeScript domain, as it only offers a calculator tool with no other TypeScript-specific operations like code analysis, compilation, or linting. This represents a significant gap that will cause agent failures in handling TypeScript tasks.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
A Model Context Protocol server for Wix AI tools
The Mercado Pago MCP Server implements the Model Context Protocol to provide AI agents and LLMs with access to Mercado Pago's APIs and tools within compatible development environments. It acts as an intermediary that translates Mercado Pago resources into executable functions (tools) that AI applications can invoke to perform actions and automate flows. The server simplifies integration, enables using documentation to implement or improve code, and optimizes operations through natural language interactions without manual implementations.
Model Context Protocol server for the Apideck Unified API. Connect any MCP-compatible agent framework to 100+ accounting systems, HRIS platforms, file storage providers, and more through one integration. More information https://www.apideck.com/mcp-server
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/KyleAnthonyMcAdam/Typescript-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
