typescript-sdk VS inspector

Model Context Protocol Documentation - Complete MCP reference Typescript SDK

View on GitHub

For TypeScript you can refer to https://github.com/modelcontextprotocol/typescript-sdk/blob/...

There isn't much documentation available right now but you can ask coding agent eg. Claude Code to generate an example.

@modelcontextprotocol/sdk: MCP server framework

At the time of this writing, this is little more than a proof of concept as a combination of the starter Pulsar package-generator package, the Atom package creation tutorial and the example from the official MCP Typescript SDK with some editor tool functions registered. Hopefully it will become more soon, since I am looking forward to actually using it to build stuff!

MCP TypeScript SDK

For this, we're going to use McpServer from the modelcontextprotocol SDK. The SDK supports: Resources, Tools, Prompts. However for this demo we'll only need tools.

Building a custom MCP server is straightforward with the right tools. While servers can be written in any language supporting stdout, official SDKs simplify the process. The TypeScript SDK is a great starting point.

For me it was implementing a simple `execute_terminal_command` tool along with hooking up to my company's jira and gitlab (dont worry security gurus, for the command line, I have a hardcoded list of allowed read-only commands that the LLM can execute, and both jira and gitlab servers likewise have readonly options.

What I will say is I agree there should be an option to get rid of the chat confirmations of every single new tool call in a chat - as well as building a set of "profiles" of different tools depending what I'm working on. Also strongly agree there needs to be an internal prompt possibility to explicitely tell the LLM what tool(s) to favor and how to use them (even in addition to the descriptions / schemas of the tools themselves) I opened an issue on the anthropic repo exactly about this: https://github.com/modelcontextprotocol/typescript-sdk/issue...

This will use npx to run the MCP inspector, a tool for testing and debugging MCP servers.

You can use the MCP inspector on GitHub for debugging and testing locally.

Learn more about the inspector here.

MCP Inspector is a valuable tool for debugging. It lets you test tools as if you were the LLM.

Thanks for the pointers! Will do. I've fired up https://github.com/modelcontextprotocol/inspector and the code looks helpful too.

I'm looking at integrating MCP with desktop app. The spec (https://spec.modelcontextprotocol.io/specification/basic/tra...) mentions "Clients SHOULD support stdio whenever possible.". The server examples seem to be mostly stdio as well. In the context of a sandboxed desktop app, it's often not practical to launch a server as subprocess because:

- sandbox restrictions of executing binaries

- needing to bundling binary leads to a larger installation size

Would it be reasonable to relax this restriction and provide both SSE/stdio for the default server examples?