mcpField
S
stacktrace-mcp

stacktrace-mcp

Local
github.com/antonybudiantoDeveloper Tools1Updated 76w ago

About stacktrace-mcp

stacktrace-mcp is a JavaScript stack trace MCP server for developers using bundles without source maps. It identifies the nearest location in a bundle URL so an LLM can check for a match in the current codebase.

Key features

  1. 01Locate errors from bundle URLs
  2. 02Support workflows without source maps
  3. 03Check locations against the codebase with an LLM

Use cases

  1. 01Investigate errors from a JavaScript bundle
  2. 02Relate a production stack trace to current code
  3. 03Use stack trace analysis in an MCP-supported app

MCP support

Exposes JavaScript stack trace location lookup to MCP clients. The server is configured over stdio in MCP-supported applications.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

stacktrace-mcp

Simple JS Stacktrace MCP for getting the nearest error location from JavaScript bundle URL and lets an LLM checks if it matches anything in the current codebase.

Designed for non-sourcemap users.

Getting started

  1. Clone the repo
  2. Run pnpm i for install
  3. Run pnpm build for building the server
  4. Add the local mcp server file path to your MCP-supported app (VSCode Copilot, etc):
    // settings.json
    "mcp": {
        "servers": {
        "stacktrace-mcp-server": {
            "type": "stdio",
            "command": "node",
            "args": [
                 "<your-path-to>\/stacktrace-mcp\/dist\/mcp_server.cjs"
            ]
        }
        }
    }
    
  5. Make sure the mcp tool is already enabled
  6. Copy your error stack trace to the prompt chat! That's it

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.