Uniprof MCP Server

Universal CPU profiler designed for humans and AI agents

Local serverstdioPython

What is the Uniprof MCP server?

Universal CPU profiler designed for humans and AI agents. Exposed over MCP by the uniprof mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.

What it actually does

uniprof simplifies CPU profiling for humans and AI agents. Profile any application without code changes or added dependencies.

Its toolset

Everything the assistant can do here goes through one of these:

  • Platform — Profiler
  • Node.js0x
  • Rubyrbspy
  • PHPExcimer
  • JVMasync-profiler
  • BEAMperf
  • Compiler — DWARF Debug Info
  • gcc — gcc -g -o myapp main.c
  • clang — clang -g -o myapp main.cpp
  • swift — swiftc -g main.swift
  • cargo — cargo build (debug mode) cargo build --release + [profile.release] debug = true
  • zig — zig build-exe -O Debug main.zig

Adding it to your client

Installation goes through your MCP client rather than a global install: point it at uniprof on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

When to reach for it

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Uniprof's toolset — Platform, Node.js, Ruby and 10 more — is a fair guide to whether it matches your workflow. It is maintained by indragiek; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Uniprof's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 13 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Uniprof.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the uniprof mcp server does with a few real requests.

Available tools

ToolWhat it does
PlatformProfiler
Node.js[0x](https://github.com/davidmarkclements/0x)
Ruby[rbspy](https://github.com/rbspy/rbspy)
PHP[Excimer](https://github.com/wikimedia/mediawiki-php-excimer)
JVM[async-profiler](https://github.com/async-profiler/async-profiler)
BEAM[perf](https://perf.wiki.kernel.org)
CompilerDWARF Debug Info
gccgcc -g -o myapp main.c
clangclang -g -o myapp main.cpp
swiftswiftc -g main.swift
cargocargo build (debug mode) cargo build --release + [profile.release] debug = true
zigzig build-exe -O Debug main.zig
ghcghc -g -rtsopts main.hs

How to install the Uniprof MCP server

{
  "mcpServers": {
    "uniprof": {
      "command": "npx",
      "args": ["-y", "uniprof"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Uniprof to Platform.
  • Use Uniprof to Node.js.
  • Use Uniprof to Ruby.

Frequently asked questions

It connects Uniprof to MCP-compatible AI assistants such as Claude and Cursor, exposing 13 tools (Platform, Node.js, Ruby, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Uniprof directly.