# Polar Signals

MCP server for Claude Code, Cursor, GitHub Copilot, and other AI-powered editors that connects Polar Signals Cloud continuous profiling.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: docker
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/docker/mcp-registry/blob/98a203ca6e58c67031b8aaed037a26a07ec73ce3/servers/polar-signals/server.yaml
- Updated: 2026-10-29
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/polar-signals

## What it does

The server integrates with Claude Code, Codex, Cursor, GitHub Copilot, Windsurf, Cline, Zed, and Gemini CLI. It gives the AI assistant access to continuous profiling data—examining CPU allocation, memory patterns, and where your application burns resources inefficiently. Useful when you need to investigate why an application slows down or consumes excess memory without spinning up separate profilers.

Requires a Polar Signals Cloud account and API credentials. The server lives in your MCP configuration and becomes an analysis tool for the assistant—ask your AI helper where CPU time goes, and it pulls the profiles directly from the platform.

## Requirements
- Needs: Docker

## Install

### Claude Code (native platform)

**Install**
- The MCP registry has no launch command for it: see the repository README

## When to use it
- find CPU hotspots and performance bottlenecks in production
- identify which functions consume the most memory
- analyze performance profiles with AI assistance
- compare profiling data across application versions

## Example prompts
- Show me which parts of the code are burning the most CPU in production
- Which functions use the most memory? Check the profiles and tell me
- Analyze these profiles and suggest what to optimize first

## Similar
- [intel-vtune-amd-uprof](https://affpapa.org/en/nevibecode/skills/intel-vtune-amd-uprof.md) — skill · 559 installs
- [uniprof](https://affpapa.org/en/nevibecode/mcp/uniprof.md) — MCP server · ★ 409 repo stars
- [argent-react-native-profiler](https://affpapa.org/en/nevibecode/skills/argent-react-native-profiler.md) — skill · 32500 installs
- [cpu-pipelines-and-hazards](https://affpapa.org/en/nevibecode/skills/cpu-pipelines-and-hazards.md) — skill · 398 installs
- [metrics](https://affpapa.org/en/nevibecode/skills/metrics.md) — skill · 51 installs
- [CPU Performance Engineering](https://affpapa.org/en/nevibecode/mcp/cpu-performance-engineering.md) — MCP server · ★ 1160 repo stars

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
