Pprof Analyzer
This is a Model Context Protocol (MCP) server implemented in Go, providing a tool to analyze Go pprof performance profiles.
What is Pprof Analyzer?
Pprof Analyzer is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to this is a model context protocol (mcp) server implemented in go, providing a tool to analyze go pprof performance profiles.
This is a Model Context Protocol (MCP) server implemented in Go, providing a tool to analyze Go pprof performance profiles.
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- This is a Model Context Protocol (MCP) server implemented in
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx pprof-analyzerConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Pprof Analyzer
The Pprof Analyzer MCP Server is a Go-based MCP server that brings Go performance profiling directly into your AI assistant workflow. It can parse local or remote pprof profile files (CPU, heap, goroutine, allocs, mutex, and block profiles), generate SVG flame graphs, detect memory leaks by comparing heap snapshots, and compare two profiles to surface regressions—all through natural language requests in an MCP client. Engineers debugging Go application performance no longer need to run separate pprof CLI commands; they can ask their AI assistant to analyze profiles and get structured Markdown or JSON summaries inline.
Prerequisites
- Go 1.21 or later installed (required to build or install the server binary)
- Graphviz (the `dot` command) installed for SVG flame graph generation: `brew install graphviz` on macOS or `sudo apt-get install graphviz` on Debian/Ubuntu
- An MCP-compatible client such as Claude Desktop, Cursor, or VS Code with MCP support
- Go pprof profile files (.pprof) accessible via local file paths or HTTP/HTTPS URLs
Install the server binary via go install
The recommended installation method fetches and builds the latest release directly into your Go bin directory, making the binary available system-wide.
go install github.com/ZephyrDeng/pprof-analyzer-mcp@latestVerify the binary is in your PATH
Confirm that $(go env GOPATH)/bin is in your PATH, then verify the binary is reachable.
export PATH=$PATH:$(go env GOPATH)/bin
pprof-analyzer-mcp --versionAdd the server to your MCP client config
Register the pprof-analyzer-mcp binary as an MCP server in your client's configuration file. No environment variables are required for basic use.
{
"mcpServers": {
"pprof-analyzer": {
"command": "pprof-analyzer-mcp"
}
}
}Alternatively, run via Docker
If you prefer not to install Go locally, build and run the server as a Docker container.
docker build -t pprof-analyzer-mcp https://github.com/ZephyrDeng/pprof-analyzer-mcp.git
# Then in your MCP config:
# "command": "docker", "args": ["run", "-i", "--rm", "pprof-analyzer-mcp"]Restart your MCP client and collect a pprof profile
Restart the client so it picks up the new server. Use the standard Go pprof HTTP endpoint or go test to capture a profile file to analyze.
# Capture a 30-second CPU profile from a running Go server:
curl -o cpu.pprof http://localhost:6060/debug/pprof/profile?seconds=30
# Capture a heap profile:
curl -o heap.pprof http://localhost:6060/debug/pprof/heapPprof Analyzer Examples
Client configuration
Minimal MCP client config using the installed binary. For Docker, replace command/args as shown in the comment.
{
"mcpServers": {
"pprof-analyzer": {
"command": "pprof-analyzer-mcp"
}
}
}Prompts to try
Use natural language to invoke the analyzer tools. Provide the full file path or a reachable URL to the .pprof file.
- "Analyze the CPU profile at file:///tmp/cpu.pprof and show the top 10 hotspots in Markdown"
- "Generate a flame graph SVG from file:///tmp/heap.pprof and save it to /tmp/heap_flame.svg"
- "Compare the CPU profiles at file:///tmp/before.pprof and file:///tmp/after.pprof to find regressions"
- "Detect memory leaks by comparing file:///tmp/heap_before.pprof and file:///tmp/heap_after.pprof"
- "Analyze the goroutine profile at https://myservice.internal/debug/pprof/goroutine"Troubleshooting Pprof Analyzer
'pprof-analyzer-mcp: command not found' after go install
The Go bin directory is not in your PATH. Add `export PATH=$PATH:$(go env GOPATH)/bin` to your shell profile (~/.zshrc or ~/.bashrc) and reload with `source ~/.zshrc`.
Flame graph generation fails with 'exec: dot: executable file not found in $PATH'
Graphviz is not installed. Install it with `brew install graphviz` on macOS, `sudo apt-get install graphviz` on Debian/Ubuntu, or `sudo yum install graphviz` on CentOS/Fedora.
analyze_pprof returns an error for a remote profile URL
Ensure the URL is reachable from the machine running the MCP server. For Go services, the pprof HTTP handler must be enabled: import _ "net/http/pprof" and ensure the HTTP server is listening on a reachable address.
Frequently Asked Questions about Pprof Analyzer
What is Pprof Analyzer?
Pprof Analyzer is a Model Context Protocol (MCP) server that this is a model context protocol (mcp) server implemented in go, providing a tool to analyze go pprof performance profiles. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Pprof Analyzer?
Follow the installation instructions on the Pprof Analyzer GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Pprof Analyzer?
Pprof Analyzer works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Pprof Analyzer free to use?
Yes, Pprof Analyzer is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Pprof Analyzer Alternatives — Similar Developer Tools Servers
Looking for alternatives to Pprof Analyzer? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Browse More Developer Tools MCP Servers
Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Pprof Analyzer in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Pprof Analyzer?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.