MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Agent Skills and an MCP server for GPU performance profiling, benchmarking, optimization, and reporting, with an inference focus.
MIT ★ 4 -
instrumentsmcpgithub.com/nemanjavlahovic/instruments-mcp-serverupdated this year
AI-native performance profiling for iOS and macOS apps. Profile while you use the app — start/stop recording, simulator control, scenario automation, all through Xcode Instruments via MCP.
npm MIT -
MCP server for Xcode Instruments — AI agents get structured performance profiling (CPU, SwiftUI, memory, hitches) instead of raw xctrace XML
MIT ★ 20 -
High-performance, modular MCP v2 server with safe-by-default profiles, Streamable HTTP, stdio, worker threads, metrics, and LRU caching
npm MIT -
MCP server for Google Business Profile — review performance, reply to reviews and publish location updates from an AI app
smithery -
MCP server for Google Business Profile: read reviews and performance, draft replies, score profile completeness for local SEO. Writes are off by default and need a single-use human approval token.
MIT -
MCP server for React Native runtime debugging — gives Claude access to logs, errors, network, state, storage, and performance profiling from your running app
MIT ★ 1 -
data-forge-mcpgithub.com/angrysky56/data-forge-mcpupdated this year
Data-Forge is a Model Context Protocol (MCP) server that transforms any LLM into a powerful Data Science Assistant. It provides a suite of high-performance tools for data loading, cleaning, validation, profiling, feature engineering, and visualization.
MIT ★ 2 -
MCP server for loading and analyzing V8 and Chrome CPU profiles for GitHub Copilot and other MCP clients
npm MIT -
@rog0x/mcp-perf-toolsgithub.com/rog0x/mcp-perf-toolsupdated this year
Performance analysis tools for AI agents via MCP
npm MIT -
crispy-profiling: React re-render profiler and snapshot tests. Finds unnecessary re-renders, explains why, and fails CI on regressions. CLI, MCP server and Agent Skill.
npm MIT -
Lightweight Android profiler and Layout Inspector in your browser, with MCP tools for AI agents
npm Apache-2.0 ★ 1 -
MCP server for analyzing Next.js React Profiler exports: render summaries, rerender causes, hot commits, and profile diffing
npm MIT -
Spectra — a Chrome DevTools Protocol profiler that identifies the files, functions and components causing frontend slowness, across React, Vue, Svelte, Angular and Next.js builds.
npm MIT -
Lightweight Android profiler and Layout Inspector in your browser, with MCP tools and an agent skill for AI agents: CPU, memory, frames, stalls, layouts, network and logcat over adb
npm Apache-2.0 -
Point it at a slow training run: it finds the bottleneck, tries the fixes, and keeps only speedups it can prove with the loss unchanged.
MIT -
A V8 deoptimization toolkit for AI agents and dev workflows: MCP server, findings engine, benchmark harness, and fix-verify comparison for inline caches, deopts, and hidden-class churn
npm MIT -
rhizophoragithub.com/punic-pillars/rhizophoraupdated this year
MCP server for React Native spatial integrity and layout audit. Provides Ground Truth for your component tree by detecting margin pollution, token deviations, bridge crossings, and render traps. 15 tools for structural analysis, layout auditing, performan
npm MIT -
On-demand .NET runtime diagnostics for live CoreCLR apps — no code changes. Ships an MCP server (let an LLM drive the investigation), a standalone CLI, and a BenchmarkDotNet diagnoser, all on one engine: counters, CPU/off-CPU/alloc sampling, heap & thread snapshots, GC/contention/threadpool events, dumps.
MIT ★ 27