"Top 100 MCP Servers Ranked by Weekly Downloads" matching MCP servers:

An interactive coding agent and MCP server that provides access to various AI models via the Tsinghua University lab proxy API. It enables users to inspect files and execute shell commands within their local directory using models like DeepSeek, GLM, and Qwen.

Turn rough requests into rigorously structured prompts for any coding agent. Quality-scored to ≥90/100 across 12 dimensions, calibrated on 1,000+ real coding cases.

A TypeScript MCP server for launching, tracking, and managing external coding-agent runs across local and remote backends like Codex and Claude Code. It allows top-level agents to orchestrate subagents through tools for spawning tasks, polling events, and handling interactive sessions.

Enables finding existing shadcn-format UI components by plain-language description instead of exact names, returning ranked matches with install commands and per-dimension match reasons.

Enables multiple AI coding agents to collaborate on a project by coordinating tasks, file leases, and messages through a shared hub, preventing conflicts and enabling parallel development.

Enables MCP-capable assistants to build, preview, and publish full-stack web apps by directing a hosted coding agent, with tools for projects, wallet balance, domains, previews, downloads, and GitHub export.

Provides token-efficient code retrieval for coding agents by indexing repositories and enabling ranked snippet search, symbol outlines, and surgical line reads.

Let your memories live forever by passing your knowledge to the next generation with SelfMemory.

Read, inspect and navigate codebase symbols by connecting to a Language Server

Easily create custom reusable automation tools from casual browser actions using Apify Agent. Automate workflows by running your recorded actions turned into MCP tools.

Wraps FastContext-1.0 as a repo-exploration subagent for Claude Code, enabling efficient codebase navigation by returning file paths and line ranges as grounded citations, reducing main-agent token consumption by up to 60%.

A Spec-Driven Development toolkit that transforms LLMs into development agents by providing expert-crafted prompts for generating structured specifications and validating documents across the Requirements → Design → Tasks → Code workflow.

Enables launching Claude Code in a specified project directory by opening a new terminal session with optional initial prompt.

Enables AI coding agents to efficiently query code context via a symbol graph, reducing token usage by up to 20x.

Enables structured, step-by-step problem-solving through dynamic thinking processes that can be revised, branched, and adjusted as understanding deepens. Supports breaking down complex problems into manageable steps with the ability to revise previous thoughts and explore alternative reasoning paths.

Enables LLMs to apply Martin Fowler's 71+ refactoring patterns to codebases through a pluggable, language-agnostic architecture. Supports previewing and applying refactorings, analyzing code smells, and inspecting code structure with safe-by-default operations.

A Model Context Protocol (MCP) server that wraps the dbt CLI tool, enabling AI coding agents to interact with dbt projects through standardized MCP tools. Developed by Mammoth Growth.

MCP server that lets Claude Code, Codex or opencode hand coding work to cheaper models run by opencode.

AST-targeted code editing MCP server with 28 surgical tools for structural edits across 11 languages. Built on tree-sitter, replaces brittle search/replace with byte-correct edits keyed by symbol names.

Enables multiple AI agents to collaborate on the same git repository by coordinating work via a shared claims branch, detecting file conflicts before they happen.

Enables agents to autonomously resolve GitHub issues by editing code, running tests, and opening pull requests, while enforcing guardrails that protect critical files and systems.

Provides accurate, source-grounded breaking-change briefings for npm packages by reading real GitHub release notes and CHANGELOGs, helping coding agents avoid hallucinated dependency migrations.

Prevents coding agents from repeatedly attempting the same failed fix by tracking attempts and blocking further fixes until the agent uses its own web search tool.

Enables MCP clients like VS Code and Copilot Chat to drive the Freebuff coding agent from the editor, with persisted sessions, transcripts, and a safe read-only ask agent by default.

MCP server that runs JetBrains' ReSharper command-line tools for code inspection and cleanup, exposed to C# coding agents over stdio.

The IDE for agents — read by symbol, edit against a revision, validate with your own build, revert. It is a local stdio MCP server for coding agents. It reads code by symbol with tree-sitter and real language servers (Go, Java, Scala, TypeScript, Python, Rust, Ruby), edits against a known revision and returns compiler diagnostics with each edit, runs the repository's own build, test etc.

Enables Codex to use an installed Devin CLI as an additional worker by starting, polling, and cancelling bounded tasks through local MCP tools. It runs as a local stdio server in a given working directory, so jobs execute with the Devin account's model and permissions while Codex's own routing rules still decide when to delegate.

Enables coding agents to search and retrieve persistent repository memory created by Cliper, providing context, gaps, architecture, and timeline information via MCP tools.

Receives UI feedback captured by the PickFix browser extension—element picks, inline text rewrites, page comments, and recorded bug steps—and hands it to a local coding agent to fix in the current repository, with screenshots and per-item results reported back to the extension. It also pairs the extension per machine, queues batches so only one session claims each, and keeps everything loopback-only and untrusted.

MCP server that analyzes videos locally with frame-by-frame understanding and optional browser sidecars, producing structured context bundles for coding agents to fix bugs, add features, or build new functionality.