MCP servers for coding agents, picked by job

1. Rank 11

   Serena

   MCP server

   Gives a coding agent symbol-level code search, editing and refactoring tools backed by language servers

   Pick it if your agent spends many steps on grep and line-based edits in a large codebase and should look up symbols and references instead.

   • score 51
   • 30.3k stars
   • 53.1 stars/day since creation
   • pushed Oct 14
   • v2.0.0 on Oct 13
   • GPL-3.0-or-later

   Install with uv

   uv tool install -p 3.13 serena-agent

   Copy install command for Serena
   Use it when, skip it if, stats for Serena

   Why you'd want it

   Serena exposes IDE-style tools over MCP, such as find symbol, find referencing symbols, rename and replace symbol body, so the agent works with code structure instead of line numbers and text search. The default backend uses language servers, and the README lists support for over 40 programming languages. An optional paid JetBrains plugin backend adds moves, inlining, type hierarchy and searches in project dependencies.

   Best for

   • Navigating and refactoring large codebases
   • Cross-file renames and reference lookups
   • Multi-language repositories

   Use it when

   Your agent spends many steps on grep and line-based edits in a large codebase and you want it to look up symbols and references the way an IDE does.

   Skip it if

   Your projects are small and the agent's built-in search and edit tools already cope. It reports anonymous usage data on startup unless SERENA_USAGE_REPORTING is set to false, and its docs assume a trusted machine and repository and recommend a sandbox. The app moved from MIT to GPL-3.0-or-later in v2.

   Stats

   Stars

   30,271

   Last push

   Oct 14

   Release

   v2.0.0, Oct 13

   License

   GPL-3.0-or-later

   Pricing

   Open source

   Works with

   Any MCP client, Claude Code, Codex, Gemini CLI, VS Code, Cursor, JetBrains, Windsurf, Claude Desktop, Docker

   Stars per day, since repo creation

   53.1

   New and rising score

   51 of 100

   Full stat block for Serena

2. Context7

   MCP server Standard

   Pulls current, version-specific library docs and code examples into your agent's context

   Pick it if your agent keeps writing code against outdated or nonexistent APIs for the libraries you depend on. Requests go to the hosted Context7 API.

   • 63.1k stars
   • 111 stars/day since creation
   • pushed Oct 14
   • @upstash/[email protected] on Oct 13
   • MIT

   Run the setup CLI

   npx ctx7 setup

   Copy install command for Context7
   Use it when, skip it if, stats for Context7

   Why you'd want it

   Context7 targets outdated training data and hallucinated APIs by fetching documentation and code examples for the library and version you name in the prompt. Its MCP server has two tools: resolve-library-id maps a library name to a Context7 ID, and query-docs returns docs relevant to a question. It can also run without MCP as the ctx7 CLI plus an agent skill, and npx ctx7 setup configures either mode for Cursor, Claude Code or OpenCode.

   Best for

   • Coding agents working with fast-moving libraries
   • Pinning answers to a specific library version
   • Cursor and Claude Code users

   Use it when

   Your agent keeps writing code against outdated or nonexistent APIs for the libraries you depend on.

   Skip it if

   You need a fully self-hosted setup: only the MCP server and CLI are in the repo, and requests go to the hosted Context7 API, with low rate limits unless you add an API key. Library docs are community-contributed and Context7 does not guarantee their accuracy.

   Stats

   Stars

   63,053

   Last push

   Oct 14

   Release

   @upstash/[email protected], Oct 13

   License

   MIT

   Pricing

   Free tier + paid

   Works with

   Any MCP client, Claude Code, Claude Desktop, Codex, Cursor, Gemini CLI, VS Code, JetBrains, Zed, Docker

   Stars per day, since repo creation

   111

   Tier

   Standard, not ranked

   Full stat block for Context7

3. GitHub MCP Server

   MCP server Standard

   Connects agents to GitHub repos, issues, pull requests, Actions runs and security alerts

   Pick it if your agent needs to read or act on GitHub repositories, issues, pull requests or Actions runs as part of its task.

   • 33.6k stars
   • 57 stars/day since creation
   • pushed Oct 14
   • v2.0.2 on Oct 8
   • MIT

   Add the remote server to Claude Code

   claude mcp add-json github '{"type":"http","url":"https://api.githubcopilot.com/mcp","headers":{"Authorization":"Bearer YOUR_GITHUB_PAT"}}'

   Copy install command for GitHub MCP Server
   Use it when, skip it if, stats for GitHub MCP Server

   Why you'd want it

   GitHub's official MCP server lets an agent browse and search code, manage issues and pull requests, monitor Actions runs and review code scanning and Dependabot alerts. GitHub hosts a remote version at api.githubcopilot.com/mcp with OAuth or personal access token auth, and the same server runs locally from a Docker image or a Go binary. Tools are grouped into toolsets you can enable selectively, and a read-only mode removes every tool that makes changes.

   Best for

   • Agents that triage issues or review pull requests
   • Investigating CI failures from the editor
   • Teams that want a hosted server with OAuth

   Use it when

   Your agent needs to read or act on GitHub repositories, issues, pull requests or workflows as part of its task.

   Skip it if

   You do not use GitHub. Remote OAuth depends on each host configuring a GitHub App or OAuth App, so some clients need a personal access token, and GitHub Enterprise Server needs extra setup.

   Stats

   Stars

   33,623

   Last push

   Oct 14

   Release

   v2.0.2, Oct 8

   License

   MIT

   Pricing

   Open source

   Works with

   Any MCP client, Claude Code, Claude Desktop, Codex, Cursor, Gemini CLI, VS Code, JetBrains, Windsurf, Zed, Docker

   Stars per day, since repo creation

   57

   Tier

   Standard, not ranked

   Full stat block for GitHub MCP Server

1. Chrome DevTools MCP

   MCP server Standard

   Lets a coding agent control and inspect a live Chrome browser through DevTools

   Pick it if you want the agent to check its changes in a real Chrome instance and read console, network and performance data.

   • 53.6k stars
   • 134 stars/day since creation
   • pushed Oct 15
   • chrome-devtools-mcp-v1.10.1 on Sep 23
   • Apache-2.0

   Add to your MCP client config

   {
     "mcpServers": {
       "chrome-devtools": {
         "command": "npx",
         "args": [
           "-y",
           "chrome-devtools-mcp@latest"
         ]
       }
     }
   }

   Copy install command for Chrome DevTools MCP
   Use it when, skip it if, stats for Chrome DevTools MCP

   Why you'd want it

   It gives an agent the parts of Chrome DevTools a developer reaches for: recording performance traces with extracted insights, inspecting network requests, reading console messages with source-mapped stack traces and taking screenshots. Automation runs on Puppeteer and waits for action results automatically. A --slim mode trims the tool set for basic browser tasks, and a separate CLI works without MCP.

   Best for

   • Debugging front-end bugs with an agent
   • Performance analysis of web pages
   • Checking console and network errors after a code change

   Use it when

   You want your coding agent to check its changes in a real Chrome instance, reading console, network and performance data the way you would in DevTools.

   Skip it if

   You need Firefox or WebKit; only Chrome and Chrome for Testing are officially supported. Usage statistics go to Google by default (opt out with --no-usage-statistics), and performance tools may send trace URLs to the CrUX API unless you pass --no-performance-crux.

   Stats

   Stars

   53,560

   Last push

   Oct 15

   Release

   chrome-devtools-mcp-v1.10.1, Sep 23

   License

   Apache-2.0

   Pricing

   Open source

   Works with

   Any MCP client, Claude Code, Codex, Cursor, Gemini CLI, VS Code, JetBrains, Windsurf

   Stars per day, since repo creation

   134

   Tier

   Standard, not ranked

   Full stat block for Chrome DevTools MCP

2. Playwright MCP

   MCP server Standard

   Lets an agent drive a real browser with Playwright using accessibility snapshots, not screenshots

   Pick it if your agent needs to navigate, fill forms and inspect pages over many steps in one browser session.

   • 38.2k stars
   • 66.7 stars/day since creation
   • pushed Oct 8
   • v0.0.83 on Sep 28
   • Apache-2.0

   Add to Claude Code

   claude mcp add playwright npx @playwright/mcp@latest

   Copy install command for Playwright MCP
   Use it when, skip it if, stats for Playwright MCP

   Why you'd want it

   Microsoft's MCP server exposes Playwright browser automation as tools that act on structured accessibility snapshots, so no vision model is needed and actions avoid the ambiguity of screenshot-based clicking. It runs Chrome, Firefox, WebKit or Edge, headed or headless, can attach to your logged-in browser through the Playwright extension, and has opt-in capabilities for network, storage, DevTools, PDF, vision and test assertions. The README positions MCP for long-running loops that need persistent browser state, and points coding agents to the more token-efficient Playwright CLI with skills.

   Best for

   • Exploratory web automation by agents
   • Self-healing tests and long-running browser workflows
   • MCP clients without built-in browser control

   Use it when

   Your agent needs to navigate, fill forms and inspect pages across many steps while keeping the same browser session.

   Skip it if

   You use a coding agent and care about context size; Microsoft suggests Playwright CLI with skills for that. It is not a security boundary, so keep it away from sessions or data you would not hand to the model.

   Stats

   Stars

   38,158

   Last push

   Oct 8

   Release

   v0.0.83, Sep 28

   License

   Apache-2.0

   Pricing

   Open source

   Works with

   Any MCP client, Claude Code, Claude Desktop, Codex, Cursor, Gemini CLI, VS Code, Windsurf, Docker

   Stars per day, since repo creation

   66.7

   Tier

   Standard, not ranked

   Full stat block for Playwright MCP

1. Rank 16

   Apify MCP Server

   MCP server

   Lets an agent search Apify Store and run its ready-made scrapers and crawlers as MCP tools

   Pick it if an existing Apify Actor already scrapes the site you need and paying per run beats maintaining a scraper.

   • score 44
   • 11.3k stars
   • 17.3 stars/day since creation
   • pushed Oct 14
   • v0.18.2 on Oct 14
   • MIT

   Add the hosted server (OAuth)

   {
     "mcpServers": {
       "apify": {
         "url": "https://mcp.apify.com"
       }
     }
   }

   Copy install command for Apify MCP Server
   Use it when, skip it if, stats for Apify MCP Server

   Why you'd want it

   The server turns Apify Actors into MCP tools: the agent can search Apify Store, read an Actor's details, run it and page through the resulting dataset. By default it loads Actor search and calling tools, Apify docs search, and the RAG Web Browser and Web Fetch Actors. The hosted endpoint at mcp.apify.com signs in with OAuth, and a local stdio server runs through npx with an APIFY_TOKEN.

   Best for

   • Scraping social media, maps and search results
   • Agents that need structured web data
   • Teams already using Apify

   Use it when

   Your agent needs data from a site that an existing Apify Actor already scrapes and you would rather pay per run than maintain a scraper.

   Skip it if

   You want a free or offline tool: running Actors needs an Apify account, token or agentic payment and uses paid platform usage beyond the Free plan's monthly allowance. Telemetry on tool calls is on by default; the README documents how to turn it off.

   Stats

   Stars

   11,273

   Last push

   Oct 14

   Release

   v0.18.2, Oct 14

   License

   MIT

   Pricing

   Free tier + paid

   Works with

   Any MCP client, Claude Code, Claude Desktop, Cursor, VS Code, Web, Docker

   Stars per day, since repo creation

   17.3

   New and rising score

   44 of 100

   Full stat block for Apify MCP Server

2. Rank 32

   Firecrawl MCP Server

   MCP server

   Lets agents search, scrape, crawl and interact with web pages through Firecrawl, returning markdown or JSON

   Pick it if your agent needs content from known URLs, a whole site or a search query as markdown or JSON.

   • score 30
   • 7.6k stars
   • 11.2 stars/day since creation
   • pushed Oct 15
   • v3.2.1 on Sep 26, 2025
   • MIT

   Add the hosted server (OAuth sign-in)

   {
     "mcpServers": {
       "firecrawl": {
         "type": "http",
         "url": "https://mcp.firecrawl.dev/v2/mcp-oauth"
       }
     }
   }

   Copy install command for Firecrawl MCP Server
   Use it when, skip it if, stats for Firecrawl MCP Server

   Why you'd want it

   The server exposes Firecrawl scrape, map, crawl, search, parse, interact and agent tools, plus monitors for recurring page checks and a credit usage tool. A hosted endpoint works keyless for scrape, search and parse within rate limits, and signing in or adding an API key unlocks the full tool set. You can also run it locally with npx or Docker and point it at a self-hosted Firecrawl API with FIRECRAWL_API_URL.

   Best for

   • Turning URLs into clean markdown or schema-shaped JSON
   • Crawling many pages under one site
   • Pages that need a click before they can be read

   Use it when

   Your agent needs content from known URLs, a whole site or a search query, in a format it can read directly.

   Skip it if

   You want to drive a browser session step by step from your own client: each interact call runs to completion and returns control. Crawl, map and agent tools need a Firecrawl account or API key.

   Stats

   Stars

   7,607

   Last push

   Oct 15

   Release

   v3.2.1, Sep 26, 2025

   License

   MIT

   Pricing

   Open source

   Works with

   Any MCP client, Cursor, Windsurf, VS Code, Claude Desktop, Docker

   Stars per day, since repo creation

   11.2

   New and rising score

   30 of 100

   Full stat block for Firecrawl MCP Server

3. Rank 42

   Exa MCP Server

   MCP server

   Gives agents Exa web search and page fetching as MCP tools, with optional multi-step research runs

   Pick it if your agent needs web search and pages as clean markdown from a hosted server, with nothing to install.

   • score 21
   • 5.1k stars
   • 7.5 stars/day since creation
   • pushed Oct 7
   • MIT

   Install the Claude Code plugin

   claude plugin install exa@claude-plugins-official

   Copy install command for Exa MCP Server
   Use it when, skip it if, stats for Exa MCP Server

   Why you'd want it

   Exa hosts the server at mcp.exa.ai/mcp and it works without an API key under rate limits, so setup is a URL or a plugin install. The default tools are web_search_exa, which returns clean content for search results, and web_fetch_exa, which reads pages as markdown; advanced search with domain and date filters and Exa Agent runs for multi-step research can be turned on with the tools URL parameter. The repo also ships search and exa-agent skills that load with plugin installs.

   Best for

   • Coding agents that need current web results
   • Multi-step research and list-building
   • Improving built-in web search in Claude, ChatGPT or Codex

   Use it when

   Your agent needs to search the web or read pages as clean markdown and you want a hosted server with nothing to install.

   Skip it if

   You need more than light anonymous use: the keyless server is rate-limited, and Exa Agent requires OAuth or an Exa API key.

   Stats

   Stars

   5,130

   Last push

   Oct 7

   Release

   none tagged

   License

   MIT

   Pricing

   Open source

   Works with

   Any MCP client, Claude Code, Codex, Cursor, VS Code, Gemini CLI, Windsurf, Zed, Claude Desktop

   Stars per day, since repo creation

   7.5

   New and rising score

   21 of 100

   Full stat block for Exa MCP Server

1. Rank 24

   Supabase MCP Server

   MCP server

   Lets an AI assistant work with Supabase projects: tables, migrations, SQL, logs and Edge Functions

   Pick it if your app runs on Supabase and the agent should read schemas, run SQL, apply migrations or check logs. Supabase recommends project scoping and read-only mode.

   • score 39
   • 3k stars
   • 4.5 stars/day since creation
   • pushed Oct 14
   • mcp-server-supabase-v0.14.0 on Oct 14
   • Apache-2.0

   Add the hosted server to your MCP config

   {
     "mcpServers": {
       "supabase": {
         "type": "http",
         "url": "https://mcp.supabase.com/mcp"
       }
     }
   }

   Copy install command for Supabase MCP Server
   Use it when, skip it if, stats for Supabase MCP Server

   Why you'd want it

   Supabase hosts the server at mcp.supabase.com, so most clients need only the URL and an OAuth login to reach your projects. Tools are grouped into features (database, debugging, development, Edge Functions, account, docs, branching, storage) that you can restrict, and you can scope the server to one project or run it in read-only mode, where SQL runs as a read-only Postgres user. The npm package also exports tool schemas for the Vercel AI SDK MCP client and a handler for serving the tools from your own endpoint.

   Best for

   • Apps built on Supabase
   • Letting a coding agent inspect schemas and apply migrations
   • Debugging with project logs and advisors

   Use it when

   Your app runs on Supabase and you want the agent to read schemas, run SQL, apply migrations or check logs from your editor.

   Skip it if

   You do not use Supabase, or you cannot keep it away from production data: Supabase warns about prompt injection, recommends project scoping and read-only mode, and says not to give the server to your end users. The local CLI and self-hosted setups get only a subset of tools and no OAuth.

   Stats

   Stars

   2,952

   Last push

   Oct 14

   Release

   mcp-server-supabase-v0.14.0, Oct 14

   License

   Apache-2.0

   Pricing

   Open source

   Works with

   Any MCP client, Claude Code, Cursor

   Stars per day, since repo creation

   4.5

   New and rising score

   39 of 100

   Full stat block for Supabase MCP Server

2. Rank 29

   Stripe MCP and Agent Toolkit

   MCP server

   Lets agents call the Stripe API and search Stripe docs through a hosted MCP server or framework toolkits

   Pick it if you build on Stripe. Write tools act on a real Stripe account, so Stripe advises tool approval and restricted API keys.

   • score 32
   • 1.9k stars
   • 2.8 stars/day since creation
   • pushed Oct 15
   • MIT

   Add to Claude Code

   claude mcp add --transport http stripe https://mcp.stripe.com/

   Copy install command for Stripe MCP and Agent Toolkit
   Use it when, skip it if, stats for Stripe MCP and Agent Toolkit

   Why you'd want it

   Stripe hosts an MCP server at mcp.stripe.com with OAuth; its tools search, inspect, read and write Stripe API methods and search the Stripe docs, which makes much of the API reachable without loading every endpoint into context. Stripe requires human confirmation before some write actions, such as refunds and outbound payments. The stripe/ai repo also holds the Agent Toolkit for Python and TypeScript (OpenAI Agents SDK, LangChain, CrewAI, Vercel AI SDK), a local MCP package, billing integrations for the Vercel AI SDK and native OpenAI, Anthropic and Gemini SDKs, and Stripe agent skills and plugins.

   Best for

   • Products built on Stripe
   • Agent frameworks that need Stripe tools via function calling
   • Looking up Stripe docs while integrating

   Use it when

   You build on Stripe and want a coding agent or your own agent to query and change Stripe objects, or to answer integration questions from the Stripe docs.

   Skip it if

   You do not use Stripe. Write tools act on a real Stripe account, so Stripe advises turning on tool approval in your client and using restricted API keys to limit what the toolkit can do.

   Stats

   Stars

   1,943

   Last push

   Oct 15

   Release

   none tagged

   License

   MIT

   Pricing

   Open source

   Works with

   Any MCP client, Claude Code, Cursor, Codex, VS Code, Claude Desktop

   Stars per day, since repo creation

   2.8

   New and rising score

   32 of 100

   Full stat block for Stripe MCP and Agent Toolkit

3. Rank 35

   Framelink MCP for Figma

   MCP server

   Gives a coding agent the layout and styling data behind a Figma file, frame or group link

   Pick it if you build UI from Figma designs and want the agent to read the file data instead of a screenshot.

   • score 28
   • 16k stars
   • 26.2 stars/day since creation
   • pushed Oct 14
   • v0.13.2 on Jun 18
   • MIT

   Add to your MCP client config (macOS / Linux)

   {
     "mcpServers": {
       "Framelink MCP for Figma": {
         "command": "npx",
         "args": [
           "-y",
           "figma-developer-mcp",
           "--figma-api-key=YOUR-KEY",
           "--stdio"
         ]
       }
     }
   }

   Copy install command for Framelink MCP for Figma
   Use it when, skip it if, stats for Framelink MCP for Figma

   Why you'd want it

   Paste a Figma link into your agent's chat and the server fetches that design's metadata from the Figma API, then simplifies it to the layout and styling information before handing it to the model. The author's case is that this reduced, structured context lets the model implement designs more accurately than pasting screenshots. It runs locally through npx with your own Figma access token.

   Best for

   • Implementing Figma designs in code
   • Cursor users
   • Front-end work from design handoff

   Use it when

   You build UI from Figma designs and want the agent to read the actual file data instead of a screenshot.

   Skip it if

   You do not use Figma or cannot create a Figma personal access token. The README says it is designed specifically for Cursor, though the same config works in other MCP clients.

   Stats

   Stars

   15,988

   Last push

   Oct 14

   Release

   v0.13.2, Jun 18

   License

   MIT

   Pricing

   Open source

   Works with

   Any MCP client, Cursor, macOS, Linux, Windows

   Stars per day, since repo creation

   26.2

   New and rising score

   28 of 100

   Full stat block for Framelink MCP for Figma

4. Rank 40

   Sentry MCP Server

   MCP server

   Gives coding agents access to Sentry errors, issues, traces and performance data over MCP

   Pick it if your app reports to Sentry and the agent should pull issue details, errors and traces while it works on a fix.

   • score 24
   • 928 stars
   • 1.6 stars/day since creation
   • pushed Oct 15
   • [email protected] on Oct 5
   • FSL-1.1-Apache-2.0

   Add to Claude Code

   claude mcp add --transport http sentry https://mcp.sentry.dev/mcp/{organizationSlug}/{projectSlug}

   Copy install command for Sentry MCP Server
   Use it when, skip it if, stats for Sentry MCP Server

   Why you'd want it

   Sentry runs a remote MCP server at mcp.sentry.dev that uses OAuth and acts as middleware to the Sentry API, with tools chosen for debugging workflows in coding assistants rather than full Sentry coverage. You can scope the connection to one organization or project, which sets defaults and hides discovery tools. For self-hosted Sentry there is a stdio transport (npx @sentry/mcp-server) that takes a user auth token; its AI-powered search tools need an OpenAI, Azure OpenAI, Anthropic or OpenRouter key.

   Best for

   • Teams already on Sentry
   • Debugging production errors from the editor
   • Self-hosted Sentry via the stdio transport

   Use it when

   Your app reports to Sentry and you want the coding agent to pull issue details, errors and traces while it works on a fix.

   Skip it if

   You do not use Sentry. Sentry says it is not a general-purpose server for all Sentry functionality, and the stdio transport is still a work in progress.

   Stats

   Stars

   928

   Last push

   Oct 15

   Release

   [email protected], Oct 5

   License

   FSL-1.1-Apache-2.0

   Pricing

   Free

   Works with

   Any MCP client, Claude Code, Cursor, VS Code

   Stars per day, since repo creation

   1.6

   New and rising score

   24 of 100

   Full stat block for Sentry MCP Server

1. Rank 3

   agent-memory

   Memory

   Gives coding agents a shared long-term memory kept as plain Markdown files, with local ranked recall

   • score 70
   • 3.7k stars
   • 84.4 stars/day since creation
   • pushed Oct 14
   • MIT

   Install from a checkout with uv

   git clone https://github.com/tigerless-labs/agent-memory.git
   cd agent-memory
   uv sync --all-packages

   Copy install command for agent-memory
   Use it when, skip it if, stats for agent-memory

   Why you'd want it

   agent-memory keeps each memory as one Markdown file in a single store, with a SQLite index beside it that can be deleted and rebuilt at any time. Recall runs locally and returns a ranked list of paths with one-line abstracts, so the agent opens only what it needs, and Claude Code, Codex CLI and Muse Code can share the same store. Hooks write memories at conversation boundaries, and a separate sleep-time pass consolidates them, with deletions only arriving as proposals you confirm. It needs no API key of its own and borrows judgement from the host agent's CLI.

   Best for

   • Memory shared between Claude Code and Codex
   • Memory you can grep and keep in git
   • Agents that forget between sessions

   Use it when

   You want an agent to remember decisions across sessions and prefer a store you can read, grep and commit over an opaque database.

   Skip it if

   You want a packaged install: there is no PyPI release yet, so it installs from a git checkout with uv, and the repo was created on 2026-09-01. Setup writes lifecycle hooks into your agent's settings and runs the host agent's CLI headlessly to distil and consolidate memories.

   Stats

   Stars

   3,655

   Last push

   Oct 14

   Release

   none tagged

   License

   MIT

   Pricing

   Open source

   Works with

   Claude Code, Codex, Any MCP client

   Stars per day, since repo creation

   84.4

   New and rising score

   70 of 100

   Full stat block for agent-memory

2. Rank 8

   Hex-Rays IDA MCP

   MCP server

   Connects an agent to IDA to open, analyse and script binaries, headless or in the IDA GUI

   • score 56
   • 1.2k stars
   • 23.8 stars/day since creation
   • pushed Oct 8
   • v20261008.0.1 on Oct 8
   • MIT

   Install with Hex-Rays hcli

   uvx ida-hcli mcp install

   Copy install command for Hex-Rays IDA MCP
   Use it when, skip it if, stats for Hex-Rays IDA MCP

   Why you'd want it

   This is the official Hex-Rays MCP server for IDA, built on the ida-nexus library, which lets several clients share IDA databases. Its tools open, list, save and close databases and run Python inside IDA, so the agent works through the IDA API, and a GUI plugin lets it see what you have open while headless use works without it. It ships plugins for Claude Code, Codex CLI, Copilot CLI, Pi and oh-my-pi, a stdio or Streamable HTTP server for other agents, and a dashboard of session logs.

   Best for

   • Reverse engineering binaries with an agent
   • Scripting IDA analysis through Python
   • Teams already using IDA 9.4+

   Use it when

   You reverse engineer in IDA and want your agent to open a sample, run analysis and answer questions about it, or to work on the database you have open in the GUI.

   Skip it if

   You do not have IDA 9.4 or later with idalib and Python 3.11+. The agent runs Python inside IDA, and sessions are logged locally with links to agent transcripts; Hex-Rays recommends disabling other IDA MCP servers.

   Stats

   Stars

   1,159

   Last push

   Oct 8

   Release

   v20261008.0.1, Oct 8

   License

   MIT

   Pricing

   Open source

   Works with

   Claude Code, Codex, Any MCP client

   Stars per day, since repo creation

   23.8

   New and rising score

   56 of 100

   Full stat block for Hex-Rays IDA MCP

3. Rank 9

   Browser Harness

   Browser agent

   Lets Claude Code, Codex or Cursor drive your own Chrome over CDP, logged in as you

   • score 53
   • 18.4k stars
   • 102 stars/day since creation
   • pushed Oct 15
   • v0.1.13 on Sep 4
   • MIT

   Install with uv

   uv tool install --python 3.12 --upgrade --force browser-harness

   Copy install command for Browser Harness
   Use it when, skip it if, stats for Browser Harness

   Why you'd want it

   Browser Harness connects a coding agent to your running Chrome through the DevTools Protocol, so it can open pages, click, type, read and download with your existing logins. It installs as a CLI with a skill that teaches the browser workflow, and the agent writes missing helpers into its local workspace as it works while the core package stays protected. A browser-harness-mcp command exposes the same helpers as MCP tools for any MCP client.

   Best for

   • Logged-in web tasks from a coding agent
   • Claude Code, Codex and Cursor
   • MCP clients that need a real browser

   Use it when

   You want your coding agent to work in the browser where you are already signed in, instead of a fresh headless profile.

   Skip it if

   You do not want an agent acting in your real, logged-in browser profile: setup turns on Chrome remote debugging, and the agent acts as you on the sites you use. Optional local recordings save screenshots and action traces that may include sensitive page content.

   Stats

   Stars

   18,433

   Last push

   Oct 15

   Release

   v0.1.13, Sep 4

   License

   MIT

   Pricing

   Open source

   Works with

   Claude Code, Codex, Cursor, Any MCP client

   Stars per day, since repo creation

   102

   New and rising score

   53 of 100

   Full stat block for Browser Harness

4. Rank 19

   Godot AI

   MCP server

   Connects Claude Code, Codex and other MCP clients to a live Godot editor to build scenes, nodes and scripts

   • score 42
   • 3k stars
   • 16.1 stars/day since creation
   • pushed Oct 14
   • v4.3.0 on Oct 3
   • MIT

   Download, no command

   Download a release into addons/godot_ai, then enable the plugin
   Use it when, skip it if, stats for Godot AI

   Why you'd want it

   Godot AI is a Godot editor plugin plus a Python MCP server; the README lists 46 tools and 120+ operations to build scenes, edit nodes and scripts, wire signals and configure UI, materials, animation, particles, cameras and environments. GDScript written through the tools is parse-validated, hot-reloaded and attached, while C# support is text-only. A dock inside Godot shows the connection and has a Configure button that writes the client entry for Claude Code, Claude Desktop, Codex, Cursor, VS Code and others.

   Best for

   • Building Godot scenes from prompts
   • GDScript projects in Godot 4.7+
   • Running a game's scene tests from an agent

   Use it when

   You build games in Godot 4.7 or later and want your agent to read and change the open project in the editor instead of editing .tscn files blind.

   Skip it if

   You work mainly in C#, which is text-only (it does not build .NET or report compiler errors), or you are on Godot older than 4.7. Usage telemetry is on unless GODOT_AI_DISABLE_TELEMETRY=true is set, and the agent gets write access to the open project.

   Stats

   Stars

   2,988

   Last push

   Oct 14

   Release

   v4.3.0, Oct 3

   License

   MIT

   Pricing

   Open source

   Works with

   Claude Code, Claude Desktop, Codex, Cursor, VS Code, Any MCP client

   Stars per day, since repo creation

   16.1

   New and rising score

   42 of 100

   Full stat block for Godot AI

More guides

• Open-source coding agents compared
• Claude Code alternatives, by what you need instead
• AI agent frameworks compared
• Agent observability and eval tools
• Category: MCP servers