Skip to main content
Glama
123,617 servers. Updated
20 Best GitHub MCP Servers: compared and ranked, November 2026Ranked from 2,309 matching servers on stars, growth, downloads and maintenance. Updated .

Matching MCP tools:

Matching MCP Connectors:

"Official GitHub Website or Account" matching MCP servers:

GET /v1/servers – MCP directory API reference
  • A
    license
    Not graded
    quality
    B
    maintenance
    一个带有产品经理思维的 AI 建站策划工具。用户通过多轮对话澄清需求后,一键生成结构化的网站策划书,并自动输出三大 Mermaid 架构图(功能脑图、系统架构图、核心业务时序图)。同时支持按页生成现代风格的静态 HTML 概念稿。
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Enables fetching daily Product Hunt launches as dataset rows with maker names, product website and company domain, X and LinkedIn links, votes, rank, and topics. Users can filter by specific days or days back, topics, keywords, and minimum votes, or skip already-seen launches on a schedule.
    1
    118 npm
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Turns your AI host into a product videographer — scripted screen recordings of your own web app with a gliding cursor, camera zooms, highlight callouts, captions, and branded transitions, plus marketing-grade screenshots. Automatic dark-frame cleanup and MP4/GIF export. Free, MIT, 100% local — no account, no API keys.
    14
    83 npm
    3
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Read Layerdock website feedback in your coding agent. Each pin comes with the CSS selector, screenshot, page URL and the console and network trace captured when the client reported it. Fix the bug, reply on the thread and mark it resolved without leaving the editor. Works with Claude Code, Cursor, Codex CLI, Windsurf, VS Code, Zed and Antigravity.
    5
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Pre-build reality check for AI coding agents. Scans GitHub, Hacker News, npm, PyPI & Product Hunt in parallel — returns a 0-100 reality signal with real competitor data.
    1
    75 PyPI
    832
    MIT
  • F
    license
    A
    quality
    D
    maintenance
    An MCP server for accelerator programs to query, review, and manage startup applications via natural language. It enables searching applications by sector or impact score, fetching full application details with reviewer notes, listing pending reviews, and flagging applications for panel discussion.
    4
    -
  • A
    license
    A
    quality
    B
    maintenance
    Wildberries product analytics by article number with no account or API token: price, discount, rating, reviews, stock, delivery time, price history and competitor comparison. Optional seller tools via the official WB API (sales, orders, stocks, replies to reviews and questions).
    17
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Enables AI assistants to draft customer-ready or internal release notes from work closed in GitHub, Jira, or Linear, using deterministic fetching and rule-based categorization that flags uncertain items in a review list instead of guessing. Everything stays read-only, so a human approves and publishes the final notes.
    2
    1
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Enables reading release lifecycle status, recent written reviews and bulk monthly report CSVs for allowlisted apps, and searching the full pinned Play API catalog with each method's implementation status. Read-only by design, with keyless authentication, explicit app allowlists and bounded, GET-only access to official Google interfaces.
    6
    GPL 3.0
  • A
    license
    A
    quality
    B
    maintenance
    Enables customer-success teams and AI hosts to inspect account evidence, assess onboarding readiness, assemble unsent bilingual follow-up drafts, and prepare traceable technical handoffs through scoped MCP tools. It preserves source references and distinguishes recorded failures, missing evidence, and possible explanations for human review.
    8
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    MCP server that provides demand-signal scanning tools from GitHub, Hacker News, npm, and PyPI to validate digital-product and dev-tool ideas. Enables agents to query repo signals, trends, and download counts via stdio JSON-RPC.
    6
    1
    MIT
  • A
    license
    B
    quality
    B
    maintenance
    Guides product design through mandatory phases—discovery, definition, prioritization, flows, and verification—so an AI assistant can run a project from problem to verified scope, with strict or free progression modes.
    36
    170 npm
    3
    MIT
  • A
    license
    C
    quality
    C
    maintenance
    Enables goal-driven plan simplification by tracing each step's necessity, detecting cycles, broken links, and transitive waste, and classifying items as required or pointless with review and recheck capabilities.
    8
    Apache 2.0
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI assistants to create and validate surveys, distribute them, read and tag responses, and generate reports or exports through a hosted Streamable HTTP MCP endpoint with API-key authentication.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Build surveys, read responses and make reports in SurveyNinja from your AI assistant. Describe a survey in plain words, check it before launch and publish it, then read the responses, get a summary or an AI report and export the results to CSV, Excel, SPSS or PDF. Hosted server, sign in with OAuth or an API key; works on every plan, Free included.
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Official MCP server for FeatureJet, enabling agents to read and act on customer feedback boards: list/search posts, file feature requests, and pull top-voted planned items.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Lets agents read session replay and product analytics data: detected cases ranked by impact, session timelines and verdicts, grouped JavaScript and network errors, funnels, paths, retention, and natural-language session search. With the right scope, agents can also link pull requests, commits or issues to a case.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Official DSers MCP for AliExpress dropshipping, product sourcing, and order fulfillment. Discover products across AliExpress, Alibaba, and 1688; import them to connected Shopify, Wix, WooCommerce, and TikTok Shop stores; then edit listings, set prices, and publish. Manage supplier products and orders, coordinate fulfillment, and track shipments from your AI assistant.
    20
    Apache 2.0
  • A
    license
    Not graded
    quality
    B
    maintenance
    This stateless MCP server enables AI clients to analyze profiles, draft gigs and client replies, organize portfolio case studies, estimate pricing from supplied inputs, and review competitor observations without logging into or modifying Fiverr.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Connects MCP clients to a hosted experimentation platform so agents can start, pause, stop, and roll back live website A/B tests, inspect Bayesian results, and capture hypotheses.
    36 npm
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Official MCP server for Weft, an agent-first Scrumban board. Agents claim tasks with leases, report progress, and finish with receipts you accept or return from an Inbox. Hosted remote endpoint, OAuth 2.1, no API keys.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to query Mixpanel event data, funnel conversion rates, and retention cohorts via MCP tools or natural language.
    113 npm
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables retrieval of App Store and Google Play reviews, ratings summaries, and ASO keyword rankings for any app using its store ID or package name.
    81 npm
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    A task-management MCP server that enforces strict gates on task states, WIP limits, and closing reasons, refusing operations that would leave the list ambiguous or rotting.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables users to query complaint-velocity recall-risk signals for a named product, brand, or model, returning a 0–100 risk score and band with the complaint velocity, acceleration, and severe-hazard share behind it.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Lets agents put a five-second question to fifty verified real people and get the split back, with tools to estimate cost and timing before spending, ask and cancel questions, add more heads, page through individual answers, target audiences and countries, and export results as CSV, PDF, or PNG.
    108 npm
    1
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Connects an AI assistant to a dealer account so it can build and link a shop website that shows live vehicle stock and takes enquiries and test-drive bookings with no database to run. It also lets the assistant read and change listings, prices, test drives, reviews and leads in plain language, with read-only access by default and every change written to an audit log.
    35 npm
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to run a full QFD session over the Model Context Protocol: build and edit a House of Quality (stakeholder needs, measurable characteristics, relationship cells, trade-off roof, work items), validate it, and read back priorities, gates, the diagonal build order and item progress. It also exports the house as TSV, CSV, JSON, SVG or an Excel workbook, with optional file persistence so a person can keep editing where the agent left off.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables an AI agent to audit a website for launch readiness, find suitable startup/SaaS/AI directories using filters like DR and link type, and submit product listings to SaaSCity as drafts.
    60 npm
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Remote MCP server that lets AI assistants read tracked competitive intelligence — competitor news, reviews, website changes, social posts and ads — and act on it by managing projects, competitors, battle cards, reports and canvases. Every answer carries a source and a date, and write actions only publish when explicitly shared.
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables developers to list test drafts, active and completed tests, create unpaid test drafts, read tester feedback with ratings, voice timestamps and screen captures, and view account status, wallet credits and publisher profile through Testbay's REST API.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Connects Claude Code, Codex, Cursor, and other coding agents to a project's idea, feature topology, and ordered task queue over MCP, so they can answer planning jobs, claim, build, and tick off implementation tasks live in your repository, or assemble a shareable PRD.
    3 npm
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI agents to vet and rank product name candidates in batch by checking domain availability, App Store and Google Play collisions, exact-phrase web results, GitHub handles and repos, and trademark register lookups.
    1
    MIT
  • A
    license
    Not graded
    quality
    A
    maintenance
    Enables AI assistants to research topics, map and analyze codebases, curate development context, and generate product requirement documents, user stories, task lists, fullstack starter kits, and multi-step workflows. It runs as an MCP server over stdio or SSE, or as a CLI/REPL interface for natural-language software development tasks.
    42 npm
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables conversion of business briefs or authenticated saved projects into structured handoffs for the Lovable plugin, with both anonymous basic mode and authenticated full mode including knowledge base, SEO, WCAG, security, and roadmap guidance.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    An MCP server that lets AI agents report unanswered questions and submit knowledge corrections to a self-hosted feedback endpoint. Reports are grouped, deduplicated, and routed to documentation owners through an admin inbox, email, or signed webhooks.
    1
    Apache 2.0
  • A
    license
    Not graded
    quality
    C
    maintenance
    Bridges MCP clients such as Cursor, Claude Code and Claude Desktop to the Ascope server running locally on your Mac, so you can read App Store keyword rankings, popularity and difficulty scores, research or suggest keywords, and add, remove or refresh the apps and keywords you track. Everything stays on your machine with no API key required.
    72 npm
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    MCP server for Jama Connect that brings requirements, traceability, tests, and baselines into MCP clients like Claude, Cursor, VS Code, or GitHub Copilot, with access control, audit trail, and rate limiting. It provides 53 tools across 8 individually enableable toolsets, with an admin dashboard for managing access and usage.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables you to rehearse how a crowd would react to a pricing, launch, or policy change before shipping, by simulating persona reactions inside your existing coding agent and ranking the strongest objections by blast radius. Every claim in the resulting report traces back to the simulated post behind it, with deterministic replay and no API keys or network calls.
    Apache 2.0
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables querying an AI product landscape: look up products by name or URL for market, status and risk bands, browse a verified graveyard of shut-down or acquired products, and explore scored markets with their averages and top products.
    314 npm
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI assistants and developers to read, filter, compare, and summarize software reviews from G2, Capterra, TrustRadius, and Gartner Peer Insights through a hosted, read-only MCP connection with no review-site login or API keys.
    MIT
  • F
    license
    Not graded
    quality
    B
    maintenance
    Provides a local, agent-maintained product context layer over MCP, serving structured strategy, competitor, customer feedback, and feature inventory data to any AI tool such as Claude, Cursor, or ChatGPT, with local data storage, bring-your-own-LLM support, and weekly evidence-based roadmap reviews that can sync suggestions to Jira or Linear.
    -
  • F
    license
    Not graded
    quality
    C
    maintenance
    Enables coding agents to generate investor-grade business strategy artifacts — SWOT, Business Model Canvas, TAM-SAM-SOM, financial forecasts, pricing and competitive analyses — plus shareable investor decks from a single business idea, with built-in strategy chat and credit balance tools. All 8 tools are exposed over stdio MCP so agents can run research, generation, and deck creation themselves without a browser or human in the loop.
    44 npm
    1
    -
  • A
    license
    A
    quality
    B
    maintenance
    Enables agents to fetch app reviews from Apple's App Store and Google Play per country store, newest first, filtered by date or star rating, with each scheduled run returning only reviews not seen before. It also returns a per-app, per-country rating trend row with the current rating, rating count, change since the last run, and the star split of new reviews.
    1
    121 npm
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Enables agents to evaluate whether a product-adoption message is worth sending by applying a fixed, evidence-based rubric to a draft, recipient context, evidence, and the agent's own assessment, returning a send, revise, or hold recommendation with a score and reasons.
    2
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    Enables read-only queries across App Store Connect and Google Play from one toolset, letting users list apps, track release states, and review merged store feedback without extra dependencies or credentials in demo mode.
    5
    49 npm
    MIT