MCP server directory

Local CI/CD engine for AI agents: listens to [LGH](https://github.com/JoeGlenn1213/lgh) git events and runs plugin jobs (Go/Python/Java/web toolchains) in isolated checkouts, with structured results, AI failure diagnosis, approval gates, auto-rollback, a web console, and 22 MCP tools including one-call `dev_cycle_run` (commit → CI → verdict). `brew install JoeGlenn1213/tap/actiond`

QQ MCP Server — connects to QQ via NapCatQQ (OneBot v11), giving AI agents direct control over QQ (send/receive messages, group management, auto-wake on incoming messages, and more).

Secure MCP server for safe, read-only DB access by AI agents, with SQL guardrails, table allowlists, PII masking, and audit logs.

Official MCP server for **EU VAT validation** via the EU Commission's VIES service + offline VAT rates for 45 European countries. Five tools: `validate_vat_number` (live VIES with company name, address, registration date, and optional consultation number for audit), `get_country_vat_rates`, `list_eu_vat_rates`, `check_vat_format`, `list_supported_countries`. Four of five tools work offline without an API key (data bundled via `eu-vat-rates-data`). Open source MIT, every release signed with npm provenance via GitHub Actions OIDC. Install: `npx -y vatnode-mcp`.

PHP static analysis MCP server for architecture and maintainability. 11 tools exposing 60+ code quality metrics, problem detection, refactoring priorities, dependency graphs, git hotspots, test coverage, and impact analysis. Installable via Composer.

Cross-border debt collection: check case status, read partner messages, get pricing, and submit collection cases handled by vetted local partners in 183 countries.

6 tools · cases, messages

Self-hosted coordination layer for AI agent fleets. Shared semantic memory, tasks, agent-to-agent messages, session handoffs, and a background archivist that synthesizes cross-agent knowledge. Any HTTP client participates — Claude Code, AutoGen, raw scripts.

Public Telegram channels without a user session: channel profiles, posts with view and forward counts, the discussion thread under a post, and the channels Telegram itself recommends.

Run your website's Asyntai AI support agent from any MCP client: manage the knowledge base, edit agent instructions, read conversations and leads, reply live to visitors and check plan usage.

📇 ☁️ 🏠 – A programming-focused task management system that boosts coding agents like Cursor AI with advanced task memory, self-reflection, and dependency management. [ShrimpTaskManager](https://cjo4m06.github.io/mcp-shrimp-task-manager)

Full-coverage MCP server for Instagram Graph API v25.0, Threads API & Meta platform — 57 tools for publishing, comments, insights, hashtags, DMs, and token management.

Ahrefs MCP lets AI agents securely access the Ahrefs API and enrich their answers with real Ahrefs data. MCP (Model Context Protocol) is a standard that allows AI tools to connect with third-party APIs in a secure, consistent way. In our case, it connects AI tools with Ahrefs, enabling things like this: Ahrefs provides a hosted MCP server that allows users with a Lite plan or higher to connect their Ahrefs account to supported AI tools. Once connected, your setup is synced and available across all devices linked to your personal or company account.

Persistent memory MCP server for AI coding agents (Claude Code, Codex, Gemini CLI). Hybrid retrieval (vector + BM25), cross-encoder reranking, knowledge graph with PPR traversal, session checkpoint/resume, and multi-scope isolation. Local-first with LanceDB + SQLite, zero external dependencies.

connects Jupyter Notebook to Claude AI, allowing Claude to directly interact with and control Jupyter Notebooks.

Link multiple data sources (SQL, CSV, Parquet, etc.) and ask AI to analyze the data for insights and visualizations.

Counterparty risk scoring for agentic commerce. Scores wallets, domains, IPs, and companies 0-100 via x402 micropayments. $0.01 USDC per request on Base.

LLM-agent-native backtest framework for SHFE daily futures research. 23 MCP tools (strategy validation, scaffolding, indicator catalog, error-code lookup), 22 in-package skills, 32 catalogued error codes, working strategy templates. `pip install echolon` then `claude mcp add -s user echolon -- echolon-mcp`.

Access the Global Legal Entity Identifier (LEI) database for company verification, KYC, and corporate ownership research via GLEIF's public API.

SEC EDGAR MCP for agents: search 10-K/10-Q, free sample preview, full filing JSON via x402 USDC on Polygon. xpay: `sec-edgar-filings`. Trial without xpay key: [docs](https://github.com/stagproject/sec-filings-mcp/blob/main/docs/TRY_WITHOUT_XPAY.md). Registry: `io.github.stagproject/sec-filings-mcp`.

> Create, run, and manage Superserve sandboxes from any MCP client. The Superserve MCP server (@superserve/mcp) exposes sandbox primitives as Model Context Protocol tools, so any MCP-capable client — Claude, Cursor, VS Code, Windsurf, Codex — can create sandboxes, run commands, read and write files, build templates, broker secrets, and control network access in an isolated Firecracker microVM. Run it two ways: locally over stdio via npx, or against the hosted endpoint at https://mcp.superserve.ai with no local install. Both authenticate with your SUPERSERVE_API_KEY and target a sandbox per call by ID. It's a thin wrapper over the TypeScript SDK, so the per-sandbox data-plane token never reaches the model.

5 tools · sandbox_create, sandbox_files_read

Sweepstakes management platform with 70 MCP tools for legally compliant promotions in the US and Canada. Manage participants, official rules, winner drawings, entry pages, billing, and more. Requires a [Sweeppea](https://www.sweeppea.com/) subscription.

Self-custodial crypto portfolio for AI agents. Reads EVM wallet balances, ENS, token prices, and DeFi positions across Ethereum/Arbitrum/Polygon/Base (Aave V3, Compound V3, Morpho Blue, Uniswap V3 LP, Lido, EigenLayer), surfaces health-factor alerts and protocol risk scores, then prepares unsigned transactions (supply, borrow, repay, withdraw, stake, send, LiFi swap/bridge) signed on Ledger via WalletConnect — private keys never leave the hardware wallet.

MCP server providing comprehensive Datadog observability access for AI assistants. Features grep-like log search, APM trace filtering with duration/status/error queries, smart sampling modes for token efficiency, and cross-correlation between logs, traces, and metrics.

Read jira data via JQL and api and execute requests to create and edit tickets.

A Model Context Protocol (MCP) server that queries multiple Ollama models and combines their responses, providing diverse AI perspectives on a single question.

> Note > > MCP integration is currently available only in the desktop Editor for Windows and macOS. You can connect the Rive Editor to AI tools through MCP (Model Context Protocol). The first set of tools are designed to let AI handle repetitive tasks, like creating complex View Models, State Machines with hundreds of states/layers, Layouts, Shapes, and more. Create and manage Rive files — add, rename, resize, arrange, and focus artboards. Inspect and edit the scene — query hierarchies, select objects, update properties, rename, duplicate, reorder, reparent, or delete elements. Build designs — create shapes, paths, layouts, component instances, component lists, and asset-based elements. Create animation and interaction — edit linear animations, state machines, states, transitions, conditions, keyframes, and interpolation. Work with data binding — create view models, properties, instances, bindings, and custom property groups. Edit scripts and shaders — manage Luau scripts and WGSL shad

6 tools · Build designs, Create and manage Rive files

Control Google Colab notebooks and assign GPUs (T4/L4/A100) from any AI agent. Enhanced fork of Google's colab-mcp with all tools visible at startup, OAuth GPU control, and Windows support.

Intelligent agent memory with semantic recall, automatic consolidation, contradiction detection, and bi-temporal knowledge graph. 80% on LOCOMO benchmark using 96% fewer tokens than full-context approaches.

MCP server exposing SSH control for Linux and Windows servers via Model Context Protocol. Securely execute remote shell commands with password or SSH key authentication.

AI agents read & send email, manage mailboxes, custom domains and webhooks via the QMailing API (npm stdio + hosted OAuth connector).

Self-evolving MCP server that generates and improves its own tools at runtime. Built on FastMCP, Janee uses LLM-driven tool generation to dynamically create, test, and refine MCP tools from natural language descriptions — enabling AI agents to extend their own capabilities on the fly.

BotIndex + Agorion MCP server — AI signal intelligence API + agent service discovery network. x402 payment gating on premium endpoints.

MCP server for Bosch eBike Flow (Smart System / BES3). Read-only, signs in with your own Bosch account via PKCE. Battery health and charge-cycle trends, components and firmware, live state-of-charge, and per-ride activity data (distance, elevation, power, assist-mode, CO2). Local SQLite cache with auto-sync.

The Travel Industry's First Remote MCP Server for AI Assistants Organizing the perfect trip used to be a lot of work, involving many hours of research. However, thanks to generative AI assistants, building the perfect, personalized itinerary has become a breeze. Today's AIs know everything about the city you're traveling to, its attractions, the quality of the hotels, and the hidden gems. Planning the best things to do has remained an elusive challenge. Listed experiences often have out-of-date descriptions or are out of season or already booked out.

4 tools · Build itineraries within time and budget constraints, Compare experiences by price and duration