Packages

An open-core, self-improving code search platform that indexes codebases into vector embeddings and exposes semantic search via MCP servers. Uses ONNX embeddings, Qdrant vector DB, Redis cache, and an adaptive reranking system that learns from usage patterns. Provides two MCP endpoints: a memory server and an indexer server.

CLI tool and scaffolding generator that creates/extents production-ready Model Context Protocol (MCP) server projects (TypeScript) with prebuilt tools/resources/prompts and test workflows, plus commands to add additional components (tools, resources, prompts, services, transports, utils) to existing projects.

An intentionally vulnerable Model Context Protocol (MCP) server and companion web tools (inspector, dashboard, exfil listener) for security training: it simulates a fictional company with multiple departmental toolsets and challenge scenarios that demonstrate common attack classes (prompt/tool injection, SQL/command/path injection, privilege escalation, data exfiltration, TOCTOU, etc.).

Domscribe instruments supported frontend apps to map rendered DOM elements to stable source locations (AST-injected data-ds IDs and a manifest) and to enable agents to query live runtime context from the browser (props/state/DOM snapshots). It also provides a UI overlay for pointing at elements and sending UI-change annotations that agents can claim/implement via MCP.

EnrichMCP is a Python framework for building MCP (Model Context Protocol) servers that expose a semantic, type-safe data layer. It generates typed/discoverable tools from data models (e.g., SQLAlchemy models) or user-defined Pydantic schemas, supports relationships, validation, pagination, caching/context, and can serve over multiple transports (stdio by default, plus streamable HTTP).

mcpc (@apify/mcpc) is a universal CLI client for the Model Context Protocol (MCP) that exposes MCP server operations as intuitive shell commands, supports persistent sessions via a bridge process, and provides OAuth 2.1 (PKCE) and secure credential storage (OS keychain / fallback file). It can also output consistent JSON for scripting and includes a proxy mode for authenticated session access from AI “code mode” environments, with experimental x402 support for agentic payments.

Provides a local Model Context Protocol (MCP) server for the Perses application, allowing MCP-capable LLM hosts to manage Perses resources (projects, dashboards, datasources, roles, variables, plugins). Supports stdio (local) and HTTP (remote/shared) transports and can run in read-only mode.

An MCP server that uses Playwright to let an LLM agent automate a real browser: navigate to URLs, interact with page elements (click/hover/fill/select), run JavaScript in the page context, capture screenshots, and view browser console logs via MCP tools/resources.

Minecraft MCP Server is an MCP server that connects Claude Desktop to a Minecraft Java Edition world via the Mineflayer API, enabling AI-driven control of a Minecraft bot for building, exploration, inventory management, and in-game communication through natural language.

Oracle Cloud Agent MCP Server supports various integrations and management capabilities for cloud services.

phabricator-mcp is an MCP (Model Context Protocol) server that wraps Phabricator's Conduit API, exposing MCP tools for interacting with tasks (Maniphest), code reviews/diffs (Differential), repositories and file contents (Diffusion), users, projects, pastes, wiki (Phriction), blogs (Phame), transactions, uploads/files, builds (Harbormaster), owners, activity feed, chat threads (Conpherence), audits, and PHID lookup—via stdio MCP transport.

Provides an MCP (Model Context Protocol) server that bridges AI tool/service integrations to Portkey, exposing MCP tools for creating prompts, rendering prompts, and listing prompts via Portkey APIs. Supports both stdio and SSE (HTTP) transports.

Provides a local Model Context Protocol (MCP) server (FastMCP-based) that exposes ~108 reservoir engineering / petroleum engineering calculation tools by bridging AI agents (e.g., Claude Desktop) to the pyResToolbox library for tasks like PVT, well performance/IPR, nodal/VLP, DCA, material balance, geomechanics, brine properties, and related workflows.

Scout is an MCP server that enables AI clients to automate browser tasks: inspect page structure, find elements, execute user-like actions (click/type/navigate/scroll/etc.), run page JavaScript, capture screenshots/video, monitor network traffic, and export session workflows. It supports connecting either by launching its own browser session or via a Chrome extension “extension mode” to reuse an existing logged-in browser state. It also includes helpers for securely typing credentials from a server-side .env and retrieving 2FA OTP codes via Twilio.

Exports Zhihu collection(s) (public and private) to Markdown files, optionally downloading embedded images and producing Obsidian-compatible output. Includes a configurable MCP server (stdio-based) with tools to list collections, export a collection, get collection info, and search collections using a local config.

A MCP server for summarizing text

A QR code generation MCP server implemented using FastMCP, supporting text-to-QR code conversion with base64 encoding output.

4EVERLAND Hosting MCP Server Tool

[](https://smithery.ai/server/@aamangeldi/dad-jokes-mcp)

AI-powered multi-carrier shipping — ship packages, compare rates, track shipments through Claude and any MCP client