Packages

NestJS module for building MCP servers that expose AI tools, resources, and prompts. Provides decorator-based API (@Tool, @Resource, @Prompt) with full NestJS dependency injection, multiple transport support (HTTP+SSE, Streamable HTTP, STDIO), Zod schema validation, per-tool authorization, and an optional built-in OAuth authorization server.

Official MiniMax MCP server (JavaScript) enabling AI agents to access MiniMax's multimodal AI capabilities — text-to-speech with voice cloning, speech-to-text, image generation, video generation, and music generation — integrating MiniMax's Chinese AI platform into agent-driven content creation workflows.

MCP server by OpenRPC maintainer shanejonas that enables AI agents to interact with OpenRPC-described JSON-RPC APIs — including Ethereum and other blockchain node APIs. Parses OpenRPC specification documents and generates dynamic MCP tools from the spec, enabling agents to call any JSON-RPC method defined in an OpenRPC document.

MCP server for Outline — the open-source team wiki and knowledge base — enabling AI agents to read and search Outline documents, create and update wiki pages, organize collections, and integrate team knowledge into agent workflows for documentation-aware assistance and knowledge management automation.

Power BI Desktop MCP server enabling AI agents to interact with Microsoft Power BI Desktop — querying report data, executing DAX queries, managing data models, retrieving visualizations, and integrating Power BI's business intelligence capabilities into agent-driven data analysis and reporting workflows.

Data validation and serialization library for Python using type annotations. Pydantic v2 rewrote the validation core in Rust (pydantic-core), making it 5-50x faster than v1. Define Python classes with type annotations, get automatic validation, serialization (model_dump, model_dump_json), JSON schema generation, and detailed error messages. The standard data modeling library for Python — used by FastAPI, LangChain, and thousands of other libraries.

ROS2 MCP server enabling AI agents to interact with Robot Operating System 2 (ROS2) — publishing and subscribing to ROS2 topics, calling ROS2 services, accessing robot sensor data and state, controlling robot actions, and integrating AI reasoning into ROS2-based autonomous robot and embedded systems workflows.

Customer Data Platform (CDP) that collects user events from any source and routes them to 400+ downstream destinations (analytics, marketing, data warehouses) without custom integrations.

MCP server for Semgrep — a popular open-source static application security testing (SAST) tool. Enables AI agents to run Semgrep security scans on codebases, apply custom rules, detect security vulnerabilities, check code patterns, and integrate SAST findings into AI-driven secure development workflows.

A Python MCP server that provides curated documentation access to AI coding assistants via llms.txt files, enabling intelligent search and retrieval with TF-IDF-based Markdown-aware ranking.

WHOIS MCP server enabling AI agents to perform domain and IP WHOIS lookups — querying domain registration information (registrar, registrant, creation/expiry dates, nameservers), IP address ownership (ASN, organization, abuse contacts), and network range data. Useful for network investigation, security research, threat intelligence, and domain monitoring workflows.

World Bank MCP server providing access to the World Bank's open data APIs — querying economic indicators, development statistics, country data, and global development metrics from the World Bank's comprehensive data catalog. Enables AI agents to access authoritative global economic, social, and development data for research, analysis, and policy work.

MCP server that enhances Claude's ability to solve complex programming tasks through structured step-by-step thinking, with thought branching, revision, and pre-built prompt templates for common development scenarios.

Full-featured Python testing framework — test discovery, fixtures, parametrize, plugins, and detailed failure reporting. pytest features: automatic test discovery (test_*.py files, test_* functions), assert introspection for detailed failure messages, @pytest.fixture for reusable test setup/teardown, @pytest.mark.parametrize for data-driven tests, conftest.py for shared fixtures, @pytest.mark for test categorization, pytest.raises() for exception testing, tmp_path/capsys/monkeypatch built-in fixtures, pytest-asyncio for async tests, pytest-cov for coverage, pytest-mock for unittest.mock integration, xfail/skip markers, and 1000+ plugins.

MCP server for Apple Mail on macOS using JavaScript for Automation (JXA) with FTS5 full-text search. Enables AI agents to read, search, send, and manage Apple Mail emails locally on macOS — with batch operations and fast full-text search over the local mail database. All operations are local, no external API required.

MCP server that integrates with Cursor IDE — the AI-first code editor — exposing Cursor's workspace state, active files, and editor context to MCP-based agents. Enables agent workflows to access Cursor project context, open files, and editor state to coordinate AI-assisted development across multiple agent tools.

MCP server for FreeCAD — the leading open-source parametric 3D CAD modeler. Enables AI agents to create and modify 3D models, manage parametric features, generate parts and assemblies, export design files, and integrate FreeCAD's powerful parametric modeling capabilities into AI-assisted engineering and design workflows.

Real-time image and video optimization CDN that automatically resizes, converts, and compresses media via URL parameters, with a REST API for asset management and transformation workflows.

Jenkins MCP server enabling AI agents to interact with Jenkins CI/CD — querying build status and history, triggering pipeline jobs, reading console output, managing plugins, and integrating Jenkins automation into agent-driven DevOps workflows for build monitoring and pipeline orchestration.

Lightweight MCP server for note-taking and note management. Enables AI agents to create, read, update, and organize notes — providing a simple local note store for capturing information, ideas, and context that agents can access and reference during conversations and workflows.