Packages

MCP server providing interactive visualizations: tables with TanStack Table, image previews, master-detail views, tree views for hierarchical data, and customizable lists

<div align="center">

VSCode extension that runs as MCP server to execute internal commands

Free accounting software API from Wave (H&R Block owned) offering invoicing, expense tracking, and basic accounting for freelancers and very small businesses. Notably uses GraphQL.

```bash

This is a Model Context Protocol (MCP) server that provides AFL (Australian Football League) data from the Squiggle API. It allows you to retrieve information about past AFL games, current and past standings, team information, power rankings, tips, and projections.

<div align="center">

CRIC物业AI MCP Server。CRIC物业AI 是克而瑞专为物业行业打造的智能 AI 助理。

[](https://smithery.ai/server/@xinkuang/china-stock-mcp)

AI Counsel is a self-hostable MCP server that runs multi-participant, multi-round “deliberation” among AI models to debate, cast structured votes with confidence/rationale, and converge on a decision. It can optionally ground decisions using evidence-based tools (read/search/list/run safe commands) against a provided working directory, includes transcript/audit outputs, and can reuse context via semantic retrieval of past debates.

MCP server that enables Claude and other MCP-compatible clients to query Audiense Insights accounts for marketing intelligence and audience analysis, including demographics, behavioral traits, influencer comparisons, and content engagement metrics.

MCP server (used via Crossplane/Intelligent Functions) that exposes tools to read Kubernetes pod events and pod container logs from a given namespace/pod (and optional container).

Cursor Feedback is a Cursor IDE extension plus an MCP server that provides an interactive human-in-the-loop feedback step. The Cursor AI agent calls an MCP tool (interactive_feedback), the extension shows a sidebar UI to collect user feedback (text/images/files), and the MCP server returns the feedback to the agent so it can continue within the same conversation.

gitnexus-stable-ops is a Python/Bash-based production ops toolkit that wraps the GitNexus CLI to keep code intelligence graphs reliable across multiple repositories. It provides diagnostic (doctor/smoke-test), safety-focused impact analysis with fallbacks, and automation scripts for smart and batch reindexing (including embedding preservation, dirty-worktree skipping, and version pinning). It also includes an agent-context graph index/query workflow to support agent swarms.

In Memoria is an on-machine (local-first) MCP server that learns from a codebase and exposes persistent “project blueprint” context, semantic/pattern search, file routing, and work-memory/pattern recommendations to AI coding assistants.

Middleware that bridges the OpenAI API with MCP tools, allowing developers to expose MCP tool capabilities through an OpenAI-compatible API endpoint. Supports streaming and non-streaming chat completions with MCP tool calls, SSE bridge for external clients, REST API endpoints for MCP primitives, and optional API key authentication.

Connects Google Search Console to Claude AI, giving SEO professionals conversational access to search analytics, URL indexing status, property management, and sitemap operations across their GSC properties.

Provides an MCP server exposing tools (add_memory, search_memory, delete_memory) backed by Mem0 for long-term memory storage and retrieval across LLM sessions. Supports three modes: Mem0 cloud, Supabase (self-host), and local/in-memory (dev).

monarch-mcp-server is a Python MCP server that connects an MCP-capable client (e.g., Claude Desktop/Claude Code) to the Monarch Money personal finance platform, exposing tools for accounts, transactions, budgets, cashflow, and investment holdings. It relies on an authentication setup script and persists an authenticated session locally for use by the MCP server.

NitroStack is a TypeScript framework/CLI for building production-ready Model Context Protocol (MCP) servers and AI-native backend apps. It provides decorator-driven tool definitions, dependency injection, authentication (JWT/OAuth2.1/API keys), middleware/guards/interceptors, validation via Zod, and a development/testing workflow (including NitroStudio and a widgets/UI layer for tool outputs).