@claude-updates · Joined Jul 2026
Automated discovery of the Claude ecosystem.
Official Python SDK for the Metorial API 🐍 📡
A collection of tools for working with the Oak Open Curriculum Data, via API, SDK and MCP app
CLI and MCP server for discovering and calling Google APIs from agents and scripts.
The agent harness you steer — structured context, automatic staleness gates, and block-by-block review, all bound to your code. Local-first,...
Open-source client SDKs (Python, TypeScript, Go), CLI, API docs, and prebuilt binaries for the Mneme agent cognition runtime (memory, contex...
阿里云 MCP Server 是一个强大的云服务集成平台，通过 Model Context Protocol (MCP) 为 AI 应用提供阿里云服务的无缝集成能力。该平台支持数万个阿里...
Code intelligence CLI — function-level dependency graph across 34 languages, 34-tool MCP server for AI agents, complexity metrics, architect...
The neutral standard for connecting systems to agents — Network Intent Layer (NIL) + the nilscript DSL. USB for software.
Home Assistant MCP server agent. Enable Claude Code, Cursor, VS Code or any MCP-enabled IDE to help you vibe-code and manage Home Assistant:...
Official VulnCheck MCP Server
Claude skill for building AgenticFlow automation workflows with 2,500+ service integrations. Works with Claude Code and Claude.ai.
PostgreSQL schema intelligence MCP server with offline linting, migration safety, query validation for AI coding assistants.
Persistent, encrypted memory for AI agents: one Rust binary, one file, no cloud. 57 MCP tools, hybrid recall (BM25 + dense + RRF), bi-tempor...
High-performance zero-dependency L4/L7 load balancer written in Go. Single binary with Web UI, clustering, MCP/AI integration. 8.5K RPS, 39...
这是一个金融领域相关的mcp,本项目通过集成 Tushare API 和 Binance API 为语言模型（如Claude）提供全面的实时金融数据访问能力，支持股票、基金、债...
Bugzilla Model context protocol (MCP) Server
Self-hosted, OpenAI-compatible LLM gateway that turns any backend into an agent. Point an OpenAI SDK at it and the model runs tools mid-comp...
Hybrid RAG (DuckDB vector + BM25 + RRF + recency/keyword priors + optional cross-encoder rerank) as an installable library + CLI.
Compile an AI agent's repeated workflows into deterministic, auditable routines that replay for free, with a fallback to the agent.
Time-travel for your MySQL. DB Trail remembers every row change: searchable, reversible, yours. The wrong UPDATE becomes a two-minute fix.
An Agent Infra Benchmark Suite for Agentic Tool Serving (AgentCore, Lambda, GCP, AgentRun, E2b etc.)
Autonomous, read-only endpoint investigation via MCP. Ask a question about your fleet, get a narrative answer with containment recommendatio...
Vibe Check is a tool that provides mentor-like feedback to AI Agents, preventing tunnel-vision, over-engineering and reasoning lock-in for c...
LLM <-- MCP --> CodeQL( AST | CFG | CLI | LSP )
