Query and Summarize chat messages with LLM. by mcpso

Automates API and MCP server creation from database schemas using LLMs, with PII protection, RLS, and multi-provider AI support.

sdk)

CodeMirror extension that implements the Model Context Protocol (MCP) for resource mentions and prompt commands

Access and editing data to your Google Sheets.

Deprecated integration enabling multi-language security scanning via stdio or streaming transport with Semgrep rules.

TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code) and Figma, allowing Agentic AI to communicate with Figma for reading designs and modifying them programmatically.

This MCP server enables LLMs to interact with the Solana blockchain with help of Solana Agent Kit by SendAI, allowing for 40+ protocol actions and growing

macOS-only automation toolkit delivering pixel-perfect screen capture, AI analysis, and complete GUI automation with multi-provider AI and native CLI integration.

Robust MCP server enabling Docker container creation, compose deployment, and logs via Claude AI integration.

Token-efficient access to local or remote OpenAPI/Swagger specs via MCP Resources.

A Model Context Protocol (MCP) server for the Open Library API that enables AI assistants to search for book and author information.

Learn it. Build it. Ship it for others.

Read and write access to NocoDB database.

High-performance, multi-format data extractor delivering code intelligence, OCR, and structured output across 91+ formats.

A Model Context Protocol server that provides AI assistants with accurate, real-time information about NixOS packages, system options, Home Manager settings, and nix-darwin macOS configurations.

Unified middleware gateway that aggregates multiple endpoints into a single configurable meta endpoint, with pluggable middlewares and OpenAPI exposure.

Interact with Tianji platform whatever selfhosted or cloud platform, powered by Tianji.

From a goal to a task DAG, automatically. TypeScript-native multi-agent orchestration with MCP and live tracing. Three runtime dependencies.

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.

754 structured cybersecurity skills for AI agents · Mapped to 5 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND & NIST AI RMF · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platforms · 26 security domains · Apache 2.0

Local-first knowledge graph built from Markdown notes, enabling persistent memory across conversations with LLMs.

Python framework for building autonomous and traditional agents with MCP tool integration, OCR support, prebuilt agents, and sandboxed execution.

Bridge between the protocol and Xero API enabling OAuth2 authentication, contacts, invoices, and chart of accounts management.