# AI Agents

Wren Engine is a semantic engine designed for MCP clients and AI agents, providing semantic layer support to enable AI to accurately understand enterprise data models and business logic. It supports multiple data sources and is embedded in MCP clients to ensure the accuracy and governance of data interaction.

Octagon MCP is an investment research tool that provides research capabilities for public and private markets by integrating the Octagon API, including functions such as financial data analysis, SEC filing parsing, and earnings conference call analysis.

This project manages the configuration rules of AI agents through the Cursor IDE, including rule editing and synchronization mechanisms, and is mainly applied to the workflows of professional agents and development agents.

This project provides a Dagster service interface based on the Model Context Protocol, enabling AI agents to interact with the Dagster data orchestration platform for data pipeline exploration, run monitoring, and asset management.

The Stripe Agent Toolkit is a toolkit that supports the integration of multiple AI agent frameworks (such as OpenAI, LangChain, CrewAI, etc.) with the Stripe API. It provides support for Python and TypeScript, simplifying payment-related operations.

Webflow MCP is a Node.js-based server that implements the Model Context Protocol (MCP), allowing AI agents to interact with the Webflow API through the Webflow JavaScript SDK.

The Solana Agent Kit is an open-source toolkit for connecting AI agents to the Solana protocol, supporting more than 60 blockchain operations.

Figma MCP Python is a tool that allows AI coding agents to directly access Figma files and prototypes, and supports quick integration into the development environment through MCP server configuration.

The Cheqd MCP Toolkit is a modular framework built around the Model Context Protocol (MCP) to standardize identity interactions for AI agents. It provides functions for securely managing decentralized identities (DIDs), verifiable credentials, and trust registries, and is a key component of AI-driven identity systems.

This project demonstrates how to use the Model Context Protocol (MCP) to integrate local and remote tools in the AutoGen framework, including a local mathematical calculation server and a remote Apify web browsing tool. It enables flexible interaction between AI agents and tools through a standardized protocol.

Agent MCP is an open-source project directory focusing on AI agent and MCP orchestration, providing functions to browse and search AI agent repositories, and supporting user authentication and search history saving.

A lightweight Model Control Protocol (MCP) server based on Cloudflare Workers for AI agents to interact with the Vercel API

Cloudera AI Agent Studio MCP Server is a lightweight model context protocol bridge service that can expose Agent Studio instances as a set of callable tools, supporting dynamic creation and management of workflows.

An MCP server connected to the Heurist Mesh API, providing access to blockchain and Web3 tools for Claude

The Nano Currency MCP Server is an MCP protocol server that provides Nano cryptocurrency transaction functions for AI agents, supporting sending Nano, querying account and block information.

The DBT CLI MCP Server is an AI coding agent service for interacting with dbt projects through standardized MCP tools

The Backlog MCP Server is a model context protocol server for interacting with the Backlog API, providing functions such as project management, issue tracking, and Wiki page management, and supporting operations on the Backlog platform through AI agents.

An MCP server collection specifically designed for Kali Linux, aiming to enhance the capabilities of AI agents in reverse engineering and security testing, providing functions such as network analysis, target sniffing, traffic analysis, binary parsing, and automation.

A Node.js client for integrating remote MCP servers to provide tool support for Voiceflow agents, supporting multiple tool discoveries and Claude AI integration.

AgentCraft is an enterprise-level AI agent framework that provides secure and scalable intelligent agent services.

The IOTA MCP Server is a comprehensive Model Context Protocol (MCP) server that provides blockchain services for IOTA and multiple EVM-compatible networks, with a particular focus on the integration of the IOTA ecosystem and AI systems. It supports more than 30 blockchain networks, providing a unified interface for AI agents to access blockchain data, interact with smart contracts, transfer tokens, etc., and includes features unique to IOTA such as staking and network status monitoring.

The OpenFGA MCP Server is an experimental Model Context Protocol service that enables large language models to read from and write to the OpenFGA authorization store, providing fine-grained permission management capabilities for AI agents and developers.

Canvas MCP is a set of tools that enables AI agents to interact with Canvas LMS and Gradescope, providing functions such as course resource query and assignment management.