affaan-m/ECC
ECC is a comprehensive agent harness performance optimization system providing skills, instincts, memory, security, and research-first development for various AI agent harnesses including Claude Co...
gotoolkits/mcp-difyworkflow-server
mcp-difyworkflow-server is a small MCP server written in Go that exposes Dify workflows as callable tools. Dify is a platform on which teams build LLM applications and workflows; this server sits between an MCP client and the Dify API server so that a model can discover which workflows are available and then run one with a given input, without the user opening the Dify interface. It supports several custom workflows at once and runs them on demand. The server is built from source with go build or the provided make build target, producing a single binary that can be referenced by absolute path in the client configuration or symlinked into a directory on PATH. Configuration follows the usual mcpServers block: the command points at the binary, the args carry a -base-url flag naming the Dify API server, typically something like http://localhost/v1, and two environment variables carry the workflow list. DIFY_WORKFLOW_NAME holds comma-separated workflow names and DIFY_API_KEYS holds the matching Dify application API keys; the two lists must correspond position by position, and each key is generated in Dify for the workflow it belongs to. The workflow names themselves are chosen by the user and are what the model refers to in a prompt. Two tools are published. list_workflows returns the workflows the server is authorised to run, letting the client see what is available. execute_workflow takes a workflow_name and an input and runs that workflow, returning its result. One constraint is documented: the input variable of the Dify workflow must be named message by default, otherwise the call will not bind. The README shows sample prompts in both English and Chinese for listing and invoking workflows.
https://github.com/gotoolkits/mcp-difyworkflow-server
Also in Agent Platforms
open-webui/open-webui
Open WebUI is a self-hosted, extensible AI platform supporting multiple LLM runners and OpenAI-compatible APIs with advanced features like Retrieval Augmented Generation, model building, and offline deployment.
Mintplex-Labs/anything-llm
AnythingLLM is an all-in-one AI application with full MCP compatibility that enables intelligent chat interactions with documents using various LLMs, multi-user support, and no-code AI agent building capabilities.
aaif-goose/goose
goose is an open-source, extensible AI agent providing desktop, CLI, and API interfaces for code, workflows, and general tasks, featuring broad LLM provider compatibility and connection to MCP exte...
HKUDS/nanobot
nanobot is an ultra-lightweight, open-source, self-hosted personal AI agent framework in Python, offering a WebUI, tools, memory, MCP integration, multi-agent workflows, automation, and chat app co...
zhayujie/CowAgent
CowAgent is an open-source, multi-model AI assistant and Agent Harness designed for autonomous task planning, tool execution, and continuous learning, featuring native Model Context Protocol (MCP) ...
sickn33/agentic-awesome-skills
This project provides an installable GitHub library and npm installer for over 1,900 agentic skills and playbooks, designed to enhance AI coding assistants like Claude Code, Gemini CLI, Cursor, and...
danny-avila/LibreChat
LibreChat is an open-source enhanced ChatGPT clone that integrates multiple AI models and supports the Model Context Protocol (MCP) for advanced AI assistant features including no-code agents, secure code execution, multimodal interactions, and customizable conversation management.