MervinPraison/praisonai-mcp

An MCP server that exposes PraisonAI AI agents and tools for use with Claude Desktop, Cursor, VS Code, Windsurf, and other MCP clients.
Features
- 🤖 **AI Agents as Tools** - Run PraisonAI agents directly from MCP
- 🔄 **Workflow Orchestration** - Multi-step agent workflows
- 🛠️ **64 Built-in Tools** - Complete coverage of all PraisonAI features
- ⚡ **Easy Setup** - Works with uvx or pip install
Installation
---
Available Tools (64 Total)
🤖 Agent Tools (Primary)
The core tools for running AI agents:
| Tool | Description |
|------|-------------|
| run_agent | Run a PraisonAI agent with a prompt |
| run_research | Deep research on any topic |
| run_auto_agents | Auto-generate and run agents for a task |
| run_handoff | Run task with agent handoff/delegation |
| generate_agents_yaml | Generate agents.yaml configuration |
🔄 Workflow Tools
Orchestrate multi-step agent workflows:
| Tool | Description |
|------|-------------|
| workflow_run | Run a multi-step workflow |
| workflow_create | Create a new workflow |
| workflow_from_yaml | Create workflow from YAML |
| export_to_n8n | Export workflow to n8n format |
---
🌐 Search Tools (13 tools)
Unified web search with automatic fallback across multiple providers:
| Tool | Description |
|------|-------------|
| search_web | **Unified search** - Auto-fallback across providers |
| get_search_providers | List available providers and their status |
| **Tavily** | |
| tavily_search | AI-powered search (requires TAVILY_API_KEY) |
| tavily_extract | Extract content from URLs |
| **Exa** | |
| exa_search | Semantic search (requires EXA_API_KEY) |
| exa_search_contents | Search with full content retrieval |
| exa_find_similar | Find similar pages to a URL |
| **You.com** | |
| ydc_search | AI search with LLM-ready snippets (requires YDC_API_KEY) |
| ydc_news | Live news search |
| **Free Providers** | |
| duckduckgo_search | DuckDuckGo search (no API key) |
| wikipedia_search | Wikipedia search |
| arxiv_search | arXiv academic papers |
| searxng_search | Self-hosted SearxNG meta search |
🕷️ Crawl & Scrape Tools
Web crawling and content extraction:
| Tool | Description |
|------|-------------|
| crawl4ai_scrape | Scrape webpage using Crawl4AI |
| crawl4ai_extract | Extract structured data with Crawl4AI |
| scrape_page | Scrape webpage and extract text |
| extract_links | Extract all links from a webpage |
| web_crawl | Crawl website and extract content |
---
📦 Supporting Tools
🧠 Memory & Knowledge
| Tool | Description |
|------|-------------|
| memory_add | Add to memory store |
| memory_search | Search memories |
| memory_list | List all memories |
| memory_clear | Clear memories |
| auto_extract_memories | Auto-extract memories from text |
| knowledge_add | Add to knowledge base |
| knowledge_search | Search knowledge base |
📋 Planning & Research
| Tool | Description |
|------|-------------|
| plan_create | Create a plan for a goal |
| plan_execute | Execute a plan step by step |
| deep_research | Deep research with iterations |
| analyze_repository | Analyze a repository |
| fast_context_search | Search codebase for context |
💻 Code & Execution
| Tool | Description |
|------|-------------|
| run_python | Execute Python code |
| run_shell | Execute shell commands |
| git_commit | Create git commits |
| code_apply_diff | Apply SEARCH/REPLACE diff |