Praison AI

AI Agents framework with 64+ built-in MCP tools for search, memory, workflows, code execution, and file operations. Install via `uvx praisonai-mcp`

GitHub

PraisonAI MCP Server

Downloads PyPI License MCP Registry

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

# Using uvx (Recommended)
uvx praisonai-mcp

# Using pip
pip install praisonai-mcp

Available Tools (64 Total)

🤖 Agent Tools (Primary)

The core tools for running AI agents:

ToolDescription
run_agentRun a PraisonAI agent with a prompt
run_researchDeep research on any topic
run_auto_agentsAuto-generate and run agents for a task
run_handoffRun task with agent handoff/delegation
generate_agents_yamlGenerate agents.yaml configuration

🔄 Workflow Tools

Orchestrate multi-step agent workflows:

ToolDescription
workflow_runRun a multi-step workflow
workflow_createCreate a new workflow
workflow_from_yamlCreate workflow from YAML
export_to_n8nExport workflow to n8n format

🌐 Search Tools (13 tools)

Unified web search with automatic fallback across multiple providers:

ToolDescription
search_webUnified search - Auto-fallback across providers
get_search_providersList available providers and their status
Tavily
tavily_searchAI-powered search (requires TAVILY_API_KEY)
tavily_extractExtract content from URLs
Exa
exa_searchSemantic search (requires EXA_API_KEY)
exa_search_contentsSearch with full content retrieval
exa_find_similarFind similar pages to a URL
You.com
ydc_searchAI search with LLM-ready snippets (requires YDC_API_KEY)
ydc_newsLive news search
Free Providers
duckduckgo_searchDuckDuckGo search (no API key)
wikipedia_searchWikipedia search
arxiv_searcharXiv academic papers
searxng_searchSelf-hosted SearxNG meta search

🕷️ Crawl & Scrape Tools

Web crawling and content extraction:

ToolDescription
crawl4ai_scrapeScrape webpage using Crawl4AI
crawl4ai_extractExtract structured data with Crawl4AI
scrape_pageScrape webpage and extract text
extract_linksExtract all links from a webpage
web_crawlCrawl website and extract content

📦 Supporting Tools

🧠 Memory & Knowledge

ToolDescription
memory_addAdd to memory store
memory_searchSearch memories
memory_listList all memories
memory_clearClear memories
auto_extract_memoriesAuto-extract memories from text
knowledge_addAdd to knowledge base
knowledge_searchSearch knowledge base

📋 Planning & Research

ToolDescription
plan_createCreate a plan for a goal
plan_executeExecute a plan step by step
deep_researchDeep research with iterations
analyze_repositoryAnalyze a repository
fast_context_searchSearch codebase for context

💻 Code & Execution

ToolDescription
run_pythonExecute Python code
run_shellExecute shell commands
git_commitCreate git commits
code_apply_diffApply SEARCH/REPLACE diff
code_search_replaceSearch and replace in file

📁 File Operations

ToolDescription
read_fileRead file contents
write_fileWrite content to file
list_directoryList directory contents
read_csvRead CSV file
write_csvWrite CSV file
read_json_fileRead JSON file
write_json_fileWrite JSON file
read_yaml_fileRead YAML file
write_yaml_fileWrite YAML file

🧮 Utilities

ToolDescription
calculateEvaluate math expressions
get_current_timeGet current date/time
solve_equationSolve math equations
convert_unitsConvert between units
calculate_statisticsCalculate statistics

📈 Finance

ToolDescription
get_stock_priceGet current stock price
get_stock_historyGet historical stock data

🖼️ Image & Query

ToolDescription
analyze_imageAnalyze image using vision
rewrite_queryRewrite query for better results
expand_promptExpand short prompt to detailed

✅ Task Management

ToolDescription
todo_addAdd task to todo list
todo_listList all tasks
todo_completeMark task as completed

💾 Session & State

ToolDescription
session_saveSave current session
session_loadLoad a saved session
session_listList all sessions

📜 Rules & Guardrails

ToolDescription
rules_listList all defined rules
rules_addAdd a new rule
rules_getGet a specific rule
guardrail_validateValidate content against rules

🖥️ System & Telemetry

ToolDescription
list_processesList running processes
get_system_infoGet system information
track_metricsTrack metrics event
get_metricsGet tracked metrics
select_modelSelect best model for task

🔌 MCP & Hooks

ToolDescription
mcp_list_serversList MCP servers
mcp_connectConnect to MCP server
hooks_listList available hooks
docs_searchSearch documentation

MCP Client Configurations

Claude Desktop

Config file: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS)

{
  "mcpServers": {
    "praisonai": {
      "command": "uvx",
      "args": ["praisonai-mcp"],
      "env": {
        "OPENAI_API_KEY": "your-openai-api-key",
        "TAVILY_API_KEY": "your-tavily-api-key"
      }
    }
  }
}

VS Code (GitHub Copilot)

Config file: .vscode/mcp.json

{
  "inputs": [
    {
      "type": "promptString",
      "id": "openai-key",
      "description": "OpenAI API Key",
      "password": true
    }
  ],
  "servers": {
    "praisonai": {
      "command": "uvx",
      "args": ["praisonai-mcp"],
      "env": {
        "OPENAI_API_KEY": "${input:openai-key}"
      }
    }
  }
}

Cursor

Config file: ~/.cursor/mcp.json

{
  "mcpServers": {
    "praisonai": {
      "command": "uvx",
      "args": ["praisonai-mcp"],
      "env": {
        "OPENAI_API_KEY": "your-openai-api-key"
      }
    }
  }
}

Windsurf

Config file: ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "praisonai": {
      "command": "uvx",
      "args": ["praisonai-mcp"],
      "env": {
        "OPENAI_API_KEY": "your-openai-api-key"
      }
    }
  }
}

Cline (VS Code Extension)

Open Command Palette → "Cline: MCP Servers" → Add:

{
  "mcpServers": {
    "praisonai": {
      "command": "uvx",
      "args": ["praisonai-mcp"],
      "env": {
        "OPENAI_API_KEY": "your-openai-api-key"
      }
    }
  }
}

Continue

Config file: ~/.continue/config.json

{
  "experimental": {
    "modelContextProtocolServers": [
      {
        "transport": {
          "type": "stdio",
          "command": "uvx",
          "args": ["praisonai-mcp"]
        }
      }
    ]
  }
}

Zed

Config file: ~/.config/zed/settings.json

{
  "context_servers": {
    "praisonai": {
      "command": {
        "path": "uvx",
        "args": ["praisonai-mcp"]
      }
    }
  }
}

Claude Code (CLI)

claude mcp add praisonai -- uvx praisonai-mcp

Environment Variables

VariableDescriptionRequired For
OPENAI_API_KEYOpenAI API keyAgent tools
TAVILY_API_KEYTavily search API keytavily_search, tavily_extract
EXA_API_KEYExa search API keyexa_search, exa_search_contents, exa_find_similar
YDC_API_KEYYou.com API keyydc_search, ydc_news
SEARXNG_URLSearxNG instance URLsearxng_search (optional)

Running as SSE Server

python -m praisonai_mcp --sse --port 8080

Links

License

MIT License

Servidores relacionados