Praisonai MCP Server

An MCP server that exposes [PraisonAI](https://github.com/MervinPraison/PraisonAI) AI agents and tools for use with Claude Desktop, Cursor, VS Code

Remote serverstreamable-httpPython

What is the Praisonai MCP MCP server?

An MCP server that exposes PraisonAI AI agents and tools for use with Claude Desktop, Cursor, VS Code, Windsurf, and other MCP clients. That is what the praisonai mcp mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

  • 🤖 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

Getting it running

Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.

The tools it exposes

The server publishes 14 tools. What each one is for:

  • 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_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_webUnified search - Auto-fallback across providers
  • get_search_providers — List available providers and their status
  • Tavily — The Tavily tool exposed by this server

What it needs from you

Configuration is passed through the environment: OPENAI_API_KEY, TAVILY_API_KEY, EXA_API_KEY, YDC_API_KEY, SEARXNG_URL. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Things to watch

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Praisonai MCP.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

How it compares

Plenty of planning and project tracking servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Praisonai MCP's toolset — run_agent, run_research, run_auto_agents and 11 more — is a fair guide to whether it matches your workflow. It is maintained by mervinpraison; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Available tools

ToolWhat it does
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_runRun a multi-step workflow
workflow_createCreate a new workflow
workflow_from_yamlCreate workflow from YAML
export_to_n8nExport workflow to n8n format
search_web**Unified search** - Auto-fallback across providers
get_search_providersList available providers and their status
TavilyThe Tavily tool exposed by this server.
tavily_searchAI-powered search (requires TAVILY_API_KEY)
tavily_extractExtract content from URLs

How to install the Praisonai MCP MCP server

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

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
OPENAI_API_KEYCredential the server authenticates with.Yes
TAVILY_API_KEYCredential the server authenticates with.Yes
EXA_API_KEYCredential the server authenticates with.Yes
YDC_API_KEYCredential the server authenticates with.Yes
SEARXNG_URLEndpoint or connection string the server talks to.Yes

Example prompts to try

  • Use Praisonai MCP to run agent.
  • Use Praisonai MCP to run research.
  • Use Praisonai MCP to run auto agents.

Frequently asked questions

It connects Praisonai MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (run_agent, run_research, run_auto_agents, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Praisonai MCP directly.