LABSCO SUMMARY

An agent framework's whole toolbox, reachable from a client that is not it.

Research, crawling, memory, planning and agent delegation arrive as one set, and the unified search falls back across providers, so a research task keeps working when one key is missing or one provider is rate-limited.

What it is

An MCP front end for PraisonAI. Agent execution, multi-step workflows, a set of web search and crawl providers, and persistent memory and knowledge stores are all exposed as tools.

What you get

Agents run from a prompt, generated automatically for a task, or handed off between each other, with the agents.yaml produced for you
Multi-step workflows created, run, built from YAML, and exported to n8n
Unified web search with automatic fallback across providers, plus direct access to Tavily, Exa, DuckDuckGo, SearXNG, You.com, Wikipedia and arXiv
Pages scraped and sites crawled — Crawl4AI extraction and scraping, link extraction, and deep research as a single call
A memory store that is added to, searched, listed and cleared, and that can extract memories from a conversation on its own
A knowledge base kept separate from memory, added to and searched
Repositories analysed, and plans created and executed as their own step

Requirements

uvx praisonai-mcp, or pip install praisonai-mcp. The agent and workflow tools run PraisonAI locally; the search tools each need a key from their own provider — Tavily, Exa and the rest — and the provider list is readable, so you can see which are actually available.

Setup effort

One command plus a key — uvx praisonai-mcp, then supply credentials

See installation options

USE CASES

01

Researching a topic properly rather than with one search

Deep research across providers with fallback when one is unavailable, and the provider list readable when a result comes back thin.

deep_researchsearch_webget_search_providers

02

Delegating a task to an agent built for it

Auto-generate the agents for the task and run them, or hand off between agents when a stage needs a different specialist.

run_auto_agentsrun_agentrun_handoffgenerate_agents_yaml

03

Turning a repeated process into a workflow

Create the workflow, run it, and export it to n8n once it has earned a schedule.

workflow_createworkflow_runworkflow_from_yamlexport_to_n8n

04

Pulling the content out of a set of pages

Scrape a page, crawl a site, extract structured content or just the links — whichever the source calls for.

scrape_pageweb_crawlcrawl4ai_scrapecrawl4ai_extractextract_links

05

Keeping what was learned across conversations

Add to memory as things are established, search it later, and let the extraction pass pick up what was implied rather than stated.

memory_addmemory_searchauto_extract_memoriesknowledge_addknowledge_search

06

Searching where the general web is the wrong index

arXiv and Wikipedia alongside the general providers, plus similar-page search when you already have one good source.

arxiv_searchwikipedia_searchexa_find_similarexa_search_contents

82 tools

Listed in project docs. Your client may show a different list.

run_agent

run_research

run_auto_agents

run_handoff

generate_agents_yaml

workflow_run

workflow_create

workflow_from_yaml

export_to_n8n

search_web

get_search_providers

tavily_search

tavily_extract

exa_search

exa_search_contents

BEFORE YOU INSTALL

What to know first

Tools you get

82 tools named in the project's documentation.

Requires

uvx on PATH
OPENAI_API_KEY in your environment

INSTALLATION

Connect your client

Server setup

TERMINAL

uvx praisonai-mcp

MCP Clients

Claude Desktop

CLAUDE DESKTOP · JSON

{
  "mcpServers": {
    "praisonai": {
      "command": "uvx",
      "args": [
        "praisonai-mcp"
      ],
      "env": {
        "OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
        "TAVILY_API_KEY": "<YOUR_TAVILY_API_KEY>"
      }
    }
  }
}

VS Code

VS CODE · 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, Windsurf, Cline

JSON

{
  "mcpServers": {
    "praisonai": {
      "command": "uvx",
      "args": [
        "praisonai-mcp"
      ],
      "env": {
        "OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>"
      }
    }
  }
}

Continue

CONTINUE · JSON

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

Zed

ZED · JSON

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

Claude Code

CLAUDE CODE · TERMINAL

claude mcp add praisonai -- uvx praisonai-mcp

Praison AI