Log inSubmit server
PraisonAI logo

PraisonAI

Python framework for building autonomous agents with MCP tool support, reflection, memory, workflows, and multi-agent execution.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install PraisonAI

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "praisonai": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-filesystem"
      ],
      "env": {
        "OPENAI_API_KEY": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

PraisonAI is a Python agent framework that combines autonomous task execution with MCP tool support, memory, knowledge retrieval, guardrails, approvals, and workflow control. Agents can connect to MCP servers through the `MCP()` interface alongside local tools, then execute tasks with reflection, iteration limits, and handoffs. Reach for it when a coding or automation agent needs more structure than a single prompt, including multi-step workflows, research, code tasks, and data processing.

Use cases

  • Build agents that use MCP tools alongside Python functions
  • Create multi-step coding and research workflows
  • Route tasks between specialist agents
  • Automate data analysis and processing tasks
  • Add approval and execution controls to agent tools

Key features

  • MCP server connections through Python
  • Agent memory and knowledge retrieval
  • Reflection and execution controls
  • Multi-agent flows and handoffs
  • Tool approvals and sandbox options

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

50/55 checks healthy over the last 91d

Supply-chain signal

2 high-severity advisories on record for this package. Most advisories affect transitive dependencies and may not be exploitable in this server's actual usage — this is a directional signal, not a security audit.

Critical 0High 2Medium 0Low 0

Scanned 3h ago via OSV.dev · @modelcontextprotocol/server-filesystem (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars9.3kStargazers on the source repository.
Last commit1d agoMost recent push to the default branch.
Directory activity4 viewsConfig copies, upvotes, and views on AllMCPs.

How PraisonAI works

What PraisonAI does

PraisonAI provides Python APIs for creating agents that can research, plan, execute tasks, and produce structured output. Its scope ranges from individual agents to coordinated groups using agent flows, handoffs, routing, parallel execution, loops, and repeated tasks.

The framework also includes controls for the agent execution cycle. Developers can configure memory, knowledge sources, context compression, guardrails, human approval, hooks, sandbox execution, reflection, autonomy, and checks for stalled or repetitive behavior.

MCP support lets an agent use tools exposed by MCP servers. The README demonstrates combining a local Python tool with an MCP filesystem server, so PraisonAI can place MCP-based capabilities alongside application-defined functions.

How it works

Agents are created in Python with the Agent class from praisonaiagents. An agent can receive instructions, a role, a goal, output preferences, memory, knowledge, context settings, and a tool list. Calling agent.start(...) begins execution for a user-provided task.

The framework describes execution as layered configuration:

  • Prompt settings define the role, instructions, examples, and output format.
  • Context settings manage memory, knowledge selection, compression, and handoff context.
  • Harness settings provide tools, MCP connections, guardrails, approvals, hooks, and sandbox options.
  • Loop settings control iterations, budgets, reflection, autonomy, and progress checks.
  • Graph settings coordinate multiple agents through routing, parallel work, loops, and repetition.

A handoff can pass work to a specialist while limiting the inherited conversation and tools. Managed execution can run tools in Docker or run an entire agent through an Anthropic-backed option, as shown by the framework's configuration examples.

Setup and configuration

Install the main package with pip:

Terminal
pip install praisonai

For the lightweight agent SDK, install praisonaiagents instead or in addition, then configure an OpenAI API key:

Terminal
pip install praisonaiagents
export OPENAI_API_KEY="your-api-key"

The project also provides an installation script:

Terminal
curl -fsSL https://praison.ai/install.sh | bash

A basic agent can be defined with Python:

server.ts
from praisonaiagents import Agent

agent = Agent(instructions="You are a senior data analyst.")
agent.start("Analyze the top 3 tech trends of 2026")

Tools and capabilities

  • Connect agents to MCP servers with MCP(...).
  • Register Python functions as agent tools with the @tool decorator.
  • Add memory, knowledge directories, and context summarization.
  • Require approval before selected tools execute.
  • Organize multiple agents with flows, routing, parallel work, loops, and handoffs.
  • Configure execution limits, reflection, autonomy, and progress checks.

Limitations and notes

PraisonAI is presented as a Python framework rather than a client-specific MCP application. The documented MCP example shows an agent consuming an MCP filesystem server; MCP server connection details depend on the command or configuration passed to MCP(...). The example uses an OpenAI API key, and the framework also includes an option for running an agent through Anthropic.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about PraisonAI

PraisonAI is an MCP server that connects Python agents to MCP-based tools and local functions. Its main tools are agent execution, Python tool dispatch, MCP integration, memory and knowledge handling, multi-agent workflows, and reflection or execution controls for tasks such as coding, research, and automation.

Install PraisonAI with `pip install praisonai`, or install the agent SDK with `pip install praisonaiagents`. The project also provides `curl -fsSL https://praison.ai/install.sh | bash` as an installation option.

Pass an MCP server command to `MCP(...)` in an agent's `tools` list. The documented example combines `MCP("npx -y @modelcontextprotocol/server-filesystem /tmp")` with a Python function decorated using `@tool`.

The quick-start agent example requires `OPENAI_API_KEY`. Set it in the environment before starting an agent with `export OPENAI_API_KEY="your-api-key"`.

Yes, PraisonAI supports multi-agent workflows through `AgentFlow`, routing, parallel execution, loops, repetition, and handoffs to specialist agents.

Related MCP servers

All in Coding Agents All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewPraisonAI AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/praisonai?style=directory)](https://allmcps.com/mcp/praisonai)
HTML Embed
<a href="https://allmcps.com/mcp/praisonai"><img src="https://allmcps.com/api/badge/praisonai?style=directory" alt="PraisonAI on AllMCPs" /></a>