# PraisonAI

Autonomous agent framework with reflection and MCP support. It orchestrates multi-agent tasks directly inside your coding workflow.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 9289
- Author: MervinPraison
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/MervinPraison/PraisonAI
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/mcp/praisonai

## What it does

The server links code editors to PraisonAI agent capabilities. The architecture spans five core layers: prompt setup, context with memory handling, execution harnesses with MCP tools, execution loops with reflection, and multi-agent graphs. It can also isolate tool executions inside Docker containers.

Agents rely on `ExecutionConfig` to prevent infinite loops while completing work. You need an active `OPENAI_API_KEY` for LLM calls when writing Python flows. Without `uvx` available in your system path, the MCP command will fail immediately.

## Requirements
- Needs: Python and uv (commands run via uvx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add praisonai -- uvx praisonai
```
uvx runs the command named after the package; if the README names another one, use uvx --from praisonai <command>

### Codex

**Platform CLI**
```bash
codex mcp add praisonai -- uvx praisonai
```
uvx runs the command named after the package; if the README names another one, use uvx --from praisonai <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "praisonai": {
            "command": "uvx",
            "args": [
                "praisonai"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from praisonai <command>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "praisonai": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "praisonai"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from praisonai <command>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add praisonai uvx praisonai
```
uvx runs the command named after the package; if the README names another one, use uvx --from praisonai <command>

## When to use it
- orchestrate multi-agent workflows with context and memory
- automate web and document research across several data sources
- generate and refactor code using self-correcting agent chains
- prevent infinite execution loops during autonomous task runs

## Example prompts
- Spin up a PraisonAI agent team to inspect the codebase and refactor functions
- Research the latest developer tools and output the results as a markdown table
- Set up an agent flow where a reviewer validates output before saving files

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 386989
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33918
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81115
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119160
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47392
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43872

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md