MCPgee
MCPgee
MCPgeeMCPgee

Haive

v1.0.0•Developer Tools•stable

Dynamic MCP integration for AI agents — search 1,960+ servers, install with HITL approval

ai-agentsdockerlangchainllmmcp
Share:
10
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Haive?

Haive is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to dynamic mcp integration for ai agents — search 1,960+ servers, install with hitl approval

Dynamic MCP integration for AI agents — search 1,960+ servers, install with HITL approval

This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Dynamic MCP integration for AI agents — search 1,960+ server

Use Cases

Dynamic MCP server discovery
Install servers with HITL approval
pr1m8

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedMay 9, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx haive

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Haive

Haive MCP is a Python library and CLI that enables AI agents to dynamically discover, install, and manage MCP servers at runtime with human-in-the-loop (HITL) approval. Instead of hardcoding MCP server configurations, agents can search a catalog of 1,960+ servers, request installation of new ones, and manage connections across STDIO, SSE, HTTP, and Docker transports — all with optional human approval gates.

Prerequisites

  • Python 3.9 or higher installed
  • pip package manager
  • Docker (optional, for Docker transport support)
  • GitHub Personal Access Token (optional, for GitHub MCP integration)
  • A LangChain-compatible LLM or agent framework
1

Install the haive-mcp package

Install haive-mcp from PyPI using pip. This installs the library and the haive-mcp CLI tool.

pip install haive-mcp
2

Configure environment variables

Set any environment variables needed by the MCP servers you plan to use dynamically. For GitHub integration, set your personal access token.

export GITHUB_PERSONAL_ACCESS_TOKEN=your_github_token_here
export POSTGRES_HOST=your_db_host  # if using PostgreSQL MCP server
3

Use static MCP configuration in your agent

Configure known MCP servers statically using MCPConfig and MCPServerConfig, then retrieve all tools for your agent.

from haive.mcp.config import MCPConfig, MCPServerConfig, MCPTransport
from haive.mcp.manager import MCPManager

config = MCPConfig(
    enabled=True,
    servers={
        "filesystem": MCPServerConfig(
            name="filesystem",
            transport=MCPTransport.STDIO,
            command="npx",
            args=["-y", "@modelcontextprotocol/server-filesystem", "/workspace"]
        )
    }
)
manager = MCPManager(config)
tools = await manager.get_all_tools()
4

Use dynamic discovery with HITL approval

Create an IntelligentMCPAgent that can search for and install servers on demand, with human approval before installation.

from haive.mcp.agents import IntelligentMCPAgent

agent = IntelligentMCPAgent(
    auto_discover=True,
    require_approval=True
)
result = await agent.arun("Find Python repositories about quantum computing")
5

Use the CLI for server discovery and management

The haive-mcp CLI lets you search for servers, install them, and list available tools without writing code.

haive-mcp discover "database"
haive-mcp install postgres
haive-mcp tools filesystem

Haive Examples

Client configuration

Python snippet to create an MCPConfig for haive-mcp with a filesystem and GitHub server.

{
  "enabled": true,
  "servers": {
    "filesystem": {
      "name": "filesystem",
      "transport": "STDIO",
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-filesystem", "/workspace"]
    },
    "github": {
      "name": "github",
      "transport": "STDIO",
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-github"],
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": "your_token_here"
      }
    }
  }
}

Prompts to try

Example queries you can send to an IntelligentMCPAgent powered by haive-mcp.

- "Search for MCP servers that can interact with PostgreSQL databases"
- "Find and install a filesystem MCP server for my workspace"
- "List all available tools from the currently connected MCP servers"
- "Find Python repositories on GitHub about quantum computing"
- "Discover MCP servers for web scraping and install the best one"

Troubleshooting Haive

haive-mcp CLI command not found after install

Ensure the pip install target's bin directory is on your PATH. Try running python -m haive.mcp as an alternative, or reinstall with pip install --user haive-mcp and add ~/.local/bin to PATH.

Docker transport fails to start a server

Ensure Docker daemon is running (docker info should succeed). Verify the docker_volumes paths exist and are correctly mapped. Set the transport to MCPTransport.DOCKER and provide the image name in the command field.

Agent installs a server but tools are not available

After dynamic installation, call await manager.get_all_tools() again to refresh the tool list. With require_approval=True, ensure the approval prompt was confirmed before querying tools.

Frequently Asked Questions about Haive

What is Haive?

Haive is a Model Context Protocol (MCP) server that dynamic mcp integration for ai agents — search 1,960+ servers, install with hitl approval It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Haive?

Follow the installation instructions on the Haive GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Haive?

Haive works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Haive free to use?

Yes, Haive is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Haive Alternatives — Similar Developer Tools Servers

Looking for alternatives to Haive? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.

Ecc

★ 188.2k

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Javaguide

★ 155.8k

Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发

Gemini CLI

★ 104.5k

A secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in

Awesome MCP Servers

★ 87.3k

⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.

MCP Servers

★ 86.0k

Model Context Protocol Servers

CC Switch

★ 77.5k

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io

Browse More Developer Tools MCP Servers

Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Developer ToolsBrowse All Servers

Quick Config Preview

{ "mcpServers": { "haive": { "command": "npx", "args": ["-y", "haive"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Haive?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides