Hive A/B Test MCP Setup & Guide
io.github.srotzin/hive-mcp-abtest · v1.0.0
A/B experiment runner for the A2A network with x402 micropayments on Base USDC.
Copy the install config on this page first, then verify docs and permissions upstream.
Overview
A/B experiment runner for the A2A network with x402 micropayments on Base USDC. Hive A/B Test is a MCP Server listed from MCP Registry. Transports: streamable-http. This page includes an overview, setup tutorial, install commands, and use cases for Trae, Tongyi Lingma, Cursor, Claude Code, and VS Code.
Use cases
AgentHub Verified AvailabilityTested & Ready
Automated pipeline validated install commands, protocol & client compatibility
Copy by platform
Choose your platform
- Open or create .cursor/mcp.json in your project root
- Click Copy config and paste; if you already have MCPs, merge only this entry under mcpServers
- Save, then Cmd+Shift+P (Ctrl+Shift+P on Windows) → Reload Window
{
"mcpServers": {
"hive-mcp-abtest": {
"url": "https://hive-mcp-abtest.onrender.com/mcp"
}
}
}Setup tutorial
- Open the Hive A/B Test page and confirm this MCP Server (source: MCP Registry).
- Copy the Cursor, Claude Code, or VS Code snippet.
- Merge it into mcpServers and replace env placeholders with real secrets.
- Reload the window, then call the MCP tools from your agent chat.
Install commands
Install commands and setup steps are in the HTML so search engines and no-JS browsers can read them without running client JavaScript.
Claude Code (remote)
- Install Claude Code CLI (claude must work in your terminal)
- Click Copy config below, paste into terminal, and run
- Restart Claude Code after it succeeds
claude mcp add --transport http hive-mcp-abtest https://hive-mcp-abtest.onrender.com/mcpCursor — .cursor/mcp.json (remote)
- Open or create .cursor/mcp.json in your project root
- Click Copy config and paste; if you already have MCPs, merge only this entry under mcpServers
- Save, then Cmd+Shift+P (Ctrl+Shift+P on Windows) → Reload Window
{
"mcpServers": {
"hive-mcp-abtest": {
"url": "https://hive-mcp-abtest.onrender.com/mcp"
}
}
}VS Code — .vscode/mcp.json (remote)
- Install GitHub Copilot in VS Code with MCP support
- Open or create .vscode/mcp.json in your project root
- Click Copy config and paste; merge only this mcpServers entry if others exist
- Save and Developer: Reload Window
{
"mcpServers": {
"hive-mcp-abtest": {
"url": "https://hive-mcp-abtest.onrender.com/mcp"
}
}
}Claude Desktop — claude_desktop_config.json (remote)
- Open Claude Desktop config: macOS ~/Library/Application Support/Claude/claude_desktop_config.json; Windows %APPDATA%\Claude\claude_desktop_config.json
- Click Copy config and merge under mcpServers
- Fully quit and restart Claude Desktop
{
"mcpServers": {
"hive-mcp-abtest": {
"url": "https://hive-mcp-abtest.onrender.com/mcp"
}
}
}Trae — .trae/mcp.json (remote)
- Trae → Settings → MCP, or edit .trae/mcp.json (project) / global mcp.json
- Use Manual add / Raw JSON, click Copy config and paste; merge only this mcpServers entry
- Save, pick an MCP-capable agent (e.g. Builder with MCP), reload window if needed
{
"mcpServers": {
"hive-mcp-abtest": {
"url": "https://hive-mcp-abtest.onrender.com/mcp"
}
}
}Cherry Studio — MCP settings (remote)
- Cherry Studio → Settings → MCP Servers
- Add via JSON import or SSE/HTTP with the URL
- Click Copy config, paste the mcpServers entry, then enable the server
{
"mcpServers": {
"hive-mcp-abtest": {
"url": "https://hive-mcp-abtest.onrender.com/mcp"
}
}
}Tongyi Lingma — MCP config (remote)
- Tongyi Lingma: avatar → Settings → MCP (agent mode; plugin ~v2.5+)
- Click + → config file or manual SSE/HTTP with the service URL
- Click Copy config and merge JSON; a healthy icon means connected
{
"mcpServers": {
"hive-mcp-abtest": {
"url": "https://hive-mcp-abtest.onrender.com/mcp"
}
}
}Cline — MCP Servers (remote)
- VS Code Cline panel → settings gear → MCP Servers
- Click Copy config and paste the mcpServers entry into Cline
- Save; Cline reconnects and shows tools
{
"mcpServers": {
"hive-mcp-abtest": {
"url": "https://hive-mcp-abtest.onrender.com/mcp"
}
}
}WorkBuddy — .workbuddy/mcp.json (remote)
- WorkBuddy: sidebar Plugins → MCP Servers → Configure MCP; or edit ~/.workbuddy/mcp.json (user) / .workbuddy/mcp.json (project)
- Click Copy config and merge under mcpServers (Tencent WorkBuddy / CodeBuddy)
- Save; status should turn green — fully restart the client if needed
{
"mcpServers": {
"hive-mcp-abtest": {
"url": "https://hive-mcp-abtest.onrender.com/mcp"
}
}
}Windsurf — mcp_config.json (remote)
- Edit ~/.codeium/windsurf/mcp_config.json (Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json)
- Click Copy config and merge; remote MCP must use serverUrl (not url)
- Save and refresh MCP in Windsurf Cascade
{
"mcpServers": {
"hive-mcp-abtest": {
"serverUrl": "https://hive-mcp-abtest.onrender.com/mcp"
}
}
}Troubleshooting & Common ErrorsFAQ
Common connection errors and verified fixes for Hive A/B Test
Getting 'connection closed' or exit code 1 in Cursor / Claude Code for Hive A/B Test?
Usually caused by missing runtime paths or IDE environment inheritance. Fix steps: 1. Verify Node.js 18+ (npx) or Python 3.10+ (uvx) is installed; 2. Run 'which npx' or 'which uvx' in terminal, and replace 'command' with absolute path; 3. Reload or restart the client window after modifying config.
# Check binary path in terminal: which npx node -v
Getting 'spawn npx ENOENT' or 'command not found'?
The editor background process does not inherit your full terminal PATH. Solution: Globally install the package, or set the absolute binary path (e.g. C:\Program Files\nodejs\npx.cmd on Windows, or /usr/local/bin/npx on macOS).
Tool calls timing out or failing to download packages?
First-time package downloading might be slow or timeout due to network limits. Configure a reliable mirror or check outbound proxy settings.
Tool Mock Playground
SandboxHive A/B Test Tool Interface Simulation · Preview tool schema & outputs without local runtime
{
"target": "Hive A/B Test",
"action": "execute",
"options": {
"mode": "standard",
"timeoutMs": 5000
}
}Click 'Run Mock' above
to preview the raw response returned to the LLM
Decision Guide: Why & When to Use
Assess suitability before installing to save trial-and-error time
- PR review
- Changelog generation
- Cross-repo issue search
- Replacing human security audit
- Unauthorized repo access
Hive A/B Test + Scenario Prompt → Complete Agent Automation
MCP hands-on: install to visible results
Follow the full lab (expected UI/output + contrast checks). After installing this item, verify with the tutorial prompts.
Related resources
顺序思考
io.mcp-cn.modelcontextprotocol/server-sequential-thinking
帮助AI进行结构化思考和推理的MCP工具
n8n
io.mcp-cn.drballs/n8n-mcp-server
n8n工作流自动化平台的MCP服务器,提供完整的工作流管理、执行控制、凭证管理等功能
Playwright
io.mcp-cn.playwright/mcp
基于Playwright的自动化测试和网页操作MCP工具
GitHub
io.mcp-cn.modelcontextprotocol/server-github
连接GitHub的MCP服务器,支持仓库管理、问题跟踪、代码搜索等功能
高德地图
io.mcp-cn.amap/amap-maps-mcp-server
高德地图的MCP服务器
Figma
io.mcp-cn.figma-developer-mcp
连接Figma的MCP服务器,支持设计文件管理和操作
Often paired with
Planning with files
v3.23.0
io.clawhub.othmanadi/planning-with-files
Persistent file-based planning for multi-step AI-agent work. Keeps task_plan.md, findings.md, and progress.md on disk; lifecycle hooks inject selected project planning context. Automatic recovery reads project planning files only. Explicit session-catchup.py --metadata reads same-project local agent session records and emits aggregate counts only; --replay may emit bounded nonce-framed excerpts. Optional gated mode can request continuation only when the host supports it and never runs commands declared in Markdown. The skill has no network upload path. Use for research or work needing 5+ tool calls.
OpenClaw Command Center
v1.5.0
io.clawhub.jontsai/command-center
Mission control dashboard for OpenClaw - real-time session monitoring, LLM usage tracking, cost intelligence, and system vitals. View all your AI agents in one place.
ClawCall
v2.0.1
io.clawhub.clawcall-dev/clawcall-dev
Use when the user wants an AI agent to place a US phone call, call a business, handle hold or phone menus, confirm/reschedule/cancel/book/follow up/check an order, reach a real person, leave voicemail, connect the user into a live call, configure ClawCall voice/personality/profile or inbound reserved-number answering, poll received inbound calls, or link a ClawCall API key. Not for SMS, email, or international calls.
self-improving agent
v4.0.3
io.clawhub.pskoett/self-improving-agent
Captures and maintains learnings, errors, and corrections. Use when a command fails, the user corrects an assumption, a capability is missing, knowledge is outdated, or a better approach is found. Review relevant saved guidance before major tasks, reuse, and promotion; revalidate it according to wha
Keep exploring AgentHub
Most people compare similar tools or check scenario guides before installing—start here.
Listing badge: put AgentHub on your site
Copy either snippet into your project homepage, docs, or GitHub README. The badge is a hotlinked SVG — nothing to host — and it links back to this page so visitors can find the install steps.
<a href="https://myagenthub.cn/p/io.github.srotzin/hive-mcp-abtest" title="Listed on AgentHub: Hive A/B Test" target="_blank" rel="noopener">
<img src="https://myagenthub.cn/badge/io.github.srotzin/hive-mcp-abtest?lang=en" alt="Listed on AgentHub: Hive A/B Test" height="20" style="border:0"/>
</a>[](https://myagenthub.cn/p/io.github.srotzin/hive-mcp-abtest)Badges are generated on the fly from /badge/<package-id>, so name and listing changes propagate automatically. Keep the link target unchanged — it is what counts as the referral.
Unified Manifest
{
"id": "io.github.srotzin/hive-mcp-abtest",
"type": "mcp-server",
"version": "1.0.0",
"displayName": "Hive A/B Test",
"description": "A/B experiment runner for the A2A network with x402 micropayments on Base USDC.",
"repository": {
"url": "https://github.com/srotzin/hive-mcp-abtest",
"source": "github"
},
"homepage": "https://www.hiveagentiq.com",
"distribution": {
"packages": [],
"remotes": [
{
"transport": "streamable-http",
"url": "https://hive-mcp-abtest.onrender.com/mcp"
}
]
},
"dependencies": [],
"installTargets": [
"claude-code",
"claude-desktop",
"cursor",
"vscode",
"trae",
"cherry-studio",
"lingma",
"windsurf",
"cline",
"workbuddy"
],
"keywords": [],
"provenance": {
"origin": "official-mcp-registry",
"originalId": "io.github.srotzin/hive-mcp-abtest",
"originalUrl": "https://registry.modelcontextprotocol.io/v0.1/servers/io.github.srotzin%2Fhive-mcp-abtest/versions/latest",
"isOfficial": true,
"status": "active"
}
}