Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者提供的说明(英文原文)
Agent-to-agent reasoning-as-a-service: chain-of-thought, analysis, and decision support.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
适用于网页版、桌面版和手机版 Claude:
https://hiveconsult.onrender.com/mcp在终端中运行这条命令
claude mcp add --transport http hiveconsult https://hiveconsult.onrender.com/mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"hiveconsult": {
"url": "https://hiveconsult.onrender.com/mcp"
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"hiveconsult": {
"type": "http",
"url": "https://hiveconsult.onrender.com/mcp"
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
ChatGPT 只能连接互联网上的服务器:
https://hiveconsult.onrender.com/mcp菜单名称可能因套餐和版本不同而略有差异。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
我们还没有读取这个服务器的工具列表;我们会轮流检查各个端点。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日
注册名称已通过 GitHub 账户 srotzin 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
尚未检查;我们会轮流检查各个端点
尚未检查;我们会轮流检查各个端点
尚未检查;我们会在检查端点时读取工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
GitHub 仓库最后更新于–,最新版本(1.0.0)于6个月前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
同一分类中有:Spec Driven Development, Remote Desktop Commander, Signoff
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Five gates that make an agent's 'done' provable: run them, read the verdict, audit the record.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Agent-to-agent reasoning-as-a-service. Provides structured reasoning, data analysis, decision support, and code/document review via REST API and MCP protocol.
| Method | Path | Description | Cost |
|---|---|---|---|
| GET | / | Service discovery | Free |
| GET | /health | Health check | Free |
| POST | /v1/consult/reason | Chain-of-thought reasoning | $0.01–$0.25 |
| POST | /v1/consult/analyze | Data analysis (trend/anomaly/forecast/comparison) | $0.05 |
| POST | /v1/consult/decide | Decision support with weighted criteria | $0.05 |
| POST | /v1/consult/review | Code/contract/document/strategy review | $0.05 |
| POST | /v1/consult/batch | Batch multiple consultations (max 10) | Per item |
| GET | /v1/consult/stats | Consultation metrics | Free |
| GET | /v1/consult/history/:did | Agent consultation history | Free |
| POST | /mcp | JSON-RPC 2.0 MCP endpoint | Per tool |
| GET | /.well-known/ai-plugin.json | AI plugin discovery | Free |
Internal (platform-to-platform):
x-hive-internal: <service_key>
Bypasses payment for inter-service calls.
External (agent-to-agent): Uses x402 micropayment protocol. If no payment is provided, the API returns 402 Payment Required with a payment challenge including USDC amount, recipient address, and accepted methods. Include payment proof in the X-Payment header.
| Depth | Cost | Steps | Description |
|---|---|---|---|
quick | $0.01 | 3 | Fast heuristic analysis |
standard | $0.05 | 6 | Balanced reasoning with evidence weighing |
deep | $0.25 | 12 | Exhaustive multi-perspective analysis |
HiveConsult exposes an MCP-compatible JSON-RPC 2.0 endpoint at /mcp.
POST /mcp
{ "jsonrpc": "2.0", "id": 1, "method": "tools/list", "params": {} }
hiveconsult_reason — Structured reasoning with configurable depthhiveconsult_analyze — Data analysis (trend, anomaly, forecast, comparison)hiveconsult_decide — Multi-criteria decision supporthiveconsult_review — Code/contract/document/strategy reviewPOST /mcp
{ "jsonrpc": "2.0", "id": 2, "method": "tools/call", "params": { "name": "hiveconsult_reason", "arguments": { "did": "did:hive:my_agent", "question": "Should we migrate from REST to GraphQL?", "reasoning_depth": "standard", "domain": "architecture" } } }
npm install
npm start
The server starts on port 3000 (configurable via PORT env var).
curl -X POST http://localhost:3000/v1/consult/reason \
-H "Content-Type: application/json" \ -H "x-hive-internal: " \ -d '{ "did": "did:hive:my_agent", "question": "What is the optimal caching strategy for a read-heavy API?", "reasoning_depth": "standard", "domain": "backend" }'
curl -X POST http://localhost:3000/v1/consult/decide \
-H "Content-Type: application/json" \ -H "x-hive-internal: " \ -d '{ "did": "did:hive:my_agent", "options": ["Redis", "Memcached", "CDN edge cache"], "criteria": ["latency", "cost", "complexity", "scalability"], "weights": [0.4, 0.2, 0.15, 0.25] }'
MIT
Hive Civilization is the cryptographic backbone of autonomous agent commerce — the layer that makes every agent transaction provable, every payment settable, and every decision defensible.
This repository is part of the PROVABLE · SETTABLE · DEFENSIBLE pillar.