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 gateway for Index discovery, AN Score evaluation, and Resolve governed execution
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。
RHUMB_API_KEY标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
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 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"rhumb": {
"command": "npx",
"args": [
"-y",
"rhumb-mcp"
],
"env": {
"RHUMB_API_KEY": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add rhumb --env RHUMB_API_KEY=your-value -- npx -y rhumb-mcp运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"rhumb": {
"command": "npx",
"args": [
"-y",
"rhumb-mcp"
],
"env": {
"RHUMB_API_KEY": "your-value"
}
}
}
}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": {
"rhumb": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"rhumb-mcp"
],
"env": {
"RHUMB_API_KEY": "your-value"
}
}
}
}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。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
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。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
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 supertrained 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
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
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。
你需要填写:RHUMB_API_KEY
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(0.8.2)于7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。你的电脑上还需要有 Node.js。
同一分类中有:Spec Driven Development, Remote Desktop Commander, 御府和田玉 在售作品查询
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.
Live in-stock Hetian jade from Yufu, Shanghai: prices, monthly price guide, book a viewing.
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-native tool intelligence for the Model Context Protocol.
Three execution layers: raw provider access (Layer 1), intelligent routing (Layer 2), and deterministic composed recipes (Layer 3, beta with a truthful public catalog). Every provider rated with the AN Score. Every execution produces a chain-hashed receipt.
No governed API key needed for discovery. Install and start immediately:
npx -y --package rhumb-mcp@latest rhumb-mcp
Or add to Claude Desktop / Cursor / any MCP client:
{
"mcpServers": { "rhumb": { "command": "npx", "args": ["-y", "--package", "rhumb-mcp@latest", "rhumb-mcp"] } } }
Ask your agent:
Rhumb is strongest today for research, extraction, generation, and narrow enrichment.
Treat it as capability infrastructure first, not as a general business-agent automation layer yet. Layer 2 is the real production surface today; Layer 3 is still beta with an intentionally sparse public catalog.
Discovery breadth is wider than current execution breadth: Rhumb scores 999 services and exposes 435 capability definitions, but current governed execution is concentrated in 28 callable providers.
X-Rhumb-KeyCanonical onboarding map: https://rhumb.dev/docs#resolve-mental-model
Rhumb Resolve — three execution layers:
| Layer | What | How |
|---|---|---|
| Layer 1 | Raw provider access | You pick the provider. Escape hatch + trust anchor. |
| Layer 2 | Capability routing | Rhumb routes to the best-fit supported provider for the call, using AN Score, availability / circuit state, estimated cost, latency proxy, credential mode, and explicit policy constraints. |
| Layer 3 | Deterministic recipes (beta) | Compiled DAG workflows. Multi-step, budget-enforced, content-firewalled. No published recipes yet. |
New infrastructure:
execute_capability now returns _rhumb_v2 metadata with attribution and receiptsnpx -y --package rhumb-mcp@latest rhumb-mcp| Tool | What it does |
|---|---|
find_services | Search indexed Services by what you need them to do |
get_score | Get the full AN Score breakdown for a Service: execution quality, access readiness, autonomy level, tier label, and freshness |
get_alternatives | Find alternative Services, ranked by AN Score |
get_failure_modes | Get known failure patterns, impact severity, and workarounds for a service |
discover_capabilities | Browse Capabilities by domain or search text |
resolve_capability | Given a Capability ID, and optionally a credential mode, returns ranked providers with health status, cost per call, auth methods, endpoint patterns, execute guidance, and machine-readable recovery fields like recovery_hint.resolve_url, recovery_hint.credential_modes_url, and, when applicable, recovery_hint.alternate_execute_hint or recovery_hint.setup_handoff, plus typo recovery when the capability ID is wrong |
{
"mcpServers": { "rhumb": { "command": "npx", "args": ["-y", "rhumb-mcp@latest"], "env": { "RHUMB_API_KEY": "rk_your_key_here" } } } }
Get a governed API key at https://rhumb.dev/auth/login (GitHub, Google, or email — 30 seconds).
| Tool | What it does |
|---|---|
execute_capability | Call a Capability through Rhumb Resolve |
estimate_capability | Estimate the active execution rail, cost, and health before a Capability call; anonymous direct system-of-record paths also preserve machine-readable execute_readiness handoffs |
credential_ceremony | Get step-by-step instructions to obtain API credentials for a Service |
check_credentials | Inspect live credential-mode readiness, globally or for a specific Capability |
rhumb_list_recipes | List the current published Rhumb Layer 3 recipe catalog |
rhumb_get_recipe | Get the full published definition for a Rhumb recipe, including input/output schemas and step topology |
rhumb_recipe_execute | Execute a published Rhumb Layer 3 recipe once one is live in the public catalog |
get_receipt | Retrieve an execution receipt by ID |
| Tool | What it does |
|---|---|
budget | Check or set your call spending limit |
spend | Get your spending breakdown for a billing period: total USD spent, call count, average cost per call, broken down by Capability and by provider |
check_balance | Check your current Rhumb credit balance in USD |
get_payment_url | Get a checkout URL to add credits to your Rhumb balance |
get_ledger | Get your billing history: charges (debits), top-ups (credits), and auto-reload events |
| Tool | What it does |
|---|---|
routing | Get or set how Rhumb auto-selects providers when you don't specify one in execute_capability |
usage_telemetry | Get your execution analytics — calls, latency, errors, costs, and provider health for your Rhumb usage |
Discovery (free): find_services, get_score, get_alternatives, get_failure_modes, discover_capabilities, resolve_capability
Execution (auth): execute_capability, estimate_capability, credential_ceremony, check_credentials, rhumb_list_recipes, rhumb_get_recipe, rhumb_recipe_execute, get_receipt
Financial (auth): budget, spend, check_balance, get_payment_url, get_ledger
Operations (auth): routing, usage_telemetry
Discovery spans 999 scored services, but current governed execution spans 28 callable providers.
Best current fit: research, extraction, generation, and narrow enrichment. Treat general business-agent automation as future scope, not the current callable promise.
"I need an email provider for agents."
find_services → search the landscapeget_score → inspect a specific providerget_failure_modes → see where it breaks in practice"I need
email.send. What should I use?"
discover_capabilities → find the capability IDresolve_capability → get ranked providers, optional credential-mode filtering, machine-readable recovery fields like recovery_hint.resolve_url, recovery_hint.credential_modes_url, and, when applicable, recovery_hint.alternate_execute_hint or recovery_hint.setup_handoff, or search suggestions when the capability ID is wrong"Can I call
deployment.listright now, and on which rail?"
check_credentials → call without params for account-wide configured BYOK/direct-bundle readiness, or pass a capability to inspect provider-level mode status and ceremony availability"Send the email with the cheapest provider above my quality floor."
estimate_capability → check the active execution rail, health, and cost before executionexecute_capability → perform the actionget_receipt → verify the HMAC-signed execution record"Is there already a published Rhumb workflow for this?"
rhumb_list_recipes → check what is actually live in the public catalogrhumb_get_recipe → inspect a recipe only after it appears thererhumb_recipe_execute → run the compiled recipe once it is publishedNo account needed — pay per call with USDC on Base:
{
"env": { "RHUMB_X402_WALLET_ADDRESS": "0x...", "RHUMB_X402_PRIVATE_KEY": "0x..." } }
cd packages/mcp
npm ci npm run dev
npm test # 84+ tests
npm run type-check npm run build
https://api.rhumb.dev/v1 (v1 compat) / https://api.rhumb.dev/v2 (Resolve v2)MIT