Log inSubmit server
Rhumb logo

Rhumb

by supertrained

Ranks external services, resolves supported capabilities, and executes calls with credentials, budgets, cost tracking, and receipts.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Rhumb

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "supertrained-rhumb": {
      "command": "npx",
      "args": [
        "-y",
        "--package",
        "rhumb-mcp@latest",
        "rhumb-mcp"
      ],
      "env": {
        "RHUMB_API_KEY": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Automated check passed— started and listed 21 tools correctly (19d ago).

Overview

The supertrained/rhumb MCP server indexes external services, scores them, and routes supported capability calls through Rhumb Resolve. Its 21 MCP tools cover discovery, provider comparison, credential readiness, execution estimates, receipts, budgets, billing, routing, and telemetry. Run it locally with npx; discovery works without authentication, while execution uses a governed API key, BYOK, Agent Vault, or supported x402 payment flow. Reach for it when an agent needs to evaluate external tools or perform research, extraction, generation, and narrow enrichment through governed provider selection.

Use cases

  • Search and rank external services by capability
  • Compare providers before selecting an API
  • Estimate execution cost and health before a call
  • Execute supported research or enrichment capabilities
  • Review receipts, spending, and provider telemetry

Key features

  • Service discovery and AN Score breakdowns
  • Capability resolution with ranked providers
  • Managed, BYOK, and Agent Vault credential modes
  • Execution estimates, receipts, budgets, and telemetry
  • Alternative and failure-mode analysis
  • x402/USDC payment support where available

Tools21

What Rhumb lets your agent do. Expand a tool for its parameters.

Verified live~4.3k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 1d ago

Recent health check succeeded.

17/18 checks healthy over the last 79d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 6d ago via OSV.dev · rhumb-mcp@latest (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars5Stargazers on the source repository.
npm downloads245Package downloads in the last 30 days.
Last commit14d agoMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed21Callable tools this server registers over MCP.
Directory activity3 viewsConfig copies, upvotes, and views on AllMCPs.

How Rhumb works

What supertrained/rhumb does

The supertrained/rhumb MCP server provides two related surfaces for working with external services. Rhumb Index helps an agent search services, inspect AN Scores, compare alternatives, review known failure modes, and browse capability definitions. Rhumb Resolve handles supported executable capabilities by ranking providers and returning information such as health, estimated cost, authentication methods, endpoint patterns, and recovery guidance.

The catalog is broader than the callable execution surface. The stated best fit is research, extraction, generation, and narrow enrichment. Broader multi-system business automation is described as future scope rather than a current execution guarantee.

How it works

An agent can begin by finding a service or capability, inspecting its score and alternatives, and checking failure patterns. For an executable capability, it can resolve providers, estimate the active execution rail and cost, then call the capability through Rhumb Resolve. Executions can produce receipts, and later calls can retrieve those receipts by ID.

Provider selection can consider AN Score, availability or circuit state, estimated cost, latency proxy, credential mode, and policy constraints. The server also exposes routing controls for automatic provider selection. Usage telemetry reports calls, latency, errors, costs, and provider health.

The supertrained/rhumb MCP server supports three credential approaches: Rhumb-managed credentials, provider keys supplied through BYOK, and keys stored in Agent Vault for injection at call time. Payment can use prepaid credits through a governed API key or, where supported, x402/USDC for per-call access without signup.

Setup and configuration

Start the stdio server with:

Terminal
npx -y --package rhumb-mcp@latest rhumb-mcp

This zero-configuration mode enables discovery tools without signup or a governed API key. To enable authenticated execution, provide a governed key:

bash
RHUMB_API_KEY=your_key npx -y --package rhumb-mcp@latest rhumb-mcp

A governed API key is obtained through Rhumb authentication. The documentation also describes wallet-prefund and x402 payment paths, but the exact availability depends on the requested execution route. Public read-only API endpoints expose service scores and capability readiness; estimates and execution require an authenticated payment path.

Tools and capabilities

The 21 tools cover these areas:

  • Discovery: search services, inspect scores, find alternatives, review failure modes, and browse capabilities.
  • Resolution and execution: rank providers, estimate calls, execute capabilities, inspect credential readiness, and obtain credential setup instructions.
  • Recipes: list published Layer 3 recipes, inspect recipe definitions, and execute a published recipe when it is live in the public catalog.
  • Account and operations: retrieve receipts, set or inspect budgets, review spending, check balances, obtain payment URLs, inspect the ledger, configure routing, and view usage telemetry.

The supertrained/rhumb MCP server is therefore suited to agents that need provider selection and execution controls, rather than a single fixed vendor integration.

Limitations and notes

Discovery breadth does not imply execution readiness. Current callable coverage is narrower than the indexed catalog, and Layer 3 recipes have a sparse public catalog and beta status. Readiness, supported routes, costs, and provider health should be checked from current Resolve responses before execution. Discovery is unauthenticated, but execution is not generally free or unauthenticated; credential and payment requirements vary by route.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Rhumb

supertrained/rhumb is an MCP server that connects agents to Rhumb Index and Rhumb Resolve for external service discovery and supported capability execution. Its main tools search and score services, compare alternatives, resolve providers, estimate and execute calls, inspect credentials, retrieve receipts, and track budgets, spending, and usage telemetry.

Install it by running `npx -y --package rhumb-mcp@latest rhumb-mcp` as a stdio MCP server. Discovery works immediately without configuration, while authenticated execution can be enabled by setting `RHUMB_API_KEY` before the command.

Yes, the README identifies Cursor as an MCP client for the package. Configure Cursor to launch the stdio command `npx -y --package rhumb-mcp@latest rhumb-mcp`; add `RHUMB_API_KEY` when the agent needs authenticated execution.

No, indexed services are not all executable through Rhumb. Check capability resolution and execution readiness before relying on a provider.

It supports governed API keys with prepaid credits and x402/USDC per-call payment where the route supports it. Credential and payment requirements vary by capability; authenticated estimates and execution require an applicable payment path.

Related MCP servers

All in Aggregators All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewRhumb AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/supertrained-rhumb?style=directory)](https://allmcps.com/mcp/supertrained-rhumb)
HTML Embed
<a href="https://allmcps.com/mcp/supertrained-rhumb"><img src="https://allmcps.com/api/badge/supertrained-rhumb?style=directory" alt="Rhumb on AllMCPs" /></a>