supertrained avatar

Rhumb Mcp

supertrained/rhumb

Rhumb is an agent gateway that scores and routes external tool calls. It indexes over 1,000 services with AN Scores that measure execution quality and access friction, then routes supported capability calls through governed execution rails. Think of it as discovery plus routing: find_services and get_score help agents compare options like Stripe or SendGrid before committing, while execute_capability routes the actual call through the best available provider based on health, cost, and credentials. It exposes 21 MCP tools covering discovery, execution estimates, receipts, and budget enforcement. Discovery works without auth. Execution requires a governed API key or wallet prefund. Best current fit is research, extraction, and generation tasks rather than broad multi-system automation.

GitHub stars
1
tools
21
auth
Secret needed
transport
STDIO
env var
1
last updated
Apr 25, 2026

Tools

21 tools

Public tool metadata for what this MCP can expose to an agent.

find_servicesSearch indexed Services by what you need them to do

Search indexed Services by what you need them to do

No parameter schema in public metadata yet.

get_scoreGet the full AN Score breakdown for a Service: execution quality, access readiness, autonomy level, tier label, and freshness

Get the full AN Score breakdown for a Service: execution quality, access readiness, autonomy level, tier label, and freshness

No parameter schema in public metadata yet.

get_alternativesFind alternative Services, ranked by AN Score

Find alternative Services, ranked by AN Score

No parameter schema in public metadata yet.

get_failure_modesGet known failure patterns, impact severity, and workarounds for a service

Get known failure patterns, impact severity, and workarounds for a service

No parameter schema in public metadata yet.

discover_capabilitiesBrowse Capabilities by domain or search text

Browse Capabilities by domain or search text

No parameter schema in public metadata yet.

resolve_capabilityGiven 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,...

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,...

No parameter schema in public metadata yet.

execute_capabilityCall a Capability through Rhumb Resolve

Call a Capability through Rhumb Resolve

No parameter schema in public metadata yet.

estimate_capabilityEstimate the active execution rail, cost, and health before a Capability call; anonymous direct system-of-record paths also preserve machine-readable execute_readiness handoffs

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

No parameter schema in public metadata yet.

credential_ceremonyGet step-by-step instructions to obtain API credentials for a Service

Get step-by-step instructions to obtain API credentials for a Service

No parameter schema in public metadata yet.

check_credentialsInspect live credential-mode readiness, globally or for a specific Capability

Inspect live credential-mode readiness, globally or for a specific Capability

No parameter schema in public metadata yet.

rhumb_list_recipesList the current published Rhumb Layer 3 recipe catalog

List the current published Rhumb Layer 3 recipe catalog

No parameter schema in public metadata yet.

rhumb_get_recipeGet the full published definition for a Rhumb recipe, including input/output schemas and step topology

Get the full published definition for a Rhumb recipe, including input/output schemas and step topology

No parameter schema in public metadata yet.

rhumb_recipe_executeExecute a published Rhumb Layer 3 recipe once one is live in the public catalog

Execute a published Rhumb Layer 3 recipe once one is live in the public catalog

No parameter schema in public metadata yet.

get_receiptRetrieve an execution receipt by ID

Retrieve an execution receipt by ID

No parameter schema in public metadata yet.

budgetCheck or set your call spending limit

Check or set your call spending limit

No parameter schema in public metadata yet.

spendGet your spending breakdown for a billing period: total USD spent, call count, average cost per call, broken down by Capability and by provider

Get your spending breakdown for a billing period: total USD spent, call count, average cost per call, broken down by Capability and by provider

No parameter schema in public metadata yet.

check_balanceCheck your current Rhumb credit balance in USD

Check your current Rhumb credit balance in USD

No parameter schema in public metadata yet.

get_payment_urlGet a checkout URL to add credits to your Rhumb balance

Get a checkout URL to add credits to your Rhumb balance

No parameter schema in public metadata yet.

get_ledgerGet your billing history: charges (debits), top-ups (credits), and auto-reload events

Get your billing history: charges (debits), top-ups (credits), and auto-reload events

No parameter schema in public metadata yet.

routingGet or set how Rhumb auto-selects providers when you don't specify one in execute_capability

Get or set how Rhumb auto-selects providers when you don't specify one in execute_capability

No parameter schema in public metadata yet.

usage_telemetryGet your execution analytics β€” calls, latency, errors, costs, and provider health for your Rhumb usage

Get your execution analytics β€” calls, latency, errors, costs, and provider health for your Rhumb usage

No parameter schema in public metadata yet.

Sponsors

Configuration

RHUMB_API_KEYsecret

Governed API key for authenticated repeat traffic on X-Rhumb-Key (optional β€” discovery works without auth; execution otherwise needs x402 payment)

Readme

Rhumb

npm version License: MIT MCP Registry

Index ranks. Resolve routes. Rhumb is an agent gateway for external tools: Index scores and compares services; Resolve routes supported capability calls through governed execution rails with receipts.

🌐 rhumb.dev Β· ⚑ Quickstart Β· 🧭 Resolve Β· πŸ’΅ Pricing Β· πŸ“Š Leaderboard Β· πŸ“– Methodology Β· πŸ”‘ Trust

For agents: See llms.txt for machine-readable documentation and agent-capabilities.json for structured capability metadata.


Start in 30 seconds

MCP (recommended)

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

Zero config. Discovery tools work immediately β€” no signup, no governed API key.


View the full README on GitHub

Details

Repository
github.com/supertrained/rhumb
Categories
AI & LLM Tools, Search & Web Crawling
Package
rhumb-mcp
Transport
STDIO
Auth
Required
Registry
MCP registry, active

Related AI & LLM Tools MCP servers

View all
1tharanabope avatarSQL Server MCP (macOS)tharanabope/sql-mcp-mac-windowsSQL Server MCP with RAG capabilities for macOS (Docker SQL Server support)0stars
2westvegh avatarExerciseapiwestvegh/exerciseapi-mcp-serverGive your AI coding agent direct access to 2,198+ exercises via exerciseapi.dev1stars
3studiomeyer-io avatarmcp-armorstudiomeyer-io/mcp-armorSecurity sidecar for MCP servers: 11 read-only control-plane tools for prompt-injection checks.1stars
4kansei-link avatarKansei Mcp Serverkansei-link/kansei-mcp-serverReduce your AI agent's token waste with collective intelligence β€” SaaS integration recipes1stars
5legatolabs avatarLegatolegatolabs/legatoA computer for any agent: a desktop container, your screen or the cloud, with settled screenshots.1stars
6lo-nau avatarLocalgym Mcp Serverlo-nau/localgym-mcp-serverRead-only MCP server for UK gym search using the LocalGym Agent API.1stars