budget
Check or set your call spending limit. Budgets are enforced BEFORE a call — you get HTTP 402 (not a surprise bill) when you'd exceed your limit. Call with no params to check current budget and remaining balance.
LABSCO SUMMARY
Makes the cost, the auth friction and the failure modes visible before the integration is written.
Choosing an external service rarely fails on features; it fails on signup friction, unstable schemas and errors nobody is watching for. The failure-modes and credential-ceremony calls put both of those on the table up front, and they cost nothing to ask. If you go on to execute through it, set the budget first — it is enforced before the call, so an overrun is a refused request rather than a surprise on the invoice — and keep the receipts, since each one carries the provider, the routing explanation and an integrity hash for the execution it describes.
What it is
Two halves behind one connection. The index scores and compares services and the capabilities they fulfil; the execution side routes a supported capability call to a provider, applies your budget and routing policy, and returns an auditable receipt for what it did.
What you get
- Services searched by what you need done rather than by name, returned ranked, with the full score breakdown for any one of them — execution quality, access readiness, autonomy level, tier and freshness
- Alternatives to a service ranked the same way, for when the first choice does not fit
- Known failure patterns for a service with severity and workarounds, which is worth reading before you write the integration rather than after the first error
- Capabilities browsed as actions that several providers can fulfil — the level to search at when you know what you need doing but not who does it
- A capability resolved into ranked providers with health status, cost per call, auth methods, endpoint patterns and machine-readable recovery hints, including a correction when the capability id is wrong
- Step-by-step credential instructions for a service: signup steps, the token format to expect, a verification endpoint, how long it takes and whether a human has to be involved
- Readiness inspected across credential modes, globally or per capability, so you know what can run right now
- Cost controls before the fact: an estimate of the rail, cost and circuit health before a call; a budget enforced ahead of execution so exceeding it returns a refusal rather than a bill; a routing policy trading cost against speed and quality with a minimum score floor and an optional per-call ceiling
- The money side visible: spending broken down by capability and provider for a period, credit balance with auto-reload status, a checkout URL to top up, and a billing ledger of charges and credits
- Execution analytics over your own usage — calls, latency, errors, costs and provider health
- An immutable chain-hashed receipt for every execution recording the provider used, cost breakdown, latency, routing explanation and integrity hash
- Published multi-step recipes listed and read before being run, executed through the same capability rail with per-step results and a receipt chain
Requirements
Nothing for discovery — scoring, comparison, failure modes and capability resolution work with no signup at all, and the same read endpoints are public over HTTP. Execution is the part that needs a governed API key in RHUMB_API_KEY, and it spends money: calls draw on a Rhumb credit balance, so the budget and routing settings are the controls worth setting before an agent runs unattended. It starts as npx -y --package rhumb-mcp@latest rhumb-mcp. Scope matters here — the index covers far more services than the execution side can call today, and the multi-step recipe catalogue is in beta and can be empty, which is why the listing tool exists to check before assuming a workflow is live. MIT.
Setup effort
One command — npx -y --package rhumb-mcp@latest rhumb-mcp
USE CASES
01
Picking a service for a job you have not integrated before
Search by what you need done, read the score breakdown for the leading candidates, and look at the alternatives in the same category before committing.
02
Writing defensively before the first call
Read the known failure patterns with their severity and workarounds, and the credential steps including whether a human has to be in the loop.
03
Finding who can perform an action at all
Browse capabilities by domain, then resolve one into ranked providers with health, cost per call and endpoint patterns.
04
Making a call without a surprise bill
Estimate the rail and cost first, set the budget that is enforced before execution, then run the capability.
05
Auditing what an agent actually did
Pull the receipt for an execution — provider used, cost breakdown, latency, routing explanation and integrity hash — and the ledger behind the charges.
06
Deciding how calls get routed when you do not name a provider
Set the strategy across cost, speed and quality with a minimum score floor, then check the analytics to see how it is playing out.
07
Checking what is ready to run right now
Inspect credential readiness across modes and the current credit balance, and get a top-up URL to hand to a person if it is low.
21 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
check_balance
Check your current Rhumb credit balance in USD. Also shows whether auto-reload is enabled. If balance is low, use get_payment_url to top up.
check_credentials
Inspect live credential-mode readiness, globally or for a specific Capability. Call without params to see which BYOK bridges or direct bundles are already configured and which Capabilities are ready now through Rhumb-managed rails. Pass a Capability to inspect provider-level mode status, configured readiness, and ceremony availability for that specific path.
credential_ceremony
Get step-by-step instructions to obtain API credentials for a Service. Returns signup steps, expected token format (prefix, pattern), verification endpoint, estimated time, and whether human intervention is needed. Use before calling in agent_vault mode. Call without params to list all Services with available ceremonies.
discover_capabilities
Browse Capabilities by domain or search text. A Capability is an action (e.g. 'email.send', 'payment.charge') that multiple providers can fulfill. Use this when you know WHAT you need to do but not which Service does it. Returns Capability IDs for resolve_capability. Different from find_services: find_services searches Services, this searches Capabilities.
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. Returns cost in USD, circuit health, and endpoint pattern. Default credential mode is auto: Rhumb uses Rhumb Resolve when an active managed config exists, otherwise falls back to byok. Legacy 'byo' is still accepted as an input alias. Always call this before execute_capability for cost-sensitive workflows — no charge for estimates.
execute_capability
Call a Capability through Rhumb Resolve. Typical workflow: discover_capabilities → resolve_capability → estimate_capability → execute_capability. Default credential mode is auto: Rhumb uses Rhumb Resolve when an active managed config exists, otherwise falls back to byok. Legacy 'byo' is still accepted as an input alias. Other explicit modes: rhumb_managed — zero-config through Rhumb Resolve when available; byok — BYOK via agent_token + method + path; agent_vault — use a key from credential_ceremony via agent_token + method + path. Alternative: pass x_payment for a per-call USDC payment with no account needed. Use check_credentials to inspect live readiness globally or for a specific Capability before choosing a rail.
find_services
Search indexed Services by what you need them to do. Returns ranked Services with AN Scores. Use this when you know the problem but not which Service to call. For Capability-level search (e.g. 'email.send'), use discover_capabilities instead.
get_alternatives
Find alternative Services, ranked by AN Score. Use when a Service doesn't meet your needs or you want to compare options in the same category.
get_failure_modes
Get known failure patterns, impact severity, and workarounds for a service. Use BEFORE integrating to write defensive code, or AFTER hitting an error to diagnose it.
get_ledger
Get your billing history: charges (debits), top-ups (credits), and auto-reload events. Each entry shows amount, balance after, description, and timestamp. Most recent first.
get_payment_url
Get a checkout URL to add credits to your Rhumb balance. Present this URL to a human to complete payment. Credits are available immediately after payment.
get_receipt
Retrieve an execution receipt by ID. Every Resolve v2 execution produces an immutable, chain-hashed receipt containing: provider used, cost breakdown, latency, routing explanation, and integrity hash. Use this to audit, debug, or verify any past execution. The receipt_id is returned in every execute_capability response when v2 policy parameters are used.
get_score
Get the full AN Score breakdown for a Service: execution quality, access readiness, autonomy level, tier label, and freshness. Use after find_services to evaluate a specific Service.
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. If the capability ID is wrong, returns a capability search URL plus suggested capabilities instead of a blank dead end. This is the core routing decision: 'I need email.send, and maybe a specific credential mode, which provider or recovery handoff should I use?' Call this before execute_capability to understand your options.
rhumb_get_recipe
Get the full published definition for a Rhumb recipe, including input/output schemas and step topology. Call this only after rhumb_list_recipes confirms the recipe is currently in the public catalog.
rhumb_list_recipes
List the current published Rhumb Layer 3 recipe catalog. Use this to check what is actually live before assuming a deterministic multi-step workflow exists; the public catalog can be empty while Layer 3 remains in beta.
rhumb_recipe_execute
Execute a published Rhumb Layer 3 recipe once one is live in the public catalog. Rhumb runs the multi-step workflow through the existing Layer 2 capability rail, applies recipe safety controls, and returns per-step results plus a recipe-level receipt chain hash.
routing
Get or set how Rhumb auto-selects providers when you don't specify one in execute_capability. Controls the tradeoff between cost, speed, and quality. Also sets a quality floor (minimum AN Score) and optional per-call cost ceiling.
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. Use to audit costs or optimize routing.
usage_telemetry
Get your execution analytics — calls, latency, errors, costs, and provider health for your Rhumb usage.
BEFORE YOU INSTALL
What to know first
Tools you get
21 tools when we connected. Governed execution covers 16 callable providers (18 elsewhere in the documentation) out of 1,038 scored services. The recipe catalog can be empty, so check rhumb_list_recipes before assuming a workflow exists.
Requires
- npx on PATH
- Node 24+
CONTEXT COST
Moderate Standing cost
Rated by the size of the 21 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Server setup
Any MCP client — no auth
TERMINAL
npx -y --package rhumb-mcp@latest rhumb-mcpMCP Clients
Any MCP client — API key
ANY MCP CLIENT — API KEY · TERMINAL
RHUMB_API_KEY=<YOUR_RHUMB_API_KEY> npx -y --package rhumb-mcp@latest rhumb-mcpOther routes
REST API — curl
REST API — CURL · TERMINAL
curl "https://api.rhumb.dev/v1/services/stripe/score"
curl "https://api.rhumb.dev/v1/capabilities/email.send/resolve"
