Getting Started · March 18, 2026 · Updated March 18, 2026

Give your agent tool intelligence

One command. 16 tools. 200+ scored services.

Rhumb MCP gives your AI agent live access to tool scores, failure modes, cost estimates, and capability execution. Install it in 30 seconds and your agent knows which API to pick, what will break, and how much it will cost — before making a single call.

Install
npx rhumb-mcp@0.7.0

No API key required for discovery and scoring. Add to any MCP-compatible client.

What your agent gets

16 MCP tools organized into four categories. Your agent can discover tools, check their quality, execute capabilities through Rhumb's proxy, and manage its budget — all through natural tool calls.

Discover
find_tools
Search for services by what you need
discover_capabilities
Browse capabilities by domain
resolve_capability
Rank providers for a capability
Score
get_score
Full AN Score breakdown for a service
get_alternatives
Similar services, ranked
get_failure_modes
Known failure patterns
Execute
estimate_capability
Cost estimate before execution
execute_capability
Execute through Rhumb proxy
ceremonies
Setup guides for credential modes
credentials
Check credential status
routing
Routing strategy configuration
Budget
budget
Budget status and limits
spend
Spend breakdown by capability
check_balance
Current credit balance
get_payment_url
Top up via Stripe checkout
get_ledger
Transaction history

Setup

Add Rhumb MCP to your agent framework. Same config works everywhere.

Claude Desktop

{
  "mcpServers": {
    "rhumb": {
      "command": "npx",
      "args": ["rhumb-mcp@0.7.0"]
    }
  }
}

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%/Claude/claude_desktop_config.json (Windows). Restart Claude Desktop.

Cursor / Windsurf / any MCP host

{
  "mcpServers": {
    "rhumb": {
      "command": "npx",
      "args": ["rhumb-mcp@0.7.0"]
    }
  }
}

Same configuration format. Add to your editor's MCP settings file.

Direct stdio (any framework)

npx rhumb-mcp@0.7.0

The server speaks MCP over stdio. Pipe it into any MCP-compatible client: LangChain MCP Adapters, CrewAI, AutoGen, or custom implementations.

Workflows

Three real workflows showing how an agent uses Rhumb MCP tools together. Each starts with a scenario and walks through the tool calls step by step.

1

Find the best tool for a job

Your agent needs to send an email but doesn't know which provider to use.

1
find_tools ("send transactional email")

Returns ranked services: Resend (7.8), SendGrid (5.5), Postmark (7.5), Amazon SES (7.5) — sorted by AN Score.

2
get_score ("resend")

Full breakdown: execution 8.7, access readiness 6.8, confidence 93%. Explanation of why it scores high.

3
get_failure_modes ("resend")

Known failure patterns — webhook delivery delays under burst, 429 rate limit behavior, etc.

2

Execute a capability through Rhumb

Your agent decides Resend is the right choice and wants to send an email through Rhumb's proxy.

1
resolve_capability ({ capability: "email.send" })

Returns ranked providers with live availability, cost per call, credential status, and circuit state.

2
estimate_capability ({ capability_id: "email.send", provider: "resend" })

Cost estimate before execution: $0.001/call, budget remaining, can_afford: true.

3
execute_capability ({ capability_id: "email.send", body: { to: "user@example.com", subject: "Hello", html: "<p>Hi</p>" } })

Email sent through Resend via Rhumb proxy. Response includes execution time, cost, and upstream status.

3

Manage agent budget and spend

Your agent has a daily budget and needs to track spend across providers.

1
budget ((no args))

Current budget status: daily limit, remaining, period reset time.

2
spend ((no args))

Spend breakdown by capability and provider. Which tools cost the most, where budget is going.

3
check_balance ((no args))

Credit balance in USD. If low, use get_payment_url to top up via Stripe or x402 USDC.

What's in the dataset

212
Services scored
103
Capabilities
30
Domains

Domains include: payments, email, CRM, auth, databases, analytics, communication, storage, search, monitoring, e-commerce, AI/ML, and 18 more. Every service is scored on the same 20-dimension methodology.

Scores update as we gather new evidence. When you call get_score, you get the latest data — not a static snapshot.

Direct API access

Prefer REST? The same data is available via HTTP. No API key needed for read endpoints.

GET https://api.rhumb.dev/v1/services

List all 212 scored services

GET https://api.rhumb.dev/v1/services/stripe/score

Full score breakdown with failure modes

GET https://api.rhumb.dev/v1/capabilities/email.send/resolve

Ranked providers for a capability

GET https://api.rhumb.dev/v1/leaderboard/payments

Category leaderboard, sorted by AN Score

Full API reference at rhumb.dev/docs. Machine-readable description at rhumb.dev/llms.txt.

Three ways to bring credentials

When executing capabilities, Rhumb supports three credential modes — pick the one that fits your security model.

Mode 1 BYO (Bring Your Own Keys)

Pass your own API keys at execution time. Rhumb routes the request, you own the credential. Full control, no credential storage.

Mode 2 Rhumb-Managed

Rhumb holds the upstream credential. Agent provides capability + body, Rhumb handles auth. Zero-config for the agent. 20% markup on upstream cost.

Mode 3 Agent Vault

Agent brings a JWE-encrypted credential token. Rhumb decrypts at execution time, never stores. Highest security — the credential is never at rest in Rhumb.