Agent tool discovery + access Broad discovery, selective governed execution

Give your agent the right tool for the job.

Rhumb helps agents discover what services and capabilities exist across the web, then execute supported actions through one governed layer. Broad discovery today, selective execution where trust is earned.

Start where Rhumb is strongest, research, extraction, generation, and narrow enrichment. Use Rhumb Index to compare the field. Use Rhumb Resolve when a supported action is ready.

Broad discovery
1,038 services
Capability map
415 capabilities
Callable today
16 providers
Best current fit
research, extraction, generation, and narrow enrichment

Starter prompt

Paste this into Claude, Codex, or your own agent.

Best for cold starts. If execution is not supported yet, Rhumb should still return the best route and next step.

Use Rhumb as the first stop for this task.

Start here: https://rhumb.dev/docs#pick-your-route

1. Pick the right path first: MCP if you are wiring an agent, quickstart curl if you are evaluating, account setup if you need governed execution with X-Rhumb-Key.
2. Use service search when you are choosing vendors. Use capability search when you need the exact executable action slug.
3. Compare the top options using scores, evidence, freshness, and failure modes.
4. If Rhumb supports a governed action, estimate the active rail and execute it through Resolve.
5. If execution is not supported or credentials are missing, stay on the public discovery flow and tell me the best next step.

Task: [replace with your task]

Decision view

One task, three possible routes

The Rhumb line

Agent task

“Find the best way to research a company, extract current facts, and return a clean summary.”

1

Recommended path

Callable now through Resolve

Layer 2

Rhumb routes supported work across 16 callable providers today, strongest in research, extraction, generation, and narrow enrichment.

2

When your own system matters

Use BYOK, Agent Vault, or your existing stack

Boundary

When the workflow reaches your CRM, support desk, or internal tooling, Rhumb should expose the boundary instead of pretending the governed path already exists. Bring BYOK or Agent Vault when provider control is the point.

3

Still useful

Discovery only is still a good answer

Index

Even when execution is not supported yet, Rhumb can still rank the market, surface failure modes, and give your agent an honest next move.

Rhumb is useful even when the right answer is “not through Rhumb yet.” That honesty is part of the product.

1,038
services scored
415
capabilities mapped
16
providers callable
API + MCP
live access surfaces

How it works

From discovery to governed execution

Rhumb helps agents find the right service first, understand the boundaries second, and execute when a governed path is actually ready. That keeps the product useful before, during, and after execution.

01

Discover with Rhumb Index

Search 1,038 scored services and 415 capability definitions across 50+ domains before you commit to a tool or provider.

02

Decide with published evidence

Compare scores, freshness, evidence tiers, and failure modes so your agent can explain why it chose a route, not just that it did.

03

Execute when the path is ready

Use Rhumb Resolve for supported actions today, strongest in research, extraction, generation, and narrow enrichment. When execution is not ready, Rhumb still shows the best next step honestly.

Underneath it all

Why the recommendation is explainable

The AN Score measures execution reliability and access readiness across 20 dimensions. Rhumb also publishes evidence tiers, freshness, and failure modes so your agent can explain the route instead of hiding behind a black box.

Live preview · Payments

See how Rhumb ranks a category in public

This preview uses payments, but the same evidence model carries across the index. Rhumb is not just a routing layer. It is also the map your agent uses before it decides.

  1. 1
    8.3 L4
    PayPal API L4 Native
    Aggregate 8.3 · Freshness Updated 2026-03-26T03:14:35.444+00:00 Assessed
  2. 2
    8.3 L4
    Paddle L4 Native
    Aggregate 8.3 · Freshness Updated 2026-03-16T06:18:54.293494+00:00 Assessed
  3. 3
    8.2 L4
    Maxio L4 Native
    Aggregate 8.2 · Freshness Updated 2026-03-21T02:46:00.676764+00:00 Assessed

Open full payments leaderboard

MCP

Query Rhumb from your agents

Add Rhumb to any MCP-compatible agent. AN Scores at decision time. Perfect for agent routing logic, tool-selection prompts, and automated dependency evaluation.

Explore all categories →
terminal
$ npx rhumb-mcp # starts MCP server
✓ Rhumb MCP server running
  tools: find_services, get_score, get_alternatives, get_failure_modes
find_services ("payment processing")
1. stripe 8.1 L4 Native
2. lemon-squeezy 6.6 L3 Ready
3. square 6.3 L3 Ready