The Green Pages · live agent index

The Green Pages
for the agents
economy.

Yellow Pages was for humans dialing businesses. Prowl is what agents read when they pick which API to call — — SaaS APIs crawled, probed, and benchmarked against ground truth. Scored, ranked, live.

Benchmark a URL Explore the index →

Free for agents, forever

MCP native

x402 · pay-per-query

PROWL / MAP LIVE

2,500 indexed · ranked

TOP RANKstripe · 96.8

↗ Open the live map

SNAPSHOT FREEZESFriday · 23:59 UTC

01 · Try it

Drop any API URL. Watch Prowl read, plan, probe, and score it.

Live simulation. Real endpoint: POST /v1/benchmark/url

Orchestrator ready

Run a 5-phase LLM benchmark in ~12 seconds.

Analyze · Plan · Onboard · Execute · Interpret. We read the spec, generate tests, run real calls, and normalize to a 0–100 score. Free, rate-limited 5/hr.

api.stripe.com

IDLE · press Prowl it

—/100

accuracy

—

latency

—

uptime

—

schema

—

errors

—

mcp

—

ANALYZE PLAN ONBOARD EXECUTE INTERPRET

02 · Verified, not self-reported

Scores come from reality. Not decks.

8 dimensions · weighted · published methodology

01 / ACCURACY

Ground-truth benchmarks

Weather against NOAA. Geocoding against OSM. Translation against BLEU. You can't game the sources.

02 / LATENCY

Probed from 3 regions

p50, p95, p99 — every five minutes. Regional latency maps included. No handwaving about "fast".

03 / SCHEMA

Drift detection

We diff your OpenAPI on every crawl. Added, removed, renamed — breaking changes flagged before agents break.

04 / AGENT-READY

Self-onboarding

Can an agent register without a human? Onboarding strategies tested: email, crypto wallet, OAuth, public. No CAPTCHAs, no KYC.

03 · Live index

The top of the prowl, right now.

Top-scored services · sorted by ASO · updated 02m ago

SERVICE

SCORE

P95

UPTIME

Own one of these?

Your API has an ASO score whether you claim it or not.

Unclaimed services cap at 75/100. Verify a domain (DNS TXT, .well-known, or meta tag) to unlock the full range and earn a Verified badge.

First benchmarkFree

Re-benchmarks$1.00 · $PROWL

Verification methods3

Claim your listing

04 · How it works

Two sides of the same network.

Agents read. Vendors get read.

FOR AGENTS ~30 seconds to first query

One endpoint. The entire SaaS ecosystem.

Instead of learning 500 APIs, learn one. Register, discover, consume. We do the reading so your context doesn't have to.

Register. POST /v1/auth/agents/register — returns an ak_ key.
Discover. GET /v1/discover?q=payments&sort=score
Trust. GET /v1/metrics/{id}/verified — benchmarks vs ground truth.
Report. POST /v1/feedback — close the loop, earn a discount.

# one-liner. free. no key needed for GET /discover
curl prowl.world/v1/discover?q="geocoding"&sort=score \
  -H "X-Agent-Key: ak_..."
→ 12 results, ranked · p95 latency · verified badge

FOR VENDORS Free listing · paid proof

Agents can't find you. Your ASO score says why.

SEO made sites findable by humans. ASO makes APIs findable by agents. Free to list, pay to prove you're good.

Get crawled. If your API is public, you're already indexed.
Claim. Prove ownership via DNS, well-known file, or meta tag.
Benchmark. First one free. Re-runs $1.00 — pay in $PROWL.
Fix. Audit report points at exactly which dimension is dragging your score.

# audit report, free for vendors
GET prowl.world/v1/audit/{service_id}
→ breakdown.schema_stability: 4.2/10
→ fix: maintain backward-compat aliases ≥ 90d
→ impact: +8 points

06 · For builders

Design endpoints agents can actually use.

prowl-design · static review + live multi-LLM test · same infra as prowl-bench

REVIEW Static · $0.02 · ~3s

Score an OpenAPI fragment before you ship it.

Parseability, token bloat, error clarity, auth simplicity, schema gotchas — graded against the same priors Prowl uses to benchmark live APIs. Concrete rewrites included. 3 reviews/day free without an account; 10/day logged-in.

# score a spec, free tier or $0.02 via x402
curl prowl.world/v1/endpoint/review -X POST \
  -d '{"spec_url":"https://api.you/openapi.json"}'
→ parseability 6.2/10 · token-bloat 4.1/10
→ fix: paginate with `cursor`, not `offset`+`limit`

LIVE TEST Multi-LLM · $0.05 · ~8s

See exactly which model breaks on your endpoint.

Claude and GPT-4o hit the URL with the spec you ship. We return per-model traces — "Claude parsed first try, GPT-4o retried because pagination uses next_cursor."

# live test against a real URL
curl prowl.world/v1/endpoint/test -X POST \
  -d '{"spec_url":"...","target_url":"...","method":"GET"}'
→ claude: 1 call, 200 OK
→ gpt-4o: 3 retries, schema confusion on `cursor`

Free tier3/day anon · 10/day logged-in

Local CLIprowl-bench design ui · unlimited offline

Sign + publishMycelio manifest stored at /v1/mycelio/manifests/{slug}

Try Prowl Design → prowl-bench source

05 · What the agent sees

No dashboard. Just JSON.

The whole product. Rendered by your model.

GET /v1/discover?q=weather

We optimize for the next token, not the next tab.

Prowl is an API. The only HTML on prowl.world is this page — and it is designed to get out of the way. Claude, GPT, Mistral, or a custom orchestrator parses the response in milliseconds.

Tabs swap the endpoint. Response is the whole UI.

GET/v1/discover?q=weather200 OK · 142ms

The Green Pages
for the agents
economy.

Paste any of these into your agent — Claude, ChatGPT, Cursor, anything.

Drop any API URL. Watch Prowl read, plan, probe, and score it.

Run a 5-phase LLM benchmark in ~12 seconds.

Scores come from reality. Not decks.

Ground-truth benchmarks

Probed from 3 regions

Drift detection

Self-onboarding

The top of the prowl, right now.

Your API has an ASO score whether you claim it or not.

Two sides of the same network.

One endpoint. The entire SaaS ecosystem.

Agents can't find you. Your ASO score says why.

Design endpoints agents can actually use.

Score an OpenAPI fragment before you ship it.

See exactly which model breaks on your endpoint.

No dashboard. Just JSON.

We optimize for the next token, not the next tab.

Every paid query settles in $PROWL on Solana.

The agent economy runs on discovery.
Be the thing it finds.

The Prowl Network

The Green Pages for the agents economy.

Paste any of these into your agent — Claude, ChatGPT, Cursor, anything.

Drop any API URL. Watch Prowl read, plan, probe, and score it.

Run a 5-phase LLM benchmark in ~12 seconds.

Scores come from reality. Not decks.

Ground-truth benchmarks

Probed from 3 regions

Drift detection

Self-onboarding

The top of the prowl, right now.

Your API has an ASO score whether you claim it or not.

Two sides of the same network.

One endpoint. The entire SaaS ecosystem.

Agents can't find you. Your ASO score says why.

Design endpoints agents can actually use.

Score an OpenAPI fragment before you ship it.

See exactly which model breaks on your endpoint.

No dashboard. Just JSON.

We optimize for the next token, not the next tab.

Every paid query settles in $PROWL on Solana.

The agent economy runs on discovery.Be the thing it finds.

The Prowl Network

The Green Pages
for the agents
economy.

The agent economy runs on discovery.
Be the thing it finds.