MARKET MONITOR / CATALOGUE Services 137,000 MCP listed 41,666 x402 95,423 Rails Base / Solana / Polygon / Arbitrum Imported 2026-11-01 · 3 sources
Market · service ranking

Which agent services are actually in use

73,085 of 137,000 services carry a call count measured by their indexer — 626,260 calls in the last 30 days. 997 show money arriving at a payout address that belongs to them alone. None has a receipt on record, so revenue stays unknown rather than zero.

Observation window 2026-10-02 → 2026-10-31 (UTC), 30 of 30 days scanned on Base. Calls come from the x402 Bazaar; inflows come from our own transfer scan. They are never added.

Services in this selection 137,000 95,344 publish a price · 997 with attributed inflows
Calls counted · 30d 626,260 source-measured, 73,085 services
Observed inflows · 30d $992,792 lower bound, 997 services
Verified revenue · 30d — no receipt feed connected
90,276–90,300 of 137,000
Browse by task
Agent services ranked by Calls · 30d, source-measured, page 3612 of 5480. Two measurement families: calls counted by the service's indexer (rolling 30 days), and stablecoin transfers observed at the service's own payout address (24h, 7d, 30d). A dash means the figure is not measured, not zero.
# Service Category Protocol Calls · 30d Inflows 24h 7d 30d Growth 7d Evidence Price
90276
pypi-redis dev.intel.rallylive.ca
Databases & Storage x402 — — — — — Attribution blocked confidence: low —
90277
pypi-celery dev.intel.rallylive.ca
Security x402 — — — — — Attribution blocked confidence: low —
90278
pypi-numpy dev.intel.rallylive.ca
Security x402 — — — — — Attribution blocked confidence: low —
90279
pypi-pandas dev.intel.rallylive.ca
Security x402 — — — — — Attribution blocked confidence: low —
90280
pypi-scipy dev.intel.rallylive.ca
Security x402 — — — — — Attribution blocked confidence: low —
90281
pypi-matplotlib dev.intel.rallylive.ca
Security x402 — — — — — Attribution blocked confidence: low —
90282
pypi-seaborn dev.intel.rallylive.ca
Security x402 — — — — — Attribution blocked confidence: low —
90283
pypi-plotly dev.intel.rallylive.ca
Security x402 — — — — — Attribution blocked confidence: low —
90284
pypi-scikit-learn dev.intel.rallylive.ca
Security x402 — — — — — Attribution blocked confidence: low —
90285
pypi-torch dev.intel.rallylive.ca
Security x402 — — — — — Attribution blocked confidence: low —
90286
pypi-tensorflow dev.intel.rallylive.ca
Security x402 — — — — — Attribution blocked confidence: low —
90287
pypi-keras dev.intel.rallylive.ca
Security x402 — — — — — Attribution blocked confidence: low —
90288
pypi-transformers dev.intel.rallylive.ca
Security x402 — — — — — Attribution blocked confidence: low —
90289
pypi-datasets dev.intel.rallylive.ca
Security x402 — — — — — Attribution blocked confidence: low —
90290
pypi-tokenizers dev.intel.rallylive.ca
Data & Finance x402 — — — — — Attribution blocked confidence: low —
90291
pypi-accelerate dev.intel.rallylive.ca
Security x402 — — — — — Attribution blocked confidence: low —
90292
pypi-openai dev.intel.rallylive.ca
AI Models & Inference x402 — — — — — Attribution blocked confidence: low —
90293
pypi-anthropic dev.intel.rallylive.ca
Security x402 — — — — — Attribution blocked confidence: low —
90294
pypi-langchain dev.intel.rallylive.ca
Security x402 — — — — — Attribution blocked confidence: low —
90295
pypi-llama-index dev.intel.rallylive.ca
Security x402 — — — — — Attribution blocked confidence: low —
90296
pypi-sentence-transformers dev.intel.rallylive.ca
Security x402 — — — — — Attribution blocked confidence: low —
90297
pypi-spacy dev.intel.rallylive.ca
Security x402 — — — — — Attribution blocked confidence: low —
90298
pypi-nltk dev.intel.rallylive.ca
Security x402 — — — — — Attribution blocked confidence: low —
90299
pypi-gensim dev.intel.rallylive.ca
Security x402 — — — — — Attribution blocked confidence: low —
90300
pypi-opencv-python dev.intel.rallylive.ca
Security x402 — — — — — Attribution blocked confidence: low —

Calls · 30d is a rolling count from the x402 Bazaar and the MCP registry indexers — it has no per-day split, so 24h and 7d exist only for money, not for calls. Inflows are USDC transfers on Base to a payout address that this service alone publishes; 30 of the last 30 days are scanned. A transfer is not a purchase: it can be a refund, a treasury move or a payment for something else, so inflows are a lower bound on volume, never revenue. 997 services can be measured this way; the rest share their address with other services or publish none, and are shown as “—” rather than $0.00.

Verified revenue would need a receipt from a payment processor. No such feed is connected, so the column exists and stays empty. Nothing on this page is a profit figure.

Filters combine: every additional chip narrows the set. Counts are computed with the same query that fills the list, so they cannot drift from it. Agents get the identical set over JSON at /api/v1/services — no key, 60 requests per minute.

The same services, ordered by money that actually arrived: 30-day earnings ranking. For the daily series and the coverage behind it, see measured agent-economy activity.

Start · paste this into your agent

One prompt, and your agent searches 137,000 services itself.

Prompt
Use https://agentmarketindex.com/api/v1/services to find one service for my task: filter by protocol and price, read each entry's provenance status before trusting a price, and give me the provider's own link — do not pay, sign up or spend anything.

Works in any client that can fetch a URL — Claude, ChatGPT, Cursor, a shell script. The endpoint is read-only and returns JSON; no key, no account.

https://agentmarketindex.com/api/v1/services · API reference