    
    Report · auto-updating
  

State of the agent economy

Live measurement of the agent web: supply funnel, live-rate by ecosystem, protocol adoption, inflow concentration, and 30-day growth. Data refreshes every five minutes from the same observability spine that powers every public Agenstry page.

    As of 2026-11-03 16:04:17 UTC
    methodology
    JSON
    CSV
    cite this
    archive
  

Weekly briefing · 2026-W45 archived view

        Nov 2, 2026
      

Agenstry’s W45 snapshot shows the measured economy widening, with live listings and listings linked to recent USDC receipts growing faster than the indexed corpus. But W45 data are only a Monday snapshot, and the underlying picture remains divided: payment claims are not the same as runtime-proven services, while recorded revenue is highly concentrated.

More listings are passing the live probe

The indexed corpus reached 11,034 listings, up 706 (+6.8%) from W44. Live endpoints rose to 1,507, up 138 (+10.1%); 9,594 listings returned a parseable A2A/MCP card, and 243 had a JWS signature. These are distinct evidence thresholds: a parseable card does not establish runtime availability, and a signature does not by itself demonstrate that a service is reachable.

Source-level live rates continue to vary considerably. The registry and A2A registry sources recorded live rates of 51.7% and 52.3%, while agentic_market was at 4.5%; n8n_workflows had no listings classified as live under this probe. These are not comparable quality rankings: source populations and listing types differ. The pattern does reinforce the operational gap between being discoverable and answering a live probe.

x402 still leads; W45 is not a full-week read

The corpus lists 6,543 x402 payment records, compared with 131 for MPP, 79 for A2A x402 and 40 for AP2. The W45 cohort contains 51 entries—50 x402 and 1 A2A x402—but the week began on November 2, the data cutoff. It is therefore an intake snapshot, not a full-week adoption comparison with W44’s 722 entries.

Evidence quality remains material to interpreting those declarations. Of 6,800 labelled payment records, 3,517 are classified as self-declared live: an endpoint answered an unpaid request with an HTTP 402 challenge or served an x402 manifest. The remaining records rely on cards, directories or catalog listings. Agenstry’s note is explicit that runtime challenges remain authoritative.

The official MCP repository showed implementation and documentation work rather than a newly released specification during the week: an October 29 pull request proposes restoring optional _meta fields, and another points Skills specification links to the beta specification. These are repository changes, not a new stable MCP version. MCP specification repository pull requests The latest stable specification release listed by the project remains dated July 28, 2026. MCP releases

Earning reach expands, but receipts remain concentrated

Agenstry counted 4,736 earning listings over the measured 30-day window, up 651 (+15.9%) week over week. The measure tracks listings whose declared payTo wallet received inbound USDC; 2,897 of 3,045 wallets with a wallet were scanned so far. Multiple listings can share a wallet, and earning is not a subset of Live: many paid APIs return a 402 challenge instead of responding to a free JSON-RPC probe. This is a measured sample, not an ecosystem-wide revenue census.

Gross receipts in the window were $871,242. The median was $0.295, while the top listing accounted for 66.7% of receipts and the top 10 for 89.0%; the Gini coefficient was 0.994. The number of listings linked to recent receipts is growing, but these figures do not establish broad or evenly distributed commercial demand. The HHI fell to 4,531.1 from 5,369, down 838 (-15.6%); concentration remains high even as that measure eased.

Capital and policy focus on deployed agents

Phonic announced Phonic-1, a speech-to-speech model for agent tasks, alongside a $27.5 million Series A led by First Round. The company says the round brings its total funding to $31.5 million; those are company-reported claims, and the announcement also cites an external benchmark for its model comparison. Phonic announcement

On policy, the UK Information Commissioner’s Office has opened a call for evidence on how data-protection law applies to agentic AI’s capabilities and risks. It is a consultation, not a new binding rule, but it makes data use and accountability for agent actions a live governance question for deployers. ICO call for evidence

What to watch next week

The next useful comparison is a complete W45 cohort against W44, especially whether x402 remains dominant once the Monday-only intake is replaced by a full-week measure. For payment providers and buyers, the more consequential signal is whether growth in earning listings is accompanied by receipts that are less concentrated.

Sources

1 · Supply funnel

Most of the agent economy is indexed, not yet operational.

Counting agents conflates supply with operation. Below is the corpus broken into five stages: what fraction of indexed agents pass each gate. The decay curve is the honest read on how mature the agent web is at any given moment.

Stage	Count	% of indexed	Definition
Indexed	11,201	100.0%	Every listing we hold across every source; 3,468 archived listings are not counted here or in any step below.
Valid card	9,755	87.1%	Returned a parseable A2A/MCP card on probe.
Live	1,541	13.8%	Live JSON-RPC / introspectable MCP.
Signed	248	2.2%	Card published with a JWS signature.
Earning (30d)	4,894	43.7%	Listings whose declared payTo wallet received inbound USDC in the last 30 days (2,228 distinct wallets; several listings can share one). Measured over the wallets scanned so far (2,960 of 3,134 with a wallet) — not an ecosystem-wide total. Not a subset of Live: most are paid APIs, which answer 402 rather than a free JSON-RPC probe.

2 · Live-rate by ecosystem

Which source registries actually ship live agents.

Each row shows one source registry (Anthropic's MCP directory, Smithery, Glama, Postman, GitHub well-knowns, Wayback CDX scans) alongside how many of the agents it lists actually respond live on probe. The gap between seen-count and live-count is the source's effective freshness.

Source	Seen	Live	Live rate
agentic_market	5,801	270	4.7%
cdp_discovery	5,402	357	6.6%
manifests	2,341	547	23.4%
mcp_registry	1,747	277	15.9%
n8n_workflows	1,445	0	0.0%
x402_list	1,388	181	13.0%
smithery	1,080	258	23.9%
registry	965	490	50.8%
github_code	905	77	8.5%
a2a_registry_org	816	427	52.3%
a2aregistry	812	461	56.8%
lists	560	64	11.4%
8004scan	219	53	24.2%
dexter_discovery	207	1	0.5%
github_topics	165	9	5.5%

3a · By protocol kind

A2A vs MCP vs paid_api

paid_api

6,350

a2a_agent

3,406

workflow

1,445

3b · By observed payment-protocol label

Index composition, not global market share. x402 has multiple dedicated catalogs and a live HTTP probe; AP2, L402 and Stripe ACP are predominantly visible only when cards declare them.

x402 / AP2 / Stripe MPP / L402

x402

6,673

mpp

133

a2a_x402

ap2

l402

stripe_acp

3b · Evidence grade

How we know they take payment

3,570 of 6,936 payment-labelled agents (51.5%) proved it themselves — their own endpoint answered an unpaid request with an HTTP 402 challenge, or the host serves a /.well-known/x402 manifest. The rest is declared in a static agent card or described by a third-party catalog.

Live 402 challenge

2,928

Facilitator feed

2,205

Agent card

729

/.well-known/x402

503

Catalog listing

420

mpp_manifest

103

mpp_challenge

Official protocol directory

3c · Indexed protocol labels over time · last 12 weeks

Newly indexed agents per week, by payment label

Changes reflect both ecosystem activity and changes in crawler source coverage.

a2a_x402 ap2 l402 mpp stripe_acp x402

4 · Inflow concentration · 30d

A few settlement wallets receive most of the money.

Across 2,228 earning wallets backing 4,894 linked services, the distribution is heavily power-law. Wallet-level Gini and HHI avoid multiplying transfers when several catalog entries share one recipient.

Observed inflow · 30d

$891,254.83

Recipient wallets

2,228

Active sellers · 30d

2,026

Median · wallet

$0.300

p95 · wallet

$99.37

Top 1 share

65.2%

Top 5 share

81.2%

Gini

0.993

extreme inequality

HHI

4336

highly concentrated

5 · 30-day growth

New agents arriving daily, by first-seen.

Daily count of agents we discovered for the first time. Sourced from every registry + open-web crawl we run.

      2026-10-05
      peak 363/day
      2026-11-03
    

New agents · 30d

+3,557

New earning wallets · 30d

755

first observed earning in the last 30 days

6 · Demand gaps

What the market asked for and didn't get.

Every section above measures the supply we indexed. This one measures demand we couldn't serve: clustered search intents — from browsers, AI assistants and agents calling our A2A and MCP endpoints — where the index returned nothing or almost nothing. Aggregate only, and shown only for intents searched by enough distinct sources to be a market signal rather than one person's session.

Intent	Demand	Unmet	Trend
aidata	active	43%	new
bitcoin+payment	very active	40%	rising

Full list + method: what the agent economy is missing. Building one of these? Add pay-per-call payments to your API →

Cite this report

Public domain numbers (CC BY 4.0). Pick the format that fits. The page auto-updates so the URL is the canonical pointer; the date stamps the snapshot you cited.

Plain text

Agenstry Research. "State of the Agent Economy." Accessed 2026-11-03. https://agenstry.com/reports/state-of-agent-economy

BibTeX

@misc{agenstry_state_of_agent_economy,
  title  = {State of the Agent Economy},
  author = {Agenstry Research},
  url    = {https://agenstry.com/reports/state-of-agent-economy},
  note   = {Accessed 2026-11-03},
  year   = {2026}
}

Embed (iframe)

<iframe src="https://agenstry.com/reports/state-of-agent-economy" width="100%" height="900" frameborder="0"></iframe>

Scope What this report measures, and what it doesn't

Inflow figures count public stablecoin transfers into wallets declared by indexed agents. They are reproducible from public chains, but a transfer may be self-funded and is not proof of a sale. See the measurement method.

Private and off-chain payments, and Agenstry's own paid-skill receipts, are excluded. Coverage varies by chain, asset and date.

Methodology

This report uses dated observations from the public index. Check source coverage, scoring rules and the public feed before comparing it with another dataset.