    
    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 2026-10-26 16:25:27 UTC
    methodology
    JSON
    CSV
    cite this
    archive
  

Weekly briefing · 2026-W44 archived view

        Oct 26, 2026
      

Agenstry’s measured agent economy expanded in W44, but the clearest signal is still the gap between discovery, operation and payment: indexed listings grew faster than live endpoints, while the 30-day earning count rose sharply. Meanwhile, x402 remains the dominant declared payment rail, and this week’s cohort is only a Monday snapshot—not a full-week adoption comparison.

Reach is widening; runtime proof still lags

The indexed corpus reached 10,328 listings, up 797 (+8.4%) from W43. Live endpoints rose to 1,369, an increase of 40 (+3.0%). The funnel remains sharply selective: 8,960 listings returned a parseable A2A/MCP card, 1,369 were live on JSON-RPC or introspectable MCP, and 245 published a JWS signature. A listing, a working endpoint and a signed card are distinct evidence levels.

Source-level live rates vary widely: a2aregistry stands at 55.3%, registry at 49.7%, and agentic_market at 5.1%. These are not like-for-like quality rankings; source populations and inclusion criteria differ. They do, however, underline why registry presence alone is a weak proxy for availability.

Payment records: x402 dominates, but evidence matters

The corpus records 6,125 x402 listings, compared with 129 for MPP, 77 for A2A x402 and 39 for AP2. The W44 cohort currently contains 41 entries, all x402. Because W44 began on October 26 and the data are as of 13:28 UTC that day, this is a partial-day intake, not evidence of a full-week shift in protocol share.

Evidence quality remains mixed. Of 6,375 labelled payment records, 3,090 are classified as self-declared live: the endpoint itself answered an unpaid request with an HTTP 402 challenge or served an x402 manifest. The rest rely on static cards, directories or catalog listings. Runtime challenges remain the stronger evidence of an endpoint’s payment behavior.

The x402 repository’s activity this week reflects implementation work as well as feature proposals. Issues and pull requests include reports about payment-wrapper multi-network handling, payment-header parsing, facilitator failures and price controls before signing; these are reports and proposed changes, not proof of widespread incidents. They nevertheless make interoperability and spending safeguards concrete implementation priorities. x402 issue tracker x402 pull requests

Revenue is growing in reach, not yet broadly distributed

Agenstry counted 4,085 earning listings over the measured 30-day window, up 740 (+22.1%) week over week. That count represents listings whose declared payTo wallet received inbound USDC; it is measured across wallets scanned so far, not an ecosystem-wide revenue census. The sample includes 2,705 of 2,926 listings with a wallet, and several listings can share one wallet. Earning is also not a subset of Live: many paid APIs return a 402 challenge rather than responding to a free JSON-RPC probe.

Gross receipts were $822,818.01. Distribution remains exceptionally concentrated: the top listing accounts for 72.8% of receipts, the top 10 for 91.6%, and the Gini coefficient is 0.994. The median is $0.2964, a reminder that a rising earning-listing count should not be read as broad-based commercial traction. The 30-day count of new agents reached 3,364, up 352 (+11.7%) from W43; the data do not establish how many will become durable, live services.

Spec and implementation: practical tooling advances

No major A2A or MCP specification release surfaced in this week’s sources. A2A’s published releases still list v1.0.1 as the latest release, while its roadmap identifies v1.1 robustness and bidirectional streaming as work in progress. A2A releases A2A roadmap

A more immediate deployment update came from MuleSoft’s October 21 release: Agent Fabric added local agent-network deployment and A2A chat testing in Anypoint Code Builder, OAuth 2.0 client-credentials authentication for LLMs, and support for reusing MCP assets that use SSE transport. These are product capabilities, not protocol changes, but they target the practical work of testing and connecting agent networks. MuleSoft release notes

What to watch next week

The key test is whether W44’s x402-heavy intake holds once a full week is observed, and whether the additional earning listings translate into less concentrated receipts. In parallel, payment implementers should track whether the reported SDK and safeguard issues become merged fixes or remain open proposals.

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	10,339	100.0%	Every listing we hold across every source; 3,135 archived listings are not counted here or in any step below.
Valid card	8,962	86.7%	Returned a parseable A2A/MCP card on probe.
Live	1,367	13.2%	Live JSON-RPC / introspectable MCP.
Signed	245	2.4%	Card published with a JWS signature.
Earning (30d)	4,085	39.5%	Listings whose declared payTo wallet received inbound USDC in the last 30 days (2,011 distinct wallets; several listings can share one). Measured over the wallets scanned so far (2,705 of 2,931 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	5,183	263	5.1%
cdp_discovery	4,480	315	7.0%
manifests	2,076	453	21.8%
mcp_registry	1,747	277	15.9%
n8n_workflows	1,377	0	0.0%
x402_list	1,186	104	8.8%
smithery	1,038	241	23.2%
registry	903	448	49.6%
github_code	903	75	8.3%
a2aregistry	751	414	55.1%
lists	553	59	10.7%
a2a_registry_org	512	240	46.9%
dexter_discovery	199	1	0.5%
github_topics	165	10	6.1%
8004scan	122	21	17.2%

3a · By protocol kind

A2A vs MCP vs paid_api

paid_api

5,716

a2a_agent

3,246

workflow

1,377

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

6,127

mpp

129

a2a_x402

ap2

l402

stripe_acp

3b · Evidence grade

How we know they take payment

3,094 of 6,377 payment-labelled agents (48.5%) 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

2,456

Facilitator feed

2,124

Agent card

691

/.well-known/x402

502

Catalog listing

456

mpp_manifest

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 mpp stripe_acp x402

4 · Inflow concentration · 30d

A few settlement wallets receive most of the money.

Across 2,011 earning wallets backing 4,085 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

$822,818.01

Recipient wallets

2,011

Active sellers · 30d

1,789

Median · wallet

$0.296

p95 · wallet

$94.36

Top 1 share

72.8%

Top 5 share

87.2%

Gini

0.994

extreme inequality

HHI

5369

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.

      2026-09-27
      peak 251/day
      2026-10-26
    

New agents · 30d

+3,372

New earning wallets · 30d

858

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	48%	new

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 2026-10-26. 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 2026-10-26},
  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.