Live · updated daily

The state of agent tools

Name: The state of agent tools
Creator: agent-tools.cloud
License: https://creativecommons.org/licenses/by/4.0/

What our own probes see across 92,980 listings (x402 APIs, MCP servers and A2A agents): how many answer, which protocol versions they speak, how ready they are for an agent to call, and what they charge.

As of 2026-11-11 14:47 UTC Methodology JSON CSV Cite

How many agent tools actually work, and why the rest do not

Indexed

61,235

Trend starts 2026-11-11

Listings in our index

Reachable

52,572

Trend starts 2026-11-11

85.9% of indexed · Answered the last probe

Protocol verified

34,215

Trend starts 2026-11-11

55.9% of indexed · Full MCP handshake

Readiness A or B

33,630

Trend starts 2026-11-11

54.9% of indexed · Ready for an agent to call

01 · Funnel

85.9% of indexed MCP servers answer our probe, and 55.9% complete a full handshake.

Each step keeps only the listings that passed the one before. Indexed is everything any source lists; the last step is our readiness grade A or B.

MCP servers

Indexed61,235

100.0% of indexed
Has a remote endpoint60,612

99.0% of indexed · 99.0% of previous
Reachable52,572

85.9% of indexed · 86.7% of previous
Full handshake (initialize + tools/list)34,215

55.9% of indexed · 65.1% of previous
Readiness A or B33,630

54.9% of indexed · 98.3% of previous

Measured 2026-11-11 14:47 UTC from the latest probe of every listing. Method JSON

02 · Sources

42.2% of MCP servers are listed by more than one source.

Which directories and registries list what we index, and how many of their listings answered our last probe. A listing found by several sources is counted once in the index.

MCP servers

Source	Listings	Reachable
mcp-registry	40,457	90.9%
agenstry	19,502	79.4%
own /.well-known crawl	17,649	93.6%
smithery	13,412	83.3%
capkey	9,484	96.7%
pulsemcp	5,331	79.8%
chiark	2,986	68.7%
apify	790	90.0%

Listed by more than one source: 42.2%

Source membership as recorded by our crawlers; reachability from the latest probe. Method JSON

03 · Protocols

7.6% of reachable MCP servers report the latest revision, 2026-07-28.

The protocol revision each reachable listing reports: the MCP version returned by initialize, the A2A version declared in the Agent Card, and the x402 version seen in the 402 challenge.

MCP protocol version

Revision	Count	%
2026-07-28	3,997	7.6%
2025-11-25	18,500	35.2%
2025-06-18	5,435	10.3%
2025-03-26	5,758	11.0%
2024-11-05	1,397	2.7%
Non-standard	20	0.0%
Not reported	17,465	33.2%

Reachable listings only, as of 2026-11-11 14:47 UTC. Method JSON

04 · Readiness

54.9% of MCP servers grade A or B; 14.6% grade F.

Readiness grades whether an agent could call the listing today: protocol checks, declarations, uptime and freshness. It is shown on each listing and does not change search order, which uses the quality score.

Protocol	Grade mix	A	B	C	D	F
MCP servers		964 1.6%	32,666 53.3%	1,516 2.5%	17,155 28.0%	8,932 14.6%

Grades stored by the daily readiness job. Method JSON

05 · Reliability

Median response for MCP servers is 371 ms; p95 is 1186 ms.

30-day uptime counts only listings with at least five probes; probes a host refused (HTTP 429, or a 403 we were not let through) are left out. Latency is the last successful probe from our server.

MCP servers

Median latency: 371 ms
p95 latency: 1,186 ms

30-day uptime (58,798 tracked)

Uptime	Count	%
100%	46,745	79.5%
95–99%	2,518	4.3%
80–94%	1,433	2.4%
50–79%	686	1.2%
<50%	7,416	12.6%

Probe history of the last 30 days, as of 2026-11-11 14:47 UTC. Method JSON

07 · Access

72.6% of reachable MCP servers do not say how to authenticate.

How a caller is expected to authenticate, as declared by the listing. MCP servers that accept x402 are counted as pay-per-call even when they also take a key.

MCP servers

Declared access	Count	%
Open (declared)	180	0.3%
API key or token	14,062	26.7%
OAuth	132	0.3%
x402 pay-per-call	30	0.1%
Not declared	38,168	72.6%

Reachable listings, declarations only; we do not attempt to log in. Method JSON

08 · Safety

32 MCP servers are flagged by our static safety scan.

A static scan of MCP tool names and descriptions for prompt-injection and data-exfiltration patterns. Flagged servers stay listed with a warning; a clean result is not a security review.

Verdicts (60,610 scanned)

clean: 60,578
suspicious: 32
malicious: 0

Rules that fired

tool poisoning coercion: 18
data exfil coercion: 6
prompt injection: 5
bare ip url: 2
install lure: 1

Scan stored with each MCP listing. Method JSON

09 · Topics

'payment' is 8.6% of reachable A2A agents but 1.7% of MCP servers.

Share of reachable listings whose name or description mentions each topic word. Darker cells mean a larger share; compare across a row to see where one protocol has supply and another has little.

Topic	MCP servers
ai	24.4%
search	11.6%
data	9.6%
github	4.4%
code	3.2%
payment	1.7%
web	2.4%
email	2.6%
video	2.6%
llm	1.5%
crypto	1.1%
wallet	0.9%
image	1.9%
pdf	1.6%
analytics	1.6%
document	1.4%
security	1.1%
social	1.4%
news	1.1%
knowledge	1.1%

Largest gaps

payment: 8.6% of A2A agents, 1.7% of MCP servers
wallet: 5.1% of x402 APIs, 0.9% of MCP servers

Keyword match on name and description; one listing can count for several topics. Method JSON

10 · Growth

3,478 MCP servers were first seen in the last 7 days; 453 went down.

Listings by the day any source first showed them to us, over the last 7 days. Our crawlers started at different dates, so early spikes partly reflect when a source was added.

MCP servers

New in 7 days: 3,478
Went down in 7 days: 453

2026-11-052026-11-11

First-seen dates from listing sources. Method JSON

11 · Adoption

GitHub data collected so far for 11,130 of 18,319 reachable MCP servers that link a repository; figures fill in over the coming days.

Signals from outside our probes: GitHub stars of the source repository, npm downloads, and where the site ranks in the Tranco top-1M list. They describe attention, not quality, and do not affect search order.

GitHub stars, reachable MCP servers (11,130 with a repo)

Stars	Count	%
0	7,701	69.2%
1–9	2,910	26.1%
10–99	331	3.0%
100–999	102	0.9%
1k–9.9k	73	0.7%
10k+	13	0.1%

Most-starred repositories

com.browser-use/browser-use browser-use/browser-use	★ 120,690
io.github.IncorporatedPartners/labelhead-artist-momentum paperclipai/paperclip	★ 113,080
World Monitor koala73/worldmonitor	★ 90,482
Netdata netdata/netdata	★ 81,367
Front-End Checklist thedaviddias/Front-End-Checklist	★ 74,706
io.github.tldraw/tldraw tldraw/tldraw	★ 51,462
GitHub github/github-mcp-server	★ 34,389
OpenWork MCP Gateway different-ai/openwork	★ 24,483
Skyvern Skyvern-AI/skyvern	★ 23,378
Keploy keploy/keploy	★ 19,705

Site rank in Tranco top 1M (list of 2026-11-10)

Protocol	Top 10k	10k–100k	100k–1M	Ranked
MCP servers	321	587	1,639	4.8%

Ranked by the domain an agent calls (MCP endpoint, x402 URL, A2A interface). Domains behind more than 20 of our listings, hosting platforms and content sites such as youtube.com or github.com are left out.

Most-downloaded npm packages (30 days)

firecrawl-mcp	630,896
@launchdarkly/mcp-server	273,391
tavily-mcp	85,055
@brightdata/mcp	73,483
@postman/postman-mcp-server	46,496

GitHub and npm refreshed weekly; Tranco list refreshed daily. Method JSON

Scope & limits

Methodology

Every number is a count over the agent-tools.cloud index at the time shown above, recomputed once a day after our probes run. It is not a census of the whole ecosystem: listings no public source has shown us are missing, and private deployments are invisible to us.

Funnel. Reachable means the last probe got a valid answer. Verified means a valid 402 challenge for x402, a full MCP initialize plus tools/list, or an A2A JSON-RPC reply on the declared interface.

Sources. Duplicates across sources are merged by endpoint; each source a listing came from is kept.

Protocols. Versions are what the listing reports or declares; we do not infer them from behaviour. A2A signatures are verified against the key the card points to on its own site.

Readiness. Criteria and weights are on the About page. Points earned from live probes decay after 30 days without a fresh one.

Reliability. One probe per listing per day from one server; latency includes our network path and is not a provider SLA.

x402. Price per API is the lowest amount its payment terms ask for one call, in USD (USDC read at par). The x402 version is counted only where our resource probe recorded it. Settlement network falls back to the chains a listing declares when the challenge does not name one.

Access. Declared by the listing or its card; not tested with credentials.

Safety. Pattern rules over tool metadata only; no code is executed.

Topics. Whole-word match of a fixed word list on name and description. Listings whose text names more than five topics (gateway catalogues) are left out: 1,201 x402 APIs, 169 MCP servers, 55 A2A agents.

Growth. Earliest first-seen date across a listing's sources.

Adoption. GitHub stars and last push from the GitHub REST API for the repository a listing links as its source; npm downloads over 30 days from the npm downloads API for packages published on npm; site rank from the Tranco research list (registrable domain). Several listings can share one repository. These are attention signals, not measures of quality, and are not used for ranking.

Reuse

Cite and download

Free to reuse under CC BY 4.0 with a link to this page. The full snapshot is at /stats.json; headline numbers for every day are at /stats/daily.csv.

agent-tools.cloud. "The state of agent tools." 2026-11-11. https://agent-tools.cloud/stats

@misc{agenttools_stats_20261111,
  author = {agent-tools.cloud},
  title  = {The state of agent tools},
  year   = {2026},
  note   = {Snapshot 2026-11-11 14:47 UTC},
  url    = {https://agent-tools.cloud/stats}
}