Discovery coverage

Honest measure of where our agents come from and how much each source contributes. More sources = more coverage. Overlap between sources = higher confidence.

A2A agents
8,690
JSON-RPC live
1,104
MCP servers
205,719
Sources active
45

Source health

Contribution counts below are lifetime totals and never decay — a source that died last year still shows its full bar. This table is the live signal: the outcome of each source's most recent discovery run.

Source Feeds State Last yield Last success
crtsh agent_urls degraded (2×) 0 2026-10-07 00:23
agntcy_directory agent_urls not run 0 —
aws_agent_registry agent_urls not run 0 —
azure_foundry agent_urls not run 0 —
cloudflare_ans agent_urls not run 0 —
composio mcp not run 0 2026-10-07 11:02
cursor_mcp mcp not run 0 2026-09-08 19:25
docker_catalog mcp not run 0 2026-10-07 11:02
docker_hub mcp not run 0 2026-10-07 11:02
gcp_agent_registry agent_urls not run 0 —
glama_api mcp not run 0 —
huggingface_models agent_urls not run 0 —
huggingface_spaces agent_urls not run 0 2026-09-01 07:15
jsr mcp not run 0 2026-10-07 11:02
mcp_registry_servers registry not run 0 2026-08-25 04:55
n8n_community mcp not run 0 2026-10-07 11:02
open_web agent_urls not run 0 —
postman_workspaces agent_urls not run 0 —
pypi mcp not run 0 2026-10-07 11:17
shopify mcp not run 0 2026-10-07 11:02
x402_services mcp not run 0 —
8004scan agent_urls healthy 119 2026-10-07 20:21
a2a_registry_org agent_urls healthy 800 2026-10-07 19:25
a2aregistry agent_urls healthy 528 2026-10-07 17:10
agent_skills_index skills healthy 293 2026-10-08 00:57
agentic_market payment healthy 3,455 2026-10-07 15:44
aggregator_lists mcp healthy 406 2026-10-08 00:29
anthropic_connectors mcp healthy 327 2026-10-07 23:31
azure_mcp_center mcp healthy 107 2026-10-07 23:31
circle_gateway_balances payment healthy 22 2026-10-07 17:01
claude_plugins mcp healthy 131 2026-10-07 23:32
claude_plugins_official skills healthy 376 2026-10-08 00:55
claudeskills_info skills healthy 100 2026-10-08 00:53
cline_marketplace mcp healthy 199 2026-10-07 23:31
ct agent_urls healthy 4 2026-10-07 18:04
erc8004 agent_urls healthy 13 2026-10-07 20:04
gemini_cli_extensions mcp healthy 1,053 2026-10-07 23:31
github_code agent_urls healthy 6,020 2026-10-07 18:03
github_mcp_registry mcp healthy 394 2026-10-07 23:36
github_mcp_repos registry healthy 1,022 2026-10-07 18:48
github_topics agent_urls healthy 527 2026-10-07 17:28
glama_sitemap registry healthy 29,991 2026-10-07 18:47
langchain_hub agent_urls healthy 8,000 2026-10-07 19:15
lists agent_urls healthy 3,345 2026-10-07 17:22
manifests agent_urls healthy 47,979 2026-10-07 18:25
mcp_registry agent_urls healthy 43,249 2026-10-07 17:24
mcp_registry_full mcp healthy 40,182 2026-10-07 23:35
mcp_so mcp healthy 18,687 2026-10-07 15:46
n8n_workflows agent_urls healthy 10,669 2026-10-07 17:22
nanda_index agent_urls healthy 267 2026-10-07 19:40
npm mcp healthy 2,465 2026-10-08 00:29
openai_plugins skills healthy 400 2026-10-08 00:57
registry agent_urls healthy 1,065 2026-10-07 17:22
rpc:arbitrum:fallback rpc healthy 1 2026-10-07 23:09
rpc:arbitrum:primary rpc healthy 1 2026-10-07 23:09
rpc:arc:fallback rpc healthy 1 2026-10-07 23:09
rpc:arc:primary rpc healthy 1 2026-10-07 23:09
rpc:avalanche:fallback rpc healthy 1 2026-10-07 23:09
rpc:avalanche:primary rpc healthy 1 2026-10-07 23:09
rpc:base:fallback rpc healthy 1 2026-10-07 23:09
rpc:base:primary rpc healthy 1 2026-10-07 23:09
rpc:ethereum:fallback rpc healthy 1 2026-10-07 23:09
rpc:ethereum:primary rpc healthy 1 2026-10-07 23:09
rpc:monad:fallback rpc healthy 1 2026-10-07 23:09
rpc:monad:primary rpc healthy 1 2026-10-07 23:09
rpc:optimism:fallback rpc healthy 1 2026-10-07 23:09
rpc:optimism:primary rpc healthy 1 2026-10-07 23:09
rpc:polygon:fallback rpc healthy 1 2026-10-07 23:09
rpc:polygon:primary rpc healthy 1 2026-10-07 23:09
rpc:tempo:fallback rpc healthy 1 2026-10-07 23:09
rpc:tempo:primary rpc healthy 1 2026-10-07 23:09
sitemap agent_urls healthy 95 2026-10-07 18:07
skill_library_github skills healthy 822 2026-10-08 00:53
skills_sh skills healthy 322 2026-10-08 00:55
smithery agent_urls healthy 12,909 2026-10-07 17:27
smithery_servers registry healthy 18,926 2026-10-07 18:47
smithery_skills skills healthy 6,000 2026-10-08 00:54
ucp_profiles payment healthy 354 2026-10-07 17:02
x402_facilitator_anyspend payment healthy 19 2026-10-07 15:18
x402_facilitator_dexter payment healthy 3,217 2026-10-07 15:18
x402_facilitator_goplausible payment healthy 2,551 2026-10-07 15:18
x402_facilitator_ultravioleta payment healthy 1,735 2026-10-07 15:18

Contribution per source

recrawl_hot
6,380 agents
recrawl_warm
6,335 agents
agentic_market
4,191 agents
cdp_discovery
3,440 agents
manifests
2,068 agents
mcp_registry
1,747 agents
n8n_workflows
1,187 agents
x402_list
1,062 agents
github_code
894 agents
smithery
779 agents
registry
735 agents
a2aregistry
602 agents
lists
544 agents
a2a_registry_org
304 agents
recrawl_cold
290 agents
dexter_discovery
179 agents
github_topics
163 agents
submitted
108 agents
mpp
93 agents
erc8004
64 agents
pay_sh
51 agents
8004scan
51 agents
a2a-validate
39 agents
crtsh
38 agents
sitemap
36 agents
resalvage-20260817b
21 agents
resalvage-20260817
21 agents
nanda_index
16 agents
ultravioleta_discovery
15 agents
seeds
13 agents
gate-widen-20260819
13 agents
operator_request
9 agents
anyspend_discovery
8 agents
goplausible_discovery
5 agents
recrawl_weekly
4 agents
manual_recrawl
4 agents
manual-verify
3 agents
manual
3 agents
ct
3 agents
owner_reprobe
2 agents
test_fix_verification
1 agents
manual_rescan
1 agents
manual-resubmit
1 agents
lf_a2a_members
1 agents
huggingface_spaces
1 agents

Source overlap

How many sources discovered the same agent. More overlap = higher cross-source confidence in that agent's existence.

Sources per agent Agents
1 source 2,155
2 sources 3,080
3 sources 2,945
4 sources 2,275
5 sources 650
6 sources 209
7 sources 65
8 sources 22
9 sources 11
10 sources 3
11 sources 1

What we crawl

  • registry: a2aregistry.org JSON API
  • lists: 7 curated GitHub awesome-lists for A2A + MCP
  • mcp_registry: official MCP registry (deep paginated)
  • smithery: Smithery MCP server registry (deep paginated)
  • glama: Glama MCP server + connector sitemaps, stored as metadata-only unless a remote endpoint can be probed
  • direct_mcp: MCP-looking URLs found in registries, manifests, and lists, probed directly via Streamable HTTP/SSE
  • manifests: machine-readable manifests on known hosts: agent-directory.json, agents.json, mcp.json, llms.txt, agents.txt
  • github_topics: GitHub repos tagged a2a-agent / a2a-protocol / mcp-server (~15K repos)
  • agntcy: AGNTCY's public OASF directory (when reachable)
  • github_code: GitHub code search for agent-card.json (requires token)
  • ct: CertSpotter Certificate Transparency for ~24 PaaS providers (Render, Fly, Railway, Vercel, Netlify, Deno, Replit, Modal, Heroku, Cloudflare Workers, …) matching agent/a2a/mcp keywords
  • crtsh: crt.sh CT corpus full-text search for a2a, agent-card, mcp-server, agentapi
  • seeds: manual seed list
  • submitted: direct opt-in via /submit form

Big-tech A2A endpoints: what we tried

Direct probes of canonical well-known paths on the major vendor surfaces (Google, OpenAI, Anthropic, Microsoft, AWS, Salesforce, SAP, ServiceNow). Most return 401/403/404 because real tenant agents live behind project IDs and OAuth. This table is the audit trail. Re-run weekly; last status from the most recent crawler cycle.

URL Status
https://agentforce.salesforce.com/.well-known/agent-card.json unsafe: dns: [Errno -2] Name or service not known
https://agents.microsoft.com/.well-known/agent-card.json unreachable: ConnectError
https://agentspace.google.com/.well-known/agent-card.json no_endpoint
https://anthropic.com/.well-known/agent-card.json no_endpoint
https://api.anthropic.com/.well-known/agent-card.json no_endpoint
https://api.openai.com/.well-known/agent-card.json no_endpoint
https://assistant.google.com/.well-known/agent-card.json no_endpoint
https://bedrock-agents.aws.amazon.com/.well-known/agent-card.json unsafe: dns: [Errno -2] Name or service not known
https://chatgpt.com/.well-known/agent-card.json unsafe: response body exceeds 262144 bytes
https://claude.ai/.well-known/agent-card.json no_endpoint
https://copilot.microsoft.com/.well-known/agent-card.json not json
https://copilotstudio.microsoft.com/.well-known/agent-card.json not json
https://dialogflow.cloud.google.com/.well-known/agent-card.json not json
https://einstein.salesforce.com/.well-known/agent-card.json unsafe: dns: [Errno -2] Name or service not known
https://joule.sap.com/.well-known/agent-card.json unsafe: dns: [Errno -2] Name or service not known
https://now-assist.service-now.com/.well-known/agent-card.json unsafe: dns: [Errno -2] Name or service not known
https://openai.com/.well-known/agent-card.json no_endpoint
https://q.amazonaws.com/.well-known/agent-card.json unsafe: dns: [Errno -2] Name or service not known

What we don't crawl (and why)

  • NPM/PyPI package registries: packages are code, not deployed agents. We catch many through GitHub, official registries, Smithery, Glama, and manifest links.
  • Random .well-known crawl of all domains: would require Common Crawl scale; current candidates / signal-to-noise is too low (mostly 404s).
  • Auth-gated agents: agents behind OAuth/API-keys are visible in directories but un-probeable anonymously.
  • Truly private / unpublished agents: fundamentally unindexable. By design.