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
8,864
JSON-RPC live
1,134
MCP servers
206,505
Sources active
47

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 (1×) 0 2026-10-10 22:03
agntcy_directory agent_urls not run 0 —
anthropic_connectors mcp not run 0 2026-10-10 16:19
aws_agent_registry agent_urls not run 0 —
azure_foundry agent_urls not run 0 —
azure_mcp_center mcp not run 0 2026-10-10 16:19
cloudflare_ans agent_urls not run 0 —
composio mcp not run 0 2026-10-10 16:19
cursor_mcp mcp not run 0 2026-09-08 19:25
gcp_agent_registry agent_urls not run 0 —
gemini_cli_extensions mcp not run 0 2026-10-10 03:07
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 2026-10-10 16:19
mcp_registry_servers registry not run 0 2026-08-25 04:55
n8n_community mcp not run 0 2026-10-10 16:19
open_web agent_urls not run 0 —
postman_workspaces agent_urls not run 0 —
shopify mcp not run 0 2026-10-10 16:19
x402_services mcp not run 0 —
8004scan agent_urls healthy 242 2026-10-11 11:56
a2a_registry_org agent_urls healthy 827 2026-10-11 10:57
a2aregistry agent_urls healthy 499 2026-10-11 07:37
agent_skills_index skills healthy 296 2026-10-11 05:42
agentic_market payment healthy 4,276 2026-10-11 06:53
aggregator_lists mcp healthy 406 2026-10-11 04:29
circle_gateway_balances payment healthy 22 2026-10-10 18:04
claude_plugins mcp healthy 131 2026-10-11 04:30
claude_plugins_official skills healthy 376 2026-10-11 05:40
claudeskills_info skills healthy 100 2026-10-11 05:38
cline_marketplace mcp healthy 199 2026-10-11 04:29
ct agent_urls healthy 4 2026-10-11 08:30
docker_catalog mcp healthy 270 2026-10-11 05:19
docker_hub mcp healthy 113 2026-10-11 05:19
erc8004 agent_urls healthy 23 2026-10-11 11:46
github_code agent_urls healthy 5,923 2026-10-11 08:30
github_mcp_registry mcp healthy 394 2026-10-11 04:29
github_mcp_repos registry healthy 1,023 2026-10-11 10:05
github_topics agent_urls healthy 527 2026-10-11 07:58
glama_sitemap registry healthy 29,991 2026-10-11 10:05
langchain_hub agent_urls healthy 8,000 2026-10-11 10:47
lists agent_urls healthy 3,504 2026-10-11 07:52
manifests agent_urls healthy 51,621 2026-10-11 08:55
mcp_registry agent_urls healthy 45,101 2026-10-11 07:53
mcp_registry_full mcp healthy 41,231 2026-10-11 04:30
mcp_so mcp healthy 18,191 2026-10-11 06:53
n8n_workflows agent_urls healthy 10,720 2026-10-11 07:52
nanda_index agent_urls healthy 267 2026-10-11 11:38
npm mcp healthy 2,467 2026-10-11 04:30
openai_plugins skills healthy 400 2026-10-11 05:41
pypi mcp healthy 7,876 2026-10-11 05:34
registry agent_urls healthy 999 2026-10-11 07:52
rpc:arbitrum:fallback rpc healthy 1 2026-10-11 16:45
rpc:arbitrum:primary rpc healthy 1 2026-10-11 16:45
rpc:arc:fallback rpc healthy 1 2026-10-11 16:45
rpc:arc:primary rpc healthy 1 2026-10-11 16:45
rpc:avalanche:fallback rpc healthy 1 2026-10-11 16:45
rpc:avalanche:primary rpc healthy 1 2026-10-11 16:45
rpc:base:fallback rpc healthy 1 2026-10-11 16:45
rpc:base:primary rpc healthy 1 2026-10-11 16:45
rpc:ethereum:fallback rpc healthy 1 2026-10-11 16:45
rpc:ethereum:primary rpc healthy 1 2026-10-11 16:45
rpc:monad:fallback rpc healthy 1 2026-10-11 16:45
rpc:monad:primary rpc healthy 1 2026-10-11 16:45
rpc:optimism:fallback rpc healthy 1 2026-10-11 16:45
rpc:optimism:primary rpc healthy 1 2026-10-11 16:45
rpc:polygon:fallback rpc healthy 1 2026-10-11 16:45
rpc:polygon:primary rpc healthy 1 2026-10-11 16:45
rpc:tempo:fallback rpc healthy 1 2026-10-11 16:45
rpc:tempo:primary rpc healthy 1 2026-10-11 16:45
sitemap agent_urls healthy 103 2026-10-11 08:34
skill_library_github skills healthy 794 2026-10-11 05:38
skills_sh skills healthy 322 2026-10-11 05:39
smithery agent_urls healthy 13,468 2026-10-11 07:57
smithery_servers registry healthy 19,479 2026-10-11 10:05
smithery_skills skills healthy 6,000 2026-10-11 05:39
ucp_profiles payment healthy 384 2026-10-10 18:05
x402_facilitator_anyspend payment healthy 19 2026-10-11 06:29
x402_facilitator_dexter payment healthy 3,203 2026-10-11 06:29
x402_facilitator_goplausible payment healthy 2,577 2026-10-11 06:29
x402_facilitator_ultravioleta payment healthy 1,436 2026-10-11 06:29

Contribution per source

recrawl_warm
8,255 agents
recrawl_hot
6,641 agents
agentic_market
4,299 agents
cdp_discovery
3,603 agents
manifests
2,068 agents
mcp_registry
1,747 agents
n8n_workflows
1,226 agents
x402_list
1,084 agents
github_code
894 agents
smithery
855 agents
registry
765 agents
a2aregistry
627 agents
lists
547 agents
a2a_registry_org
320 agents
recrawl_cold
290 agents
dexter_discovery
182 agents
github_topics
163 agents
submitted
108 agents
mpp
93 agents
8004scan
86 agents
erc8004
67 agents
pay_sh
51 agents
a2a-validate
40 agents
crtsh
38 agents
sitemap
36 agents
resalvage-20260817b
21 agents
resalvage-20260817
21 agents
ultravioleta_discovery
18 agents
nanda_index
16 agents
seeds
13 agents
gate-widen-20260819
13 agents
operator_request
9 agents
anyspend_discovery
8 agents
goplausible_discovery
7 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
submitted_by_email
1 agents
manual_rescan
1 agents
manual-resubmit
1 agents
lf_a2a_members
1 agents
huggingface_spaces
1 agents
dispute_review
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 2,236
2 sources 2,024
3 sources 3,576
4 sources 2,746
5 sources 768
6 sources 237
7 sources 88
8 sources 24
9 sources 10
10 sources 7
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.