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
6841
Alive
5313
MCP servers
148711
Sources active
39

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
aggregator_lists mcp not responding 0 —
agntcy_directory agent_urls not responding 0 —
aws_agent_registry agent_urls not responding 0 —
azure_foundry agent_urls not responding 0 —
cloudflare_ans agent_urls not responding 0 —
crtsh agent_urls not responding 0 2026-08-17 03:47
gcp_agent_registry agent_urls not responding 0 —
huggingface_models agent_urls not responding 0 —
langchain_hub agent_urls not responding 0 —
mcp_so mcp not responding 0 —
postman_workspaces agent_urls not responding 0 —
x402_services mcp not responding 0 —
glama_api mcp not run 0 —
open_web agent_urls not run 0 —
a2a_registry_org agent_urls healthy 285 2026-08-20 18:53
agentic_market payment healthy 6 2026-08-19 22:13
claudeskills_info skills healthy 100 2026-08-20 18:21
composio mcp healthy 75 2026-08-20 10:44
ct agent_urls healthy 6 2026-08-19 22:46
docker_catalog mcp healthy 271 2026-08-20 09:36
docker_hub mcp healthy 113 2026-08-20 09:13
erc8004 agent_urls healthy 49 2026-08-20 19:21
github_code agent_urls healthy 3854 2026-08-19 22:45
github_mcp_registry mcp healthy 220 2026-08-20 08:59
github_mcp_repos registry healthy 1014 2026-08-20 04:12
github_topics agent_urls healthy 496 2026-08-19 22:16
glama_sitemap registry healthy 29900 2026-08-20 04:12
huggingface_spaces agent_urls healthy 3295 2026-08-20 18:21
jsr mcp healthy 305 2026-08-20 12:44
lists agent_urls healthy 2750 2026-08-19 22:14
manifests agent_urls healthy 27813 2026-08-19 23:06
mcp_registry agent_urls healthy 23024 2026-08-19 22:15
mcp_registry_full mcp healthy 23765 2026-08-20 09:00
mcp_registry_servers registry healthy 77162 2026-08-20 04:11
n8n_community mcp healthy 2748 2026-08-20 10:51
nanda_index agent_urls healthy 335 2026-08-20 19:13
npm mcp healthy 2717 2026-08-20 08:59
pypi mcp healthy 7887 2026-08-20 09:11
registry agent_urls healthy 398 2026-08-19 22:14
shopify mcp healthy 5 2026-08-20 10:44
sitemap agent_urls healthy 64 2026-08-19 22:49
skill_library_github skills healthy 834 2026-08-20 18:21
smithery agent_urls healthy 121 2026-08-19 22:15
smithery_servers registry healthy 500 2026-08-20 04:12

Contribution per source

recrawl_hot
3114 agents
agentic_market
2753 agents
recrawl_warm
2451 agents
mcp_registry
1644 agents
cdp_discovery
1286 agents
manifests
873 agents
github_code
760 agents
lists
481 agents
x402_list
368 agents
registry
337 agents
recrawl_cold
290 agents
n8n_workflows
194 agents
github_topics
149 agents
a2aregistry
114 agents
a2a_registry_org
112 agents
smithery
89 agents
mpp
86 agents
submitted
61 agents
pay_sh
49 agents
crtsh
38 agents
erc8004
30 agents
sitemap
24 agents
resalvage-20260817b
21 agents
resalvage-20260817
21 agents
seeds
13 agents
gate-widen-20260819
13 agents
a2a-validate
12 agents
operator_request
9 agents
nanda_index
9 agents
manual_recrawl
4 agents
manual-verify
3 agents
manual
3 agents
ct
3 agents
recrawl_weekly
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 2014
2 sources 2341
3 sources 1515
4 sources 761
5 sources 158
6 sources 40
7 sources 10
8 sources 2
9 sources 1
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.