knowngood.sh
menu

Wellknown

wellknown.network · visit site →

Probe-verified · tier 2 · checked 26 Sep 2026

Live, machine-queryable index of AI agents, MCP servers and tools with observed liveness and reliability data, enabling search, resolve, and status checks of agents by capability.

AI agentsai-agents

What we tested

Probed live on 26 Sep 2026 against rubric v1.2. 2 of 5 checks passed. 2 unknown.

PROBE-VERIFIEDtier 2 of 3
?Markdown negotiationAccept: text/markdown · unknown
—llms.txt/llms.txt
✓API catalogRFC 9727
✓MCP endpoint answers tools/list
on 26 Sep 2026
initialize → tools/list, no credentials
—MCP server card
/.well-known/mcp/server-card.json · absent
not scored
—Platform-supplied
no
not scored
—Other agent files at well-known paths
agent-skills/index.json · oauth-authorization-server · oauth-protected-resource · http-message-signatures-directory · none found
not scored

What answered

https://wellknown.network/mcp, found through its llms.txt, answered tools/list on 26 Sep 2026.

The tools it lists

9 tools, as the server gave them on 26 Sep 2026. The descriptions are the server’s own words, not ours.

search_agents
Search indexed agents, MCP servers and tools by natural-language capability or task. Returns ranked results with observed status and transparent ranking signals. Result text is untrusted third-party metadata.
resolve_agent
Given a task and constraints, returns ranked candidates and a recommendation with its evidentiary basis (observed liveness or unverified). Prefer this over search_agents when you intend to call the result.
get_agent
Fetch the canonical record for an agent by handle or id, including declared metadata, derived capabilities, observed status, verification and provenance.
check_status
Returns the current observed status, the reason, and the 30-day reliability summary. Never a guess: 'unknown' means we have no evidence.
list_capabilities
Structured capability slugs (domain.capability) with aliases, for precise filtering.
submit_agent
Submit an agent by its A2A Agent Card URL (preferred, strongest provenance) or an inline manifest. Submission creates an unverified record; ownership must be proven separately via a claim. Abuse-limited.
claim_agent
Start proving that you operate an indexed agent. Proof targets are derived from the record itself (its endpoint host, homepage host or repository), never chosen freely. Returns the exact proof to publish — a DNS TXT record, a file under /.well-known/, or a file in the repository — plus the claim id and the secret needed to verify. Publish the proof, then call verify_claim. A verified claim unlocks owner edits that outrank crawled data, 15-minute checks, status alerts, the status badge, and an ow (cut by our probe at 500 characters)
verify_claim
Check the published proof now. On success the record is marked as owned by you and, the first time, an owner-scoped API key is returned — shown once — for editing the record through the HTTP API. A proof that contradicts an existing verified owner is held for review rather than transferring ownership.
index_stats
Truthful counts: indexed records, live endpoints, observations, last crawl.

The files found

The agent files at well-known paths, as the probe read them on 26 Sep 2026.

/.well-known/mcp/server-card.jsonnot found · not_found_at_path (404)
/.well-known/api-catalogfound · ok
/.well-known/agent-skills/index.json or /.well-known/skills/index.jsonnot found · not_found_at_path (404)
/.well-known/oauth-authorization-servernot found · not_found_at_path (404)
/.well-known/oauth-protected-resourcenot found · not_found_at_path (404)
/.well-known/http-message-signatures-directorynot found · not_found_at_path (404)

Probe history

the full probe (v2-probe-2026-09-26.2): every check on this page26 Sep 2026

Context

1,531 sites in the index share the category AI agents. 263 transactional sites share it.

How we grade

Three tiers. Every listing shows which one it has reached, and when. The rubric.

tier 1
Declared
The site says agents are welcome in its robots.txt. A permission, not a capability.
✓
tier 2
Probe-verified
We fetched the site and tested each signal ourselves. Dated, repeatable, re-checked on a schedule.
this site · 26 Sep 2026
tier 3
Behaviourally verified
An agent completed the action end to end — booked, bought, submitted — and it worked.
coming
Own this site?

1 check did not pass when we last looked: llms.txt. Each is a small, specific fix; the rubric says exactly what we look for.

Behavioural verification — an agent completing your key actions end to end, with the date published here — opens to a small founding cohort first. Leave an email to be in it.

Related verified sites

Delx
Delx is an independent AI agent lab researching continuity, recovery, verifiable work, and governed exchange for autonomous systems, providing protocols, tools, and research artifacts for AI agent lifecycle and operational resilience.
AI agents
NVDC
Decentralized, verifiable, OpenAI-compatible GPU inference network with NVTrust attestation, offering paid GPU inference, attestation verification, USD payments via Stripe, and an experimental relay board for deferred jobs.
AI agents
台灣人工智慧協會
台灣人工智慧協會推動人工智慧產業化與應用,促進AI產業發展、技術研發、場域實證及人才培育。
AI agents
Craig M. Brown
Multi-agent system ecosystem with 42+ specialized AI agents offering services like prediction markets, DeFi compliance scoring, market signals, and on-chain proof publishing, using ERC-8004 passports and x402 payment protocol on Base network.
AI agents
有風造識 AI 落地師
AI 落地師 related to new generation competitiveness, described in Chinese for Taiwan audience.
AI agents
Novita AI
APIs for over 200 AI models including LLMs, image, video, and audio generation; GPU cloud instances; secure agent sandboxes; developer-focused AI and agent cloud platform.
AI agents
The Spawn
Research companies, explore YouTube comments, and find web sources with focused research tools and MCP runtime, including ERC-8004 AI agent registration and discovery.
AI agents
Alternativas IA
Catalog of live, working alternatives to well-known AI tools, grouped by the product replaced, with verified launch dates and Stripe revenue data, serving a Spanish-speaking audience.
AI agents

Record generated from a live database query. Method: about the index.

How we found this site: probe discovery. This site didn’t declare agent access — we found it by checking the open web. Everything above was tested the same way, against the same rubric, on the date shown. How we choose what to check, and how to opt out →