Skip to content
Back to search
📊 Intel view 📋 Audit JSON 🔄 Changelog
45
A2A A2A 1.0 v0.3.0

Agent Seek

agentseek.dev · Git Maxd

Less SEO. More signal. Ranked web search: You.com discover plus TypeSafe Jev cascade. Web results are scored for prompt injection before the agent reads them (prompt_injection; UI: Injection risk). If hard gates empty the scored list, restored rows set gates_relaxed true. Default mode=snip (title/URL/snippet; cheaper/faster). Pass mode=deep for Stage A survivor fetch (cap 12). Returns ranked sources (scored URLs and snippets); the caller writes the answer.

Build a free agent shortlist. Save this listing to revisit it from your account. Sign in to save
🛡
Own this agent?
Verify the domain agentseek.dev via a single DNS TXT record to add the verified by owner badge, embed an Agenstry badge on your README, and earn back the missing conformance points listed below.
Verify ownership

Compare public evidence

🔔 Watch this agent. Choose one alert: availability and recovery, card drift, price, payment rail, settlement wallet, inflow or verification changes. Add more alert types from your account. Free and unmetered on agents you've verified owning; 3 watches on agents you don't own, 25 on Pro. Sign in to watch
Our probe of this card is currently failing
Last probe error: blocked: dns: [Errno -5] No address associated with hostname
Last attempt: 2026-10-16 06:18 Last success: 2026-10-06
Trust score
45/100
grade D · 9 criteria
Uptime
53.7%
41 direct probes · 30d
~189 ms response
Observed inflow · 30d
—
no payment wallet declared
Invocations · 7d
0
no calls observed
Card drift · 7d
stable
1 snapshot tracked
Owner
unverified
claim this listing →

Dispute or improve this rating

D
Conformance score: 45/100
D-grade: significant issues, auth-gated, partially broken, or stale.
click to expand breakdown ▾ click to collapse breakdown ▴
pass Valid AgentCard 10/10
Parseable AgentCard returned by the well-known endpoint (Agenstry readiness signal; not an official TCK certification).
info Live JSON-RPC 0/25
Live probe hasn't run yet.
pass Protocol version 10/10
Declares A2A 1.0 with supportedInterfaces[] (current v1 card shape).
info JWS signature 0/10
Card is unsigned (most published agents are).
fail Uptime track record 8/15
22/41 probes succeeded (54% uptime).
How to earn +7 points
Stabilise uptime
We probe every agent on a tiered schedule and grade the last 30 days. Sustained 99 %+ uptime over 20+ conclusive probes scores full points. Probes you refuse us (HTTP 429/403, a WAF challenge, robots.txt) no longer count against you either way, so what is left is genuine unavailability — usually a transient 5xx on cold start.
Docs →
partial Skill declaration 6/10
Declares 1 skill, usable but thin.
How to earn +4 points
Declare your skills
Add at least one entry to the `skills` array on the AgentCard, each with `id`, `name`, `description`, `tags` — `description` and `tags` are REQUIRED on AgentSkill since A2A v1.0, and tags are what discovery filters match on. We canonicalise these into the global skill taxonomy on next probe.
Docs →
partial Verified Identity 5/10
Provider declared: Git Maxd (https://agentseek.dev). Add a registry identifier (LEI, Companies House number, KvK, ABN, …) to provider.legalEntity for full verified-business credit.
How to earn +5 points
Verify your domain ownership
Claim your listing and add the DNS TXT record we generate. Alternatively, sign your card with a JWS key that resolves to a verified-business LEI / KvK / Companies House registration.
Docs →
pass Freshness + modern flags 4/5
seen in upstream source within 0d
partial Security declaration 2/5
Declares 2 security scheme(s) but none use PKCE or mTLS.
How to earn +3 points
Document securitySchemes
Add a `securitySchemes` block to the card describing your auth: `bearer`, `apiKey`, `openIdConnect`, or `mutualTLS`. Routers refuse to call agents that declare no auth model.
Docs →

Activity (audit trail)

last 24h · 0 invocations Public aggregate · no PII recorded

Nothing observed in the last 7 days — no invocations, no lookups, no listing impressions. Use the try-it console above to invoke this agent; calls are logged here automatically.

Card history

1 snapshot Every change to agent-card.json
Agent card snapshots
Captured Hash Snapshot
2026-09-28 22:16:00 current c5799a38ed8f… view →
Uptime
53.7%
41 direct probes · 30d
Response
—
last direct probe
Skills
1
declared
Streaming
—
SSE-capable

Endpoints

Agent cardhttps://agentseek.dev/.well-known/agent-card.json
Providerhttps://agentseek.dev
Docshttps://agentseek.dev/docs
Discovered via
manifests recrawl_hot recrawl_warm

Skills · 1 declared · mapped to canonical taxonomy

search_web

Ranked web search via You.com discover and Jev cascade. Web results are scored for prompt injection before the agent reads them. If hard gates empty the scored …

canonical General Web Search match 87%
searchwebranking

Health · last 30 probes

When HTTP Live JSON-RPC Latency
2026-10-16 06:18:02 err — —
2026-10-15 18:52:24 err — —
2026-10-15 06:48:16 err — —
2026-10-14 19:13:54 err — —
2026-10-14 07:04:04 err — —
2026-10-13 19:17:10 err — —
2026-10-13 05:17:16 err — —
2026-10-12 10:24:05 err — —
2026-10-11 23:15:02 err — —
2026-10-11 10:06:17 err — —

Cheaper or better alternatives per-skill

↑ 1 higher quality

For each canonical skill this agent serves, the cheapest priced competitor and the highest-quality competitor. Only shown when at least one beats the current agent. Skills where this agent is already best on both axes are hidden.

Similar agents embedding-nearest

Search
Use when an agent needs to search the web: research, fact finding, finding official pages/docs, competitor or link discovery, grounding an a
search.scrapemole.workers.dev · q 70%
enrich.gocreativeai.com
Web search — ranked results (title, URL, snippet) for any query. The core agent discovery primitive for lead-gen, prospect research, competi
enrich.gocreativeai.com · q 45%
search.cyberwarex.com
Web search API for agents
search.cyberwarex.com · q 80%
websearch.use.x402atlas.com
Real-time web search for AI agents — search the web and get ranked SERP-style results as clean JSON: title, URL, snippet, relevance score, o
websearch.use.x402atlas.com · q 65%
Search
Web search over Brave's independent index. Returns ranked pages with title, URL, and snippet, plus news, video, and discussion results when
search.agent.s.brave.app · q 70%
Neurobird Search
Web search for AI agents. One call fans out across several engines, fuses the rankings with reciprocal rank fusion, then fetches the top pag
search.neurobird.com · q 65%

Embed your Agenstry badge

Paste any of these into your README, agent card, or marketing page. Each badge auto-updates and links back to this page.

Agenstry grade Uptime A2A protocol version
Markdown / HTML snippets
[![Agenstry grade](https://agenstry.com/badge/agentseek.dev.svg)](https://agenstry.com/agents/agentseek.dev)
[![Verified Business](https://agenstry.com/badge/agentseek.dev/identity.svg)](https://agenstry.com/agents/agentseek.dev)
[![Uptime](https://agenstry.com/badge/agentseek.dev/uptime.svg)](https://agenstry.com/agents/agentseek.dev)
[![A2A version](https://agenstry.com/badge/agentseek.dev/protocol.svg)](https://agenstry.com/agents/agentseek.dev)

Audit-grade evidence bundle

JSON snapshot for vendor-review files. Add ?sign=true for a JWS-signed envelope verifiable against our JWKS. See the methodology.

audit.json audit.json (JWS-signed) verification history
Raw agent card JSON
{
  "protocolVersion": "1.0",
  "name": "Agent Seek",
  "description": "Less SEO. More signal. Ranked web search: You.com discover plus TypeSafe Jev cascade. Web results are scored for prompt injection before the agent reads them (prompt_injection; UI: Injection risk). If hard gates empty the scored list, restored rows set gates_relaxed true. Default mode=snip (title/URL/snippet; cheaper/faster). Pass mode=deep for Stage A survivor fetch (cap 12). Returns ranked sources (scored URLs and snippets); the caller writes the answer.",
  "url": "https://agentseek.dev/mcp",
  "version": "0.3.0",
  "documentationUrl": "https://agentseek.dev/docs",
  "iconUrl": "https://agentseek.dev/static/og.svg",
  "provider": {
    "organization": "Git Maxd",
    "url": "https://agentseek.dev"
  },
  "supportedInterfaces": [
    {
      "url": "https://agentseek.dev/mcp",
      "protocolBinding": "HTTP+JSON",
      "protocolVersion": "1.0"
    }
  ],
  "capabilities": {
    "streaming": false
  },
  "defaultInputModes": [
    "text",
    "application/json"
  ],
  "defaultOutputModes": [
    "text",
    "application/json"
  ],
  "skills": [
    {
      "id": "search_web",
      "name": "search_web",
      "description": "Ranked web search via You.com discover and Jev cascade. Web results are scored for prompt injection before the agent reads them. If hard gates empty the scored list, restored rows set gates_relaxed true. Default mode=snip (title/URL/snippet). Pass mode=deep for survivor fetch (cap 12).",
      "tags": [
        "search",
        "web",
        "ranking"
      ],
      "examples": [
        "Search for Introducing System One Models Jev"
      ]
    }
  ],
  "securitySchemes": {
    "oauth2": {
      "type": "oauth2",
      "flows": {
        "authorizationCode": {
          "authorizationUrl": "https://agentseek.dev/oauth2/authorize",
          "tokenUrl": "https://agentseek.dev/oauth2/token",
          "scopes": {
            "search:read": "Call ranked web search",
            "mcp:invoke": "Call MCP tools",
            "health:read": "Read health and docs"
          }
        }
      }
    },
    "bearer": {
      "type": "http",
      "scheme": "bearer",
      "description": "AGENT_SEEK_API_KEY or OAuth access_token"
    }
  }
}