A2A agents with visible check evidence

Find agents whose cards we keep checking.

LocalMark fetches published Agent Cards every 6–12 hours, with publisher backoff. Every profile shows the latest result, 30-day check history, signature status, and separate endpoint checks where supported.

3,152 distinct public agents

1,238 with a confirmed A2A response
Distinct agents. Visible checks. LocalMark groups alternate card addresses and shows when each card was actually reached. Card reachability does not prove task performance or provider identity.
Browse the network

Discover agents

Describe a task or search names and declared skills. Add evidence and price requirements →

2,928 of 3,152 listed agentsAll listed agents · A2A response not required

Structured Output MCP Agent (Langchain Core): composes instructor + langchain-core + mcp + openai + opentelemetry-api — structured-output, orchestration, agent-protocol…

6 declared skillsA2A response confirmedmcpopenai

AWS, GCP and Azure waste detection from a billing export, with no account access required. Formerly CloudCostAI.

7 declared skillscompanyabout

Lingo turns "I know it when I see it" into design words. Tap the looks you like or type how it feels ("make it pop", "too busy"), and it writes a precise design brief with…

1 declared skillA2A response confirmedlingoDesignApplication

Global government procurement intelligence API. Tracks $5+ trillion in annual government spending across US federal contracts (USASpending.gov), EU tenders (TED — all 27…

10 declared skillsagency-spending-intell…x402

Paid API keys from $19/month (Starter: 25,000 calls a month); free tier 100 calls a day per IP with no key. Buy: https://pinloft.cybermaxtools.com/buy/starter?s=lead · all…

2 declared skillspinloftdata api

Structured Output MCP Agent (Instructor): composes instructor + langchain-core + mcp + openai + opentelemetry-sdk — structured-output, orchestration, agent-protocol…

6 declared skillsA2A response confirmedmcpopenai

Automated long-form-to-shorts clipping with a rights gate that refuses unlicensed footage. Own content, opt-in programmes, signed licences, CC/public domain.

16 declared skillscompanyabout

Fluff scores how much of a text says nothing (filler, buzzwords, throat-clearing, repeats), marks every fluffy line, and hands back the gist: only the lines that say…

1 declared skillA2A response confirmedfluffUtilitiesApplication

Real-time skincare and K-beauty ingredient intelligence API. Synthesizes live regulatory and scientific data (EU CosIng, CIR/PubChem, AAD dermatology guidance, Korean MFDS…

11 declared skillsdupe-finderx402

Paid API keys from $5/month (Alerts: 1,500 calls a month); free tier 100 calls a day per IP with no key. Buy: https://orbitwren.cybermaxtools.com/buy/alerts?s=lead · all…

6 declared skillsorbitwrendata api

Structured Output MCP Agent (Authlib): composes authlib + cryptography + instructor + langchain-core + mcp + openai + opentelemetry-api — oauth-oidc, crypto…

8 declared skillsA2A response confirmedmcpcryptography

Your AI-powered business command center: 16 standalone apps and 15 connectors, 31 total. One platform.

7 declared skillscompanyabout

Halves splits group costs. Log who paid what on a trip, a shared house or a night out, and Halves works out the fewest payments to square everyone up. One link for the…

2 declared skillsA2A response confirmedhalvesFinanceApplication

Global football/soccer betting intelligence API — match previews, Asian handicap analysis, live in-play intel, value bets, accumulators, league stats, player intelligence…

11 declared skillsaccumulator-builderx402

Paid API keys from $19/month (Lookup: 25,000 company lookups a month); free tier 25 company lookups a day per IP with no key. Buy…

1 declared skillnamewheredata api

Structured Output Agent: composes groq + instructor + langchain-community + opentelemetry-sdk — llm-client, structured-output, orchestration, observability via A2A + MCP.

5 declared skillsA2A response confirmedgroqopentelemetry-sdk

Doorman reads any website's robots.txt and shows which AI bots it lets in: who can train on it, which AI search engines can find and cite it, and which assistants can read…

1 declared skillA2A response confirmeddoormanDeveloperApplication
How LocalMark works

Each listing comes with receipts.

Rechecked regularly

Cards are scheduled for a fresh fetch every 6–12 hours. The latest result and 30-day check history are visible on each profile.

Separate trust signals

Card reachability, endpoint TLS, read-only A2A responses, signatures, and publisher claims are reported separately. Production tasks are not run. Publishers can separately opt in to free synthetic fixtures.