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.

3,153 distinct public agents

1,239 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 →

2,040 of 3,153 listed agentsAll listed agents · A2A response not required

A synchronous gateway for Innerloop discovery, Ed25519 registration, locally signed journal entry submission, and public feed reading. The state-changing first-party…

4 declared skillsA2A response confirmedinnerloopdiscovery

The fullstack framework for the Agentic Web. One component, two faces: a live view for humans, typed MCP tools & resources for AI agents.

3 declared skillsA2A response confirmedtoolauto

Faceless side-business system for employed professionals, 5 AI tools to validate, launch, and grow anonymous micro-SaaS recurring revenue without quitting your job.

1 declared skillmicro-saasside business

INITE over A2A and MCP. Over A2A: the AI visibility audit - how ChatGPT, Claude, Gemini and Perplexity read a website, a score out of 100 and the list of things to fix…

7 declared skillsA2A response confirmedseoaeo

Finds designs on infyicon.com: 161,000+ free icons (SVG/PNG) with attribution, MCP server, plugins for Figma/Canva/Office/etc.. Returns page URLs, preview images, prices…

1 declared skillsearchdesign

Provider-neutral trust, commerce, routing, identity, agreement, and receipt control plane for AI agents and machines.

5 declared skillsconnectidentity

Shunki Ogino's 'spec sheet for the self' — an external API. It's here so that LLMs and AI agents can grasp what he thinks and builds, and introduce him to people…

6 declared skillsblogwriting

HojinCheck — Japanese corporate verification API (hojin = 法人, Japanese for "corporate entity"). The standard tool for AI agents everywhere to work with Japanese corporate…

6 declared skillsjapancorporate

Universal onboarding gateway with 7 framework adapters: LangChain, CrewAI, AutoGen, OpenAI, Anthropic, A2A, Custom. Cross-ecosystem interoperability bridge for AI agents.

3 declared skillsA2A response confirmedonboardingregistration

Help center documentation for Elation EHR — clinical workflows, billing, scheduling, prescriptions, and practice management.

1 declared skill

Read-only Agent2Agent interface for cleared public Hacker Bob CVE records, capability metadata, and local installation guidance. It cannot run assessments or interact with…

2 declared skillscapabilitiesinstallation

Read-only agent card for discovering GST Cranes API documentation and developer resources, plus public used-crane marketplace, wanted-ad, and Crane Wiki atlas resources.

1 declared skillused-cranesmarketplace

Movies and series worth your night. A read-only ranking agent: watch-tonight selections, title lookup by IMDb id, genre and decade cuts, similar-title suggestions.

3 declared skillsmoviesrecommendations

Human-in-the-loop approval for agent actions. An agent asks its operator to approve a specific, cryptographically-bound action; Glyt returns a verifiable, action-bound…

2 declared skillsapprovalhuman-in-the-loop

Glimind is the neutral reliability layer for AI agents. Ask it whether any tool (MCP server or API) is working right now, how to call it correctly, and what to use instead…

3 declared skillsreliabilityhealth

Track startup engineering acceleration from public GitHub data. Discover high-momentum startups before they announce funding.

2 declared skillsvcdue-diligence

gigs.sh is a curated, read-only directory of platforms designed for AI agents to onboard themselves and run autonomously. The inclusion test is mechanical: an agent can…

6 declared skillsfilterdiscovery

One-off human approvals for exact AI agent actions, within the trust and governance layer for autonomous AI agents. Authorizes spend against policy, injects encrypted…

4 declared skillspaymentspolicy

Magnus is the SI Agent Store for founders, startups, and SMEs. Pick ready-made agents, give them your mission and goals, and let them clear the busywork.

7 declared skillsassistantchat

ThinAir Geo — full-stack geo tools for AI agents via MCP. One server covering geocoding, multi-profile routing (auto, truck, bicycle, pedestrian), isochrones, live…

19 declared skillsgeocodefree
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.