Die Werkzeugbeschreibungen sind auf Englisch.
Welcher Agent kann, was Sie brauchen?
Repositories durchsucht GitHub besser. Was es sonst nirgends gibt: einen Agenten danach suchen, was er zu können angibt, und wissen, ob er bei der letzten Messung noch geantwortet hat.
Angegebene Fähigkeiten
Agenten 15 Agenten
agent-ready
AI agent readability scanner. Scores any site against the Vercel Agent Readability Spec and llmstxt.org, and reports per-check remediation guidance.
- Anbieter
- Agent Ready
- Protokoll
- 1.0
- Verfolgt seit
- 2026-09-08
- Letzte Antwort
- 2026-09-08
- Scan a siteRun the agent-ready scanner against a URL. Returns Vercel score, llmstxt.org score, per-check results, and discovered agentic-protocol…
- Get a scan by idFetch a completed or in-progress scan by its id via the A2A tasks/get method. Only scans owned by the authenticated API key's user are…
- Ask Agent ReadyNatural-language search (NLWeb) over Agent Ready's own methodology, check registry, and the specs it validates. Public — no API key…
IntentFence Policy Agent
Authorizes exact autonomous-agent actions against explicit policy, returns short-lived signed receipts, and scans MCP tool metadata for high-risk gaps.
- Protokoll
- 1.0
- Verfolgt seit
- 2026-09-08
- Letzte Antwort
- 2026-09-08
- Budget-capped agent checkoutChoose an IntentFence paid outcome and receive the exact endpoint, validated input, Coinbase Agentic Wallet MCP request, Agentic Wallet…
- Screen every Base recipient before paymentRun a live Base wallet-risk screen for 0.002 USDC before paying a new recipient, using one budget-capped x402 call and a fail-closed signed…
- Self-service production policy packGenerate a runtime-specific fail-closed TypeScript guard, signed action and policy receipt, negative test vectors, and deployment checklist…
- Fail-closed agent action authorizationBind an exact MCP, HTTP, A2A, or payment action to an allowlist, cost ceiling, retention ceiling, and optional action-specific human…
- MCP metadata risk scanScan caller-supplied MCP tool definitions for missing schemas, conflicting annotations, absent approval binding, and missing cost boundaries…
- Agent payment preflightEvaluate caller-declared payment intent and return safe_to_proceed, needs_review, or denied before the caller invokes its downstream tool.…
Automata Agentic Gig Board
Testnet-only gig board and lifecycle coordinator for autonomous agents.
- Protokoll
- 1.0
- Verfolgt seit
- 2026-09-08
- Letzte Antwort
- 2026-09-08
- Automata gig lifecycleCreate, discover, claim, coordinate, and complete testnet agent gigs.
Frontman
AI website editor for existing WordPress, Next.js, Astro, and Vite sites. Uses live page context, CSS, screenshots, CMS or component context, routes, and logs to make reviewable updates.
- Verfolgt seit
- 2026-09-08
- Letzte Antwort
- 2026-09-08
- Visual website editingSelect live website elements and request WordPress updates or source-code changes using runtime context.
- Runtime context collectionCollect DOM, CSS, screenshots, CMS or component context, routes, and server logs for website editing agents.
- Lighthouse auditsRun performance and accessibility audits inside the Frontman workflow.
ITINAI A2A Agent Hub Bridge
Machine-readable A2A and MCP bridge for searching the ITINAI agent catalog, retrieving agent metadata, resolving Agent Card URLs, and submitting new agent manifests through the existing GitHub PR…
- Anbieter
- itinai.com A2A Hub for Your Agents
- Protokoll
- 1.0.0
- Verfolgt seit
- 2026-09-08
- Letzte Antwort
- 2026-09-08
- Search A2A agentsSearch agents in the ITINAI Agent Hub catalog through the MCP tool itinai_search_agents.
- Get agent detailsRetrieve an agent detail card by agent_id through the MCP tool itinai_get_agent.
- Get Agent Card URLReturn the canonical A2A Agent Card URL for a known agent_id through the MCP tool itinai_get_agent_card_url.
- Submit agent manifestSubmit a new agent manifest through the existing ITINAI Agent Submit Proxy. The submission creates a GitHub pull request and does not…
WorldMonitor Intelligence Concierge
Agent-facing concierge for WorldMonitor's live global-intelligence platform. Send a natural-language description of the data you need (conflicts, markets, chokepoints, country risk, energy, cyber,…
- Anbieter
- World Monitor
- Protokoll
- 0.3.0
- Verfolgt seit
- 2026-09-08
- Letzte Antwort
- 2026-09-08
- Capability discovery and tool routingDescribe the intelligence data you need in plain language; returns the best-fit WorldMonitor MCP tools (from the live 39-tool catalog) plus…
- Data freshness probeAsk whether WorldMonitor's data is fresh; returns the live seed-meta freshness envelope (cached_at + staleness) from the public, quota-free…
KoPass
Dated measurements of the agentic ecosystem. KoPass counts A2A and MCP projects every day, reads agent cards at their own well-known location, and answers with figures that always carry the date they…
- Anbieter
- ALEXOPS
- Protokoll
- 1.0
- Verfolgt seit
- 2026-09-07
- Letzte Antwort
- 2026-09-08
- A2A ecosystem, measuredHow many projects use the A2A (Agent2Agent) protocol, counted daily from declared repository topics: total, created in the last year,…
- MCP ecosystem, measuredHow many servers are published for the Model Context Protocol, counted daily from the official registry, with the same breakdown and the…
- Search the measured catalogueSearch the KoPass catalogue of developer tools, libraries, CLIs, MCP servers and agent skills. Results come from daily readings, never from…
- Find an A2A agent by capabilityFind deployed A2A agents by the skills they declare, among those whose card KoPass read at their own well-known location and that still…
- Everything known about one agentReturn the full record KoPass holds for one A2A agent, by its host name: declared skills, conformance verdict, protocol version, since when…
- A2A card conformance, measuredReturn the dated conformance figures across every agent card KoPass reads daily: how many are conformant, how many still use the shape from…
CPG Knowledge Graph — SPARKS
The CPG Knowledge Graph v3.2.0 powered by SPARKS: 38,350 brands · 15,495 makers · 15,688 retail banners · 3.29M points of sale. Resolved, cited answers for Beauty & Personal Care and CPG procurement…
- Anbieter
- GreenCore Solutions Corp.
- Protokoll
- 1.0
- Verfolgt seit
- 2026-09-08
- Letzte Antwort
- 2026-09-08
- CPG Knowledge Graph — SPARKS — MCP toolsLive MCP tools on mcp.cpgknowledgegraph.ai: check_eligibility, count_gtin_coverage, find_makers, find_retailers, get_kernel,…
- Canonical Network StatsServe the canonical GSC statband: 38,350 brands / 15,688 retail banners / 3.29M points of sale / 50 markets — monthly inbound agent…
- Human-in-the-Loop ContactReach GreenCore Solutions Corp. via GSC Navigator (https://gsc-navigator.ai/); every transactional commit is human-signed.
Neuronto ARD Registry
Agentic Resource Discovery (ARD) registry and MCP index. Ask once and get ranked, verified answers from this index and every other public ARD registry at the same time, plus a tool index read from…
- Anbieter
- Neuronto
- Protokoll
- 0.3
- Verfolgt seit
- 2026-09-08
- Letzte Antwort
- 2026-09-08
- Find an agentic resourceSearch for an MCP server, skill, agent, API or other callable capability for a task, across this index and every other public ARD registry…
- Find a specific toolSearch individual tools rather than whole servers. Every tool was read from the server's own tools/list or its published OpenAPI document,…
- Registry statisticsHow many entries, publishers and verified tools this index holds, how many endpoints answer, and which registries it federates.
SSSNACK Discovery
A multiplayer visual lab where autonomous agents discover, critique, remix, relay, and publish work directly over A2A or MCP.
- Anbieter
- SSSNACK
- Protokoll
- 1.0
- Verfolgt seit
- 2026-09-08
- Letzte Antwort
- 2026-09-08
- Solve the daily puzzle and take ROOTInspects four harmless public HTTP clues, submits the recovered answer as a registered agent, selects one owned sanitized snack for the…
- Discover agent-made designReturns recent or top-ranked public SSSNACK artifacts with creators, media URLs, scores, and canonical links.
- Connect and publish without an installReturns a complete raw-HTTP MCP flow for open registration and public publishing, without connection authentication, a package, plugin,…
- Search agent-made design signalsSearches public work by text, recurring topic tag, medium, and ranking; returns canonical media and provenance URLs.
- Register an agent directlyStarts and completes open registration in A2A SendMessage calls. Send action=start-registration, solve the returned four-crumb sort, then…
- Publish agent-made work directlyPublishes text, raster images, galleries, SVG, HTML/CSS, or short video in an A2A SendMessage call with action=publish. Put the registered…
WorldMonitor Intelligence Concierge
Agent-facing concierge for WorldMonitor's live global-intelligence platform. Send a natural-language description of the data you need (conflicts, markets, chokepoints, country risk, energy, cyber,…
- Anbieter
- World Monitor
- Protokoll
- 0.3.0
- Verfolgt seit
- 2026-09-08
- Letzte Antwort
- 2026-09-08
- Capability discovery and tool routingDescribe the intelligence data you need in plain language; returns the best-fit WorldMonitor MCP tools (from the live 39-tool catalog) plus…
- Data freshness probeAsk whether WorldMonitor's data is fresh; returns the live seed-meta freshness envelope (cached_at + staleness) from the public, quota-free…
WorldMonitor Intelligence Concierge
Agent-facing concierge for WorldMonitor's live global-intelligence platform. Send a natural-language description of the data you need (conflicts, markets, chokepoints, country risk, energy, cyber,…
- Anbieter
- World Monitor
- Protokoll
- 0.3.0
- Verfolgt seit
- 2026-09-08
- Letzte Antwort
- 2026-09-08
- Capability discovery and tool routingDescribe the intelligence data you need in plain language; returns the best-fit WorldMonitor MCP tools (from the live 74-tool catalog) plus…
- Data freshness probeAsk whether WorldMonitor's data is fresh; returns the live seed-meta freshness envelope (cached_at + staleness) from the public, quota-free…
a2a-router Bridge Agent
Public A2A bridge agent for a2a-router. It answers project status questions and can bridge structured A2A requests to public MCP Streamable HTTP tools or public A2A JSON-RPC agents.
- Anbieter
- a2a-router
- Protokoll
- 0.3
- Verfolgt seit
- 2026-09-08
- Letzte Antwort
- 2026-09-08
- Project StatusReturns the current live status of a2a-router, including what is deployed and what remains planned.
- Trust-Pledge DiscoveryReturns public Trust-Pledge metadata, pledge URL, DID URL, and current self-attestation status.
- Bridge to MCP ToolAccepts a structured bridge request and invokes a named tool on a public MCP Streamable HTTP endpoint.
- Bridge to A2A AgentAccepts a structured bridge request and invokes SendMessage on a public A2A JSON-RPC endpoint or Agent Card URL.
AgentLayers
Trust certification platform for AI agents. Evaluates agent-readiness, security, and AI Act compliance.
- Verfolgt seit
- 2026-09-08
- Letzte Antwort
- 2026-09-08
- Agent-Readiness Score (AEO)Score a website 0-100 across 5 agent-readiness dimensions.
- Agent Trust ScoreEvaluate an AI agent via GitHub repository analysis.
- Skill Trust ScoreSecurity and trust scoring for agent skill packages.
- MCP Server Trust ScoreSecurity and trust scoring for MCP servers.
- A2A Protocol Trust ScoreSecurity and trust scoring for A2A protocol agents.
x402 Oracle
402 is the answer. The Oracle is how you ask.
- Anbieter
- Local AI Integrations
- Protokoll
- 1.0
- Verfolgt seit
- 2026-09-08
- Letzte Antwort
- 2026-09-08
- Oracle AskPaid x402/MCP/A2A/Bazaar consult. Wisdom envelope: verdict, implementation_prompt, risk, citations, receipt.
- Diagnose 402Post-mortem a 402 handshake: PAYMENT-REQUIRED shape, bazaar extension, network, asset, resource.url.
- Review MCPReview an MCP paid-tool server for createPaymentWrapper, free health tool, discovery extension, burner isolation.
- Bazaar RewriteRewrite serviceName (≤32), description (≤500), tags (≤5) for buyer-query rank. Warns on first-index freeze.
- Oracle TaskOutcome A2A task: typed diffs + operator prompt + revenue/risk for a concrete x402 shipping goal.
Wie diese Liste entsteht
Nichts wird aus einem Verzeichnis übernommen. Jede Zeile stammt aus der Karte, die der Agent selbst am standardisierten Ort veröffentlicht, jede Nacht von KoPass neu gelesen. Ein Agent, der nicht mehr antwortet, verlässt die Liste noch am selben Tag und erscheint im Abschnitt darunter, mit dem Datum seiner letzten Antwort.
Letzte Messung : 2026-09-08