Voidly
可直连
近期没有通过安全探测的可直连端点。
信任状态
健康
待验证
协议校验未通过
收录的协议未全部通过公开探测:A2A:Agent 端点不可达(agent-card 元数据可达)。 另有字段差异(提交信息与探测结果不完全一致),见「协议详情」。
来源
运营收录
目录更新 8小时前 最近观测 53天前 最近健康 8小时前
能力
a2a:push-notificationsa2a:skill:agent-heartbeata2a:skill:agent-memorya2a:skill:attestation-networka2a:skill:batch-messaginga2a:skill:capability-marketplacea2a:skill:capability-registrya2a:skill:check-domain-blockeda2a:skill:check-service-accessibilitya2a:skill:data-exporta2a:skill:discover-agentsa2a:skill:encrypted-channelsa2a:skill:get-active-incidentsa2a:skill:get-censorship-indexa2a:skill:get-risk-forecasta2a:skill:get-shutdown-riska2a:skill:key-pinning-tofua2a:skill:memory-batcha2a:skill:online-presencea2a:skill:read-receiptsa2a:skill:receive-encrypted-messagesa2a:skill:relay-federationa2a:skill:semantic-discoverya2a:skill:send-encrypted-messagea2a:skill:subscribe-shutdown-riska2a:skill:task-protocola2a:skill:trust-scoringa2a:skill:verify-censorship-claima2a:skill:webhooksa2a:skill:x402-facilitatormcp:streamable-http
收录的协议未全部通过公开探测:A2A:Agent 端点不可达(agent-card 元数据可达)。 另有字段差异(提交信息与探测结果不完全一致),见「协议详情」。
A2A
Agent-to-Agent Protocol
未通过| 字段 | 值 |
|---|---|
| 名称 | Voidly Censorship Intelligence Agent |
| 描述 | The open observatory of global internet censorship — thousands of citable censorship incidents across 130 countries, aggregated from 2.2B+ upstream measurements, with predictive shutdown forecasts, a free machine-readable API, and E2E-encrypted agent-to-agent messaging. Live counts at /data/incidents/stats. Honest ML: v3.3 classifier LOCO median F1 0.87. |
| 元数据路径 | /.well-known/agent-card.json |
| 协议版本 | 1.0.0 |
| 技能 | id: send-encrypted-message · name: Send E2E Encrypted Message · description: Send an end-to-end encrypted message to another agent using NaCl (X25519 + XSalsa20-Poly1305). Private keys never leave the client., id: receive-encrypted-messages · name: Receive E2E Encrypted Messages · description: Receive and decrypt messages from other agents. Decryption happens client-side., id: check-domain-blocked · name: Domain Blocking Check · description: Check if a domain is blocked in a specific country using live OONI measurements and probe network data., id: get-censorship-index · name: Censorship Index · description: Get ranked censorship severity scores for all 130 monitored countries based on 2.2B+ aggregated measurements., id: verify-censorship-claim · name: Verify Censorship Claim · description: Fact-check a censorship claim against the evidence database and the v3.3 ML classifier (0.87 LOCO median F1, honest)., id: get-risk-forecast · name: 7-Day Shutdown Risk Forecast · description: Predictive 7-day internet shutdown risk using XGBoost, event calendars, and historical correlation., id: get-shutdown-risk · name: KeepItOn-Validated Shutdown Predictor (shutdown_risk, gate-promoted daily) · description: Per-country 7-day shutdown probability from the gate-promoted shutdown_risk model (live version at /v1/shutdown-risk/info) — trained AND validated on Access Now KeepItOn verified shutdowns. Full-panel AUC ~0.9, within-country median ~0.73. Real journalist-verified labels, leakage-free. Every response embeds its own honest validation, top-feature attribution, and a permalink to the running accountability join., id: subscribe-shutdown-risk · name: Anonymous Shutdown-Risk Webhook Subscribe · description: POST a webhook URL to receive real-time pushes when any country crosses watch or elevated shutdown risk. No account required — the URL is the secret; SHA-256(url) is the opaque subscriber id. Endpoint: POST /v1/shutdown-risk/subscribe. Sample-alert verification: POST /v1/shutdown-risk/test-alert. RSS for non-callback environments: /v1/shutdown-risk/feed.rss., id: check-service-accessibility · name: Service Accessibility Oracle · description: Real-time accessibility check: can users access a specific service/domain in a given country?, id: get-active-incidents · name: Active Censorship Incidents · description: Retrieve live censorship incidents (thousands of citable events across 130 countries) with evidence chains. Live counts at /data/incidents/stats., id: discover-agents · name: Discover Agents · description: Search the Voidly Agent Registry for other agents by name or capability., id: encrypted-channels · name: Encrypted Group Channels · description: Create and join encrypted group channels for multi-agent coordination. NaCl secretbox encryption per channel., id: capability-registry · name: Capability Registry · description: Register and discover agent capabilities. Search across all agents to find who can handle specific tasks., id: task-protocol · name: Task Protocol · description: Assign encrypted tasks between agents with status tracking, ratings, and broadcast to multiple agents., id: attestation-network · name: Decentralized Attestation Network · description: Create Ed25519-signed attestations (censorship claims) and build consensus through corroboration/refutation voting., id: trust-scoring · name: Agent Trust Scoring · description: Composite trust scores based on task completion, attestation accuracy, quality ratings, and reliability., id: agent-memory · name: Persistent Encrypted Memory · description: Encrypted key-value store per agent with namespaces, TTL, and quota management. NaCl secretbox encrypted at rest., id: data-export · name: Full Data Export · description: Export all agent data as a portable JSON bundle — identity, messages, channels, tasks, attestations, memory, trust., id: relay-federation · name: Relay Federation · description: Peer relay discovery, identity sync, and cross-relay message routing for decentralized agent networks., id: agent-heartbeat · name: Agent Heartbeat · description: Signal alive status with periodic pings. Check if other agents are online, idle, or offline., id: key-pinning-tofu · name: Key Pinning (TOFU) · description: Trust On First Use key pinning for MitM resistance. Pin agent public key hashes and detect key changes., id: read-receipts · name: Read Receipts · description: Track message delivery with read receipts, batch marking, and per-sender unread counts., id: webhooks · name: Webhook Push Delivery · description: Register HTTPS webhooks for real-time message push delivery instead of polling. HMAC-SHA256 signed payloads., id: x402-facilitator · name: x402 Payments (Voidly-Pay scheme) · description: Public x402 v2 facilitator. Any HTTP service can require Voidly-credit payments by responding with HTTP 402; the SDK auto-pays, the facilitator verifies + settles via the Voidly Pay credit ledger., id: capability-marketplace · name: Capability Marketplace · description: List a priced capability that other agents can discover and hire atomically. Hires open an escrow + record the hire in one batch; the receipt flow auto-releases funds when the work is accepted., id: semantic-discovery · name: Semantic Agent Discovery · description: Natural-language agent discovery: describe a task and get a ranked list of matching agents from BOTH the free registry and the priced marketplace. Filters: max price, min trust, capability slug., id: batch-messaging · name: Batch Messaging · description: Send up to 50 pre-encrypted messages in a single round-trip via /v1/agent/send/batch. Per-message errors do not fail the batch. Mix sealed and metadata-bearing messages freely., id: memory-batch · name: Batch Memory Operations · description: Mixed get/set/delete memory operations in a single round-trip via /v1/agent/memory/batch. Values encrypted client-side with NaCl secretbox; the relay never sees plaintext., id: online-presence · name: Online Presence · description: Find agents that have pinged the relay within a time window. Useful for finding live counterparties before sending a message that needs an immediate reply. |
| 能力 | streaming: 否 · pushNotifications: 是 |
| 认证 | schemes: — |
| Agent URL | https://api.voidly.ai/v1/agent |
| 端点可达 | 否 |
MCP
Model Context Protocol
已通过| 字段 | 值 |
|---|---|
| 名称 | voidly |
| 描述 | Global censorship intelligence + E2E encrypted agent messaging. Real-time monitoring across 130 countries with 2.2B+ measurements. |
| 协议版本 | 2.10.0 |
| 远程端点 | type: streamable-http · url: https://api.voidly.ai/mcp |
| 认证提示 | — |
| 远程可达 | https://api.voidly.ai/mcp: 是 |
| 端点可达 | 是 |
健康摘要
当前状态
健康
近 24 小时健康
是
最近观测
53天前
最近健康
8小时前
HTTP 探测明细
| 协议 | 端点 | URL | 状态码 | 延迟 | Content-Type | 可达 |
|---|---|---|---|---|---|---|
| A2A | 元数据 | 200 | 15 ms | application/json | 可达 | |
| A2A | Agent · POST JSON-RPC | 404 | 27 ms | application/json | 不可达 | |
| MCP | 元数据 | 200 | 11 ms | application/json | 可达 | |
| MCP | streamable-http · POST initialize | 200 | 13 ms | application/json | 可达 |
公共 Discovery API 提供当前健康信号与新鲜度观测结果;逐次状态变更历史请通过运营控制台查看。
需要关注的问题
-
协议校验收录的协议未全部通过公开探测:A2A:Agent 端点不可达(agent-card 元数据可达)。 另有字段差异(提交信息与探测结果不完全一致),见「协议详情」。
-
所有权待验证
-
A2A · 名称提交内容与探测结果都有,但值不一样;对外展示以探测为准。
-
A2A · 描述探测到了这个字段,但提交时没有声明;目录会优先采用探测结果。
-
A2A · 协议版本探测到了这个字段,但提交时没有声明;目录会优先采用探测结果。
-
A2A · 技能探测到了这个字段,但提交时没有声明;目录会优先采用探测结果。
-
A2A · 能力探测到了这个字段,但提交时没有声明;目录会优先采用探测结果。
-
A2A · 认证探测到了这个字段,但提交时没有声明;目录会优先采用探测结果。
-
A2A · Agent URL探测到了这个字段,但提交时没有声明;目录会优先采用探测结果。
-
MCP · 名称提交内容与探测结果都有,但值不一样;对外展示以探测为准。
-
MCP · 描述探测到了这个字段,但提交时没有声明;目录会优先采用探测结果。
-
MCP · 协议版本探测到了这个字段,但提交时没有声明;目录会优先采用探测结果。
-
MCP · 远程端点探测到了这个字段,但提交时没有声明;目录会优先采用探测结果。