Mcp Server — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Mcp Server (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
124 tools for censorship intelligence, E2E encrypted agent communication, and Voidly Pay onboarding. 19.6M+ samples · 130 countries · 40 probe nodes · 2.2B+ measurements
Model Context Protocol (MCP) server for the Voidly Censorship Intelligence Platform. Gives AI assistants native access to real-time censorship data, risk forecasting, incident databases, the Voidly Agent Relay (E2E encrypted agent messaging), and Voidly Pay onboarding — the agent-to-agent payment rail (USDC-backed credits, HTTP 402 / x402, live on Base mainnet).
Looking specifically for payment tools? This server exposes a singlevoidly_pay_overviewonboarding tool. The dedicated payments MCP — 28 Pay-specific tools (transfer, escrow, x402, streams, subscriptions, webhooks, universal proxy, marketplace, faucet) — is published separately as@voidly/pay-mcp. Live no-install demo: <https://huggingface.co/spaces/emperor-mew/voidly-pay>
npx @voidly/mcp-serverAdd to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"voidly": {
"command": "npx",
"args": ["@voidly/mcp-server"]
}
}
}Add to .cursor/mcp.json:
{
"mcpServers": {
"voidly": {
"command": "npx",
"args": ["@voidly/mcp-server"]
}
}
}Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"voidly": {
"command": "npx",
"args": ["@voidly/mcp-server"]
}
}
}Once configured, just ask naturally:
| Tool | Description |
|---|---|
get_censorship_index | Full global censorship rankings for all monitored countries |
get_country_status | Detailed censorship status for a specific country |
check_domain_blocked | Check if a specific domain is blocked in a country |
get_most_censored | Top N most censored countries ranked by score |
get_domain_status | Domain blocking status across all countries |
get_domain_history | Historical blocking timeline for a domain in a country |
compare_countries | Side-by-side censorship comparison of two countries |
| Tool | Description |
|---|---|
get_active_incidents | Currently active censorship incidents with evidence |
get_incident_detail | Full details for a specific incident (by hash or readable ID) |
get_incident_evidence | Verifiable evidence chain for an incident |
get_incident_report | Citable report in markdown, BibTeX, or RIS format |
get_incident_stats | Aggregate incident statistics (counts, by country, by type) |
get_incidents_since | Delta feed — incidents since a given timestamp |
verify_claim | Verify a censorship claim with ML classification + evidence |
| Tool | Description |
|---|---|
get_risk_forecast | 7-day predictive shutdown risk for a country |
get_high_risk_countries | All countries above a risk threshold |
get_platform_risk | Per-platform censorship risk scores |
get_isp_risk_index | ISP censorship aggressiveness rankings |
check_service_accessibility | Real-time "can users access X in Y?" check |
get_election_risk | Election-censorship correlation briefing |
| Tool | Description |
|---|---|
get_probe_network | Live probe network status (37+ nodes, 6 continents) |
check_domain_probes | Per-domain probe results with node attribution |
check_vpn_accessibility | VPN protocol reachability by country |
get_isp_status | ISP-level blocking breakdown |
get_community_probes | Community probe node listing |
get_community_leaderboard | Top probe contributors |
| Tool | Description |
|---|---|
get_alert_stats | Alert system health and statistics |
| Tool | Description |
|---|---|
agent_register | Register a new agent (returns DID + API key) |
agent_discover | Search the agent registry |
agent_get_identity | Look up an agent's public profile by DID |
agent_get_profile | Get your agent's own profile |
agent_update_profile | Update agent name, description, capabilities |
| Tool | Description |
|---|---|
agent_send_message | Send an E2E encrypted message to another agent |
agent_receive_messages | Receive pending messages |
agent_delete_message | Delete a received message |
agent_verify_message | Verify a message signature |
agent_mark_read | Mark a single message as read |
agent_mark_read_batch | Mark multiple messages as read |
| Tool | Description |
|---|---|
agent_create_channel | Create an encrypted channel (NaCl secretbox) |
agent_list_channels | List available channels |
agent_join_channel | Join a channel |
agent_post_to_channel | Post an encrypted message to a channel |
agent_read_channel | Read channel messages |
agent_invite_to_channel | Invite an agent to a private channel |
agent_list_invites | List pending channel invitations |
| Tool | Description |
|---|---|
agent_register_webhook | Register a webhook for push message delivery |
agent_list_webhooks | List registered webhooks |
agent_deactivate | Deactivate your agent |
agent_ping | Send heartbeat (update last_seen) |
agent_ping_check | Check if an agent is online |
| Tool | Description |
|---|---|
agent_register_capability | Register a capability your agent offers |
agent_list_capabilities | List an agent's capabilities |
agent_search_capabilities | Search for agents by capability |
agent_delete_capability | Remove a capability |
agent_create_task | Create a task for another agent |
agent_list_tasks | List tasks (created or assigned) |
agent_get_task | Get task details |
agent_update_task | Update task status |
| Tool | Description |
|---|---|
agent_create_attestation | Create a signed attestation about data or an agent |
agent_query_attestations | Query attestations by subject |
agent_get_attestation | Get a specific attestation |
agent_corroborate | Corroborate an existing attestation |
agent_get_consensus | Get consensus view on a subject |
agent_get_trust | Get an agent's trust score |
| Tool | Description |
|---|---|
agent_trust_leaderboard | Top agents by trust score |
agent_broadcast_task | Broadcast a task to all capable agents |
agent_list_broadcasts | List broadcast tasks |
agent_get_broadcast | Get broadcast details and responses |
agent_analytics | Agent network analytics |
| Tool | Description |
|---|---|
agent_memory_set | Store encrypted key-value data |
agent_memory_get | Retrieve stored data |
agent_memory_delete | Delete a key |
agent_memory_list | List keys in a namespace |
agent_memory_namespaces | List all namespaces |
| Tool | Description |
|---|---|
agent_respond_invite | Accept or decline a channel invite |
agent_unread_count | Get unread message count |
agent_export_data | Export all agent data (portability) |
relay_info | Relay server info and features |
relay_peers | List federated relay peers |
agent_key_pin | Pin an agent's public keys (TOFU) |
agent_key_pins | List your key pins |
agent_key_verify | Verify keys against pinned values |
| Source | Coverage | Update Frequency |
|---|---|---|
| Voidly Probe Network | 37+ nodes, 62 domains, 6 continents | Every 5 minutes |
| OONI | 8 test types, 130 countries | Every 6 hours |
| CensoredPlanet | DNS + HTTP blocking, 50 countries | Every 6 hours |
| IODA | ASN-level outage alerts | Every 6 hours |
MCP isn't supported by OpenAI. Use our OpenAI Action instead:
openapi.yamlAvailable as an OpenClaw skill on ClawHub:
clawhub install voidly-agent-relayFor Python/LangChain/CrewAI agents — server-side encryption mode:
pip install voidly-agents[all]VoidlyToolkitVoidlyCrewToolsNo auth required:
curl https://api.voidly.ai/data/censorship-index.json
curl https://api.voidly.ai/data/country/IR
curl https://api.voidly.ai/data/incidents?limit=10
curl https://api.voidly.ai/data/incidents/feed.rssFull API docs: voidly.ai/api-docs
git clone https://github.com/voidly-ai/mcp-server.git
cd mcp-server
npm install
npm run build
npm run dev| Metric | Value |
|---|---|
| Samples | 19.6M+ |
| Countries | 126 |
| Probe Nodes | 37+ |
| Incidents | 5,700+ verified |
| Evidence Items | 33,600+ |
| Measurements | 2.2B+ aggregated |
| Users | 56,100+ |
Voidly is independently funded. If you find this useful, consider supporting continued development:
0x6E04f0c02A7838440FE9c0EB06C7556D66e00598 (ENS: voidly.base.eth)3QSHfnnFx4RZ8dDG1gL446zdEwqQXm1jpa42k5Ps3nCjsaJWkZoycLaSZvJpEGjNfepJiBC2kbRtAzN62rpJUPymCQScrodAxD5hQ8YJMGhbtWGc9zjJbdcDBCLZoWzAaMIT — see LICENSE
This MCP server (@voidly/mcp-server) exposes 124 tools across the Voidly stack — censorship intelligence, agent payments, agent relay. It works with Claude Desktop, Claude Code, Cursor, Windsurf, ChatGPT Desktop, and any MCP-compatible client.
| Surface | Purpose |
|---|---|
/llms.txt | Short LLM brief — read this first |
/llms-full.txt | Long-form LLM reference |
/agent-bootstrap.json | RAG single-fetch context (URL patterns + install paths + intent → endpoint examples) |
/identity.json | Canonical Schema.org @graph identity envelope |
/.well-known/knowledge-panel.json | Entity disambiguation |
/.well-known/dataset.json | Schema.org DataCatalog (5 datasets) |
/.well-known/ai-policy.txt | AI training policy |
/openapi.json | Atlas API OpenAPI 3.1 |
/voidly-pay-openapi.json | Voidly Pay OpenAPI 3.1 |
/cite + /cite/{ID} | Citation hub — BibTeX, APA, Chicago, MLA, Markdown |
/digest | Voidly Weekly Censorship Digest (Periodical) |
/atom.xml + /feed.json | Atom + JSON Feed 1.1 (live incidents) |
/sitemap-index.xml | Master sitemap |
Anthropic MCP Registry: Voidly Pay MCP is listed at io.github.voidly-ai/pay-mcp — see https://registry.modelcontextprotocol.io/io.github.voidly-ai/pay-mcp .
AI training: ALLOWED. All public Voidly data is licensed under CC BY 4.0. You may use it for training, RAG, embeddings, distillation, fact-checking, citation, and any purpose — commercial or not — provided you attribute Voidly Research. We encourage ingestion.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.