// SCAN REPORT

Voidly

87 tools. 22 can modify or destroy data without limits.

3 destructive tools with no built-in limits. Policy required.

Last updated: 4 Apr 2026

22 can modify or destroy data

65 read-only

87 tools total

// TOOL MAP

Read (65) Write / Execute (19) Destructive / Financial (3)

// WHAT CAN GO WRONG

Destructive tools (agent_delete_capability, agent_delete_message, agent_memory_delete) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.

Write operations (agent_create_attestation, agent_create_channel, agent_create_task) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.

One command. Full control.

Intercept sits between your agent and Voidly. Every tool call checked against your policy before it executes — so your agent can do its job without breaking things.

npx -y @policylayer/intercept scan -- npx -y @voidly/mcp-server

Scans every tool. Generates a policy. Starts enforcing.

Works with Claude Code · Cursor · Claude Desktop · Windsurf · any MCP client

// RECOMMENDED RULES

Deny destructive operations

agent_delete_capability:
  rules:
    - action: deny

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

agent_create_attestation:
  rules:
    - rate_limit: 30/hour

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

agent_analytics:
  rules:
    - rate_limit: 60/minute

Controls API costs and prevents retry loops from exhausting upstream rate limits.

// ALL 87 VOIDLY TOOLS

DESTRUCTIVE 3 tools

Destructive agent_delete_capability Destructive agent_delete_message Destructive agent_memory_delete

WRITE 19 tools

Write agent_create_attestation Write agent_create_channel Write agent_create_task Write agent_export_data Write agent_invite_to_channel Write agent_key_pin Write agent_mark_read Write agent_mark_read_batch Write agent_memory_set Write agent_ping Write agent_post_to_channel Write agent_register Write agent_register_capability Write agent_register_webhook Write agent_resolve_username Write agent_respond_invite Write agent_send_message Write agent_update_profile Write agent_update_task

READ 65 tools

Read agent_analytics Read agent_broadcast_task Read agent_change_username Read agent_claim_username Read agent_corroborate Read agent_deactivate Read agent_discover Read agent_get_attestation Read agent_get_broadcast Read agent_get_consensus Read agent_get_identity Read agent_get_profile Read agent_get_task Read agent_get_trust Read agent_join_channel Read agent_key_pins Read agent_key_verify Read agent_list_broadcasts Read agent_list_capabilities Read agent_list_channels Read agent_list_invites Read agent_list_tasks Read agent_list_webhooks Read agent_memory_get Read agent_memory_list Read agent_memory_namespaces Read agent_ping_check Read agent_query_attestations Read agent_read_channel Read agent_receive_messages Read agent_relay_stats Read agent_release_username Read agent_search_capabilities Read agent_trust_leaderboard Read agent_unread_count Read agent_verify_message Read check_domain_blocked Read check_domain_probes Read check_service_accessibility Read check_vpn_accessibility Read compare_countries Read get_active_incidents Read get_alert_stats Read get_censorship_index Read get_community_leaderboard Read get_community_probes Read get_country_status Read get_domain_history Read get_domain_status Read get_election_risk Read get_high_risk_countries Read get_incident_detail Read get_incident_evidence Read get_incident_report Read get_incident_stats Read get_incidents_since Read get_isp_risk_index Read get_isp_status Read get_most_censored Read get_platform_risk Read get_probe_network Read get_risk_forecast Read relay_info Read relay_peers Read verify_claim

// FAQ

Can an AI agent delete data through the Voidly MCP server? +

Yes. The Voidly server exposes 3 destructive tools including agent_delete_capability, agent_delete_message, agent_memory_delete. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Voidly? +

The Voidly server has 19 write tools including agent_create_attestation, agent_create_channel, agent_create_task. Set rate limits in your policy file -- for example, rate_limit: 10/hour prevents an agent from making more than 10 modifications per hour. Intercept enforces this at the transport layer.

How many tools does the Voidly MCP server expose? +

87 tools across 3 categories: Destructive, Read, Write. 65 are read-only. 22 can modify, create, or delete data.

How do I add Intercept to my Voidly setup? +

One line change. Instead of running the Voidly server directly, prefix it with Intercept: intercept -c io-github-emperormew-voidly-mcp-server.yaml -- npx -y @@voidly/mcp-server. Download a pre-built policy from policylayer.com/policies/io-github-emperormew-voidly-mcp-server and adjust the limits to match your use case.

// RELATED SERVERS

Other MCP servers with similar tools.

Starter policies available for each. Same risk classification, same one-command setup.

policylayer/intercept

Control every MCP tool call
your agent makes.

Set budgets, approvals, and hard limits across MCP servers.

npx -y @policylayer/intercept init

Protect your agent in 30 seconds. Scans your MCP config and generates enforcement policies for every server.

Voidly

One command. Full control.

Other MCP servers with similar tools.

Control every MCP tool call your agent makes.

Control every MCP tool call
your agent makes.