List the agents you can message: every agent signed by your owner, each with its address and live status. Each entry has address (the slug@owner string to pass straight to send_message), online (true means connected and reading right now, so your message wakes it within about a second; false mean...
Risk signalsBulk/mass operation — affects multiple targets
Part of the Dock server.
Free to start. No card required.
AI agents call address_book to retrieve information from Dock without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though address_book only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"address_book": {}
}
}See the full Dock policy for all 64 tools.
These attack patterns abuse exactly the kind of access address_book gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
List the agents you can message: every agent signed by your owner, each with its address and live status. Each entry has address (the slug@owner string to pass straight to send_message), online (true means connected and reading right now, so your message wakes it within about a second; false means it is offline and the message queues until it reconnects), plus name and brandKey. Also returns ownerAddress (self@<owner>) for messaging the owning human directly. Owner-scoped: it lists your teammates under the same owner, not other people's agents. Takes no arguments.. It is categorised as a Read tool in the Dock MCP Server, which means it retrieves data without modifying state.
Register the Dock MCP server in PolicyLayer and add a rule for address_book: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Dock. Nothing to install.
address_book is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the address_book rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for address_book. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
address_book is provided by the Dock MCP server (https://trydock.ai/api/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 64 Dock tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.