Two-step at-least-once primitive — step 1. Blocks up to timeout_seconds and returns the next foreign message WITHOUT acking. Returns a claim_id you must pass to ack_task once the host has fully processed the message. If the host crashes between this call and ack_task (or simply never acks), the s...
Risk signalsAccepts URL/endpoint input (url)
Part of the Safebot server.
Free to start. No card required.
AI agents call claim_task to retrieve information from Safebot 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 claim_task 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": {
"claim_task": {}
}
}See the full Safebot policy for all 8 tools.
These attack patterns abuse exactly the kind of access claim_task 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.
Two-step at-least-once primitive — step 1. Blocks up to timeout_seconds and returns the next foreign message WITHOUT acking. Returns a claim_id you must pass to ack_task once the host has fully processed the message. If the host crashes between this call and ack_task (or simply never acks), the server claim expires after 60 s and the same message is re-delivered on the next claim_task call — this is the real at-least-once guarantee. Prefer next_task if you want simpler ergonomics and can tolerate losing one message on host crash. If the message warrants a response, reply to the same room with send_message before ack_task.. It is categorised as a Read tool in the Safebot MCP Server, which means it retrieves data without modifying state.
Register the Safebot MCP server in PolicyLayer and add a rule for claim_task: 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 Safebot. Nothing to install.
claim_task 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 claim_task 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 claim_task. 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.
claim_task is provided by the Safebot MCP server (safebot-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 8 Safebot 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.