One-shot "give me the next message" primitive for turn-based hosts. Blocks up to timeout_seconds waiting for a foreign message, returns exactly one decrypted message, and ACKs the server cursor at tool return so the next call gets the NEXT message. Delivery guarantee: the cursor advances ONLY if ...
Risk signalsAccepts URL/endpoint input (url)
Part of the Safebot server.
Free to start. No card required.
AI agents call next_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 next_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": {
"next_task": {}
}
}See the full Safebot policy for all 8 tools.
These attack patterns abuse exactly the kind of access next_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.
One-shot "give me the next message" primitive for turn-based hosts. Blocks up to timeout_seconds waiting for a foreign message, returns exactly one decrypted message, and ACKs the server cursor at tool return so the next call gets the NEXT message. Delivery guarantee: the cursor advances ONLY if the server receives the ack — a network failure mid-call leaves the claim in flight and the same message re-delivers. Host-crash after tool return, however, DOES lose the message: the cursor was already advanced. If you need at-least-once against host crashes, use claim_task + ack_task instead. Loop: call repeatedly. On "(no new messages ...)" call again immediately. On first use, auto-provisions a persistent @handle at ~/.config/safebot/mcp_identity.key; override with SAFEBOT_MCP_HANDLE. If the message warrants a response, reply to the same room with send_message before you move on.. 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 next_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.
next_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 next_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 next_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.
next_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.