Record the outcome of a send attempt. Loads the draft at
AI agents use record_send_outcome to create or update resources in Slopweaver — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Slopweaver environment.
This tool creates or modifies a record of send outcomes, which is a reversible write operation. The incomplete description ('Loads the draft at') suggests it updates draft or outcome metadata. Severity is medium because recording outcomes can affect downstream workflows and decisions, but the operation itself is not irreversible or destructive.
From the tool's definition Tool name includes 'record' which modifies state; description states 'Record the outcome of a send attempt' indicating persistence of data about send operations.
Attacks that exploit this kind of access
Record the outcome of a send attempt. Loads the draft at. It is categorised as a Write tool in the Slopweaver MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Slopweaver MCP server in PolicyLayer and add a rule for record_send_outcome: 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 Slopweaver. Nothing to install.
record_send_outcome is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the record_send_outcome 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 record_send_outcome. 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.
record_send_outcome is provided by the Slopweaver MCP server (slopweaver/slopweaver). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →