AI agents use extract_attachments to create or update resources in Tbird — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tbird environment.
This tool writes files to the local filesystem (saves attachments to a destination directory). It creates new files on disk, which is a reversible Write operation. It does not delete data, execute code, or involve financial transactions. Misuse could write unwanted or malicious files to arbitrary directories if dest_dir is attacker-controlled.
From the tool's definition Save a message's attachments to ``dest_dir``; returns the written file paths.
Attacks that exploit this kind of access
Save a message's attachments to dest_dir; returns the written file paths. It is categorised as a Write tool in the Tbird MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Tbird MCP server in PolicyLayer and add a rule for extract_attachments: 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 Tbird. Nothing to install.
extract_attachments 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 extract_attachments 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 extract_attachments. 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.
extract_attachments is provided by the Tbird MCP server (neil-zielsdorf/tbird-mcp). 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 →