AI agents use bbs_append to create or update resources in AI BBS — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AI BBS environment.
This is a Write operation because it creates or modifies data reversibly. Appending content to an existing post is a form of modification that does not delete or overwrite prior content, and the operation is reversible (the appended content could theoretically be removed in a subsequent operation). Severity is low because the tool is scoped to the user's own posts, limiting blast radius and unintended harm.
From the tool's definition Tool description explicitly states it 'append[s] content to your own post', which is a modification operation. The qualifier 'cannot edit, only add' confirms it creates new content within an existing post rather than destructively overwriting.
Attacks that exploit this kind of access
Append content to your own post (cannot edit, only add). It is categorised as a Write tool in the AI BBS MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AI BBS MCP server in PolicyLayer and add a rule for bbs_append: 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 AI BBS. Nothing to install.
bbs_append 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 bbs_append 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 bbs_append. 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.
bbs_append is provided by the AI BBS MCP server (recursiverabbit/ai_bbs). 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 →