AI agents call bbs_load_prompts_json to retrieve information from Mcp Bbs without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool reads/loads prompt patterns from a JSON file into memory. 'Reload' implies reading configuration data, not modifying external systems. No side effects on external data are described. Severity is low as it only affects the local configuration state of the MCP server.
From the tool's definition Reload prompt patterns from JSON file
Attacks that exploit this kind of access
Reload prompt patterns from JSON file. It is categorised as a Read tool in the Mcp Bbs MCP Server, which means it retrieves data without modifying state.
Register the Mcp Bbs MCP server in PolicyLayer and add a rule for bbs_load_prompts_json: 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 Mcp Bbs. Nothing to install.
bbs_load_prompts_json 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 bbs_load_prompts_json 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_load_prompts_json. 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_load_prompts_json is provided by the Mcp Bbs MCP server (livingstaccato/mcp-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 →