AI agents call get_document to retrieve information from Ai Brain without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns document content without altering, deleting, or executing anything. It has no destructive, financial, or code-execution implications. The blast radius of misuse is minimal — an agent could read documents it shouldn't have access to, but the knowledge base's access controls should gate this risk. Classified as Read with low severity.
From the tool's definition Tool description explicitly states 'Fetch a single document' with 'full Markdown content' — a retrieval operation with no modification or side effects. The action is purely informational querying of stored data.
Attacks that exploit this kind of access
Fetch a single document (including its full Markdown content) by id. It is categorised as a Read tool in the Ai Brain MCP Server, which means it retrieves data without modifying state.
Register the Ai Brain MCP server in PolicyLayer and add a rule for get_document: 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 Brain. Nothing to install.
get_document 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 get_document 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 get_document. 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.
get_document is provided by the Ai Brain MCP server (thejoshgriffith/ai-brain). 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 →