AI agents call list_links 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 metadata about document relationships (wiki link references) without side effects. It queries existing data structure and returns link information. No data is created, modified, deleted, or executed. Classified as Read per definition: 'retrieves or queries data; no side effects (search, list, get, fetch).' The 'list' operation is a direct match for Read category.
From the tool's definition Tool lists outgoing wiki links from a document and their resolution status; performs no modification, deletion, or execution. Description explicitly uses 'List' verb indicating retrieval operation.
Attacks that exploit this kind of access
List the outgoing [[wiki links]] from a document, with their resolution status. 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 list_links: 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.
list_links 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 list_links 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 list_links. 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.
list_links 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 →