Get all mentionable entities (users, pages, folders) in a workspace for @-mention autocomplete. Includes member counts, workspace structure overview, and owner info. Useful for understanding workspace scope at a glance.
AI agents call get_mention_entities to retrieve information from Fusebase MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool exclusively queries and returns data about workspace structure and users without any side effects. It performs discovery/introspection of workspace metadata to populate autocomplete suggestions. No data is created, modified, deleted, or executed—it is purely informational retrieval.
From the tool's definition Tool retrieves mentionable entities, member counts, workspace structure overview, and owner info—all read-only queries with no modification, deletion, or execution of commands. Description uses 'Get' verb indicating retrieval.
Attacks that exploit this kind of access
Get all mentionable entities (users, pages, folders) in a workspace for @-mention autocomplete. Includes member counts, workspace structure overview, and owner info. Useful for understanding workspace scope at a glance. It is categorised as a Read tool in the Fusebase MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Fusebase MCP Server MCP server in PolicyLayer and add a rule for get_mention_entities: 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 Fusebase MCP Server. Nothing to install.
get_mention_entities 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_mention_entities 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_mention_entities. 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_mention_entities is provided by the Fusebase MCP Server MCP server (ryan-haver/fusebase-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 →