Poll the Fusebase activity stream for new @mentions or comments directed at this profile. Use filterText to narrow results to only items mentioning a specific display name.
AI agents call fusebase_poll_mentions 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 retrieves/queries existing mention and comment data from an activity stream. There are no creation, modification, deletion, or execution side effects. It is purely observational in nature, similar to fetching notifications or browsing a feed. The low severity reflects minimal blast radius if misused - an agent could only retrieve data about mentions already directed at the user.
From the tool's definition Tool description states 'Poll the Fusebase activity stream for new @mentions or comments directed at this profile' - polling and retrieving activity stream data is a read operation with no side effects.
Attacks that exploit this kind of access
Poll the Fusebase activity stream for new @mentions or comments directed at this profile. Use filterText to narrow results to only items mentioning a specific display name. 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 fusebase_poll_mentions: 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.
fusebase_poll_mentions 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 fusebase_poll_mentions 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 fusebase_poll_mentions. 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.
fusebase_poll_mentions 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 →