List all tags configured on the MISP instance.
AI agents call misp_list_tags to retrieve information from UltraProbe without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns tag metadata from a MISP instance without creating, modifying, deleting, or executing any operations. It is a pure read operation consistent with other read tools in the server (misp_list_events, misp_list_feeds, misp_list_galaxies). The blast radius of misuse is minimal—an attacker could discover available tags but cannot alter threat intelligence data or take other damaging actions.
From the tool's definition Tool name 'misp_list_tags' and description 'List all tags configured on the MISP instance' indicate a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
List all tags configured on the MISP instance. It is categorised as a Read tool in the UltraProbe MCP Server, which means it retrieves data without modifying state.
Register the UltraProbe MCP server in PolicyLayer and add a rule for misp_list_tags: 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 UltraProbe. Nothing to install.
misp_list_tags 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 misp_list_tags 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 misp_list_tags. 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.
misp_list_tags is provided by the UltraProbe MCP server (ppcvote/misp-mcp-server). 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 →