list_wire_predicates
AI agents call list_wire_predicates to retrieve information from Mnemosyne MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The verb 'list' is a canonical Read operation—it retrieves or queries data without side effects. In the context of a knowledge graph/SPARQL tool, 'wire_predicates' refers to RDF predicates (properties/relationships), and listing them is intrinsically a query. Empty descriptions reduce confidence slightly, but the naming convention is unambiguous.
From the tool's definition Tool name 'list_wire_predicates' suggests a listing/retrieval operation. The description is empty, but 'list' verb and 'predicates' context indicate querying or enumerating RDF predicates in the graph rather than modifying state.
Attacks that exploit this kind of access
list_wire_predicates. It is categorised as a Read tool in the Mnemosyne MCP MCP Server, which means it retrieves data without modifying state.
Register the Mnemosyne MCP server in PolicyLayer and add a rule for list_wire_predicates: 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 Mnemosyne MCP. Nothing to install.
list_wire_predicates 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_wire_predicates 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_wire_predicates. 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_wire_predicates is provided by the Mnemosyne MCP server (sophia-labs/mnemosyne-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 →