Create new knowledge graph with title and optional description
AI agents use create_graph to create or update resources in Mnemosyne MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mnemosyne MCP environment.
This tool creates new knowledge graphs, which is a reversible data creation operation (Write category). Severity is medium because creating knowledge graphs could consume resources, potentially duplicate or corrupt existing structures if misused by an agent without proper validation, but the action itself is reversible.
From the tool's definition Tool name 'create_graph' and description 'Create new knowledge graph' explicitly indicate creation of new data structures. The server description confirms it manages 'knowledge graphs' and supports 'graph operations'.
Attacks that exploit this kind of access
Create new knowledge graph with title and optional description. It is categorised as a Write tool in the Mnemosyne MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mnemosyne MCP server in PolicyLayer and add a rule for create_graph: 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.
create_graph is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_graph 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 create_graph. 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.
create_graph 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 →