Set or clear the session's default graph.
AI agents use set_home_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 modifies session configuration by setting or clearing a default graph reference, which is a reversible operation. It changes state but does not execute arbitrary code, delete data irreversibly, or create financial obligations. The 'clear' operation could affect subsequent queries if users forget they cleared the default, but the action itself is reversible (re-set the graph).
From the tool's definition Tool description states 'Set or clear the session's default graph,' indicating modification of session state and graph configuration without deletion of underlying data.
Attacks that exploit this kind of access
Set or clear the session's default graph. 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 set_home_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.
set_home_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 set_home_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 set_home_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.
set_home_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 →