Write a durable memory entry with provenance to the backing store.
AI agents use write_project_memory to create or update resources in MEMGRAPH-MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MEMGRAPH-MCP environment.
This tool creates or modifies memory entries in a backing store (SQLite-backed per server description). It has reversible effects—entries can be updated or managed—making it a Write operation.
From the tool's definition Tool description explicitly states 'Write a durable memory entry with provenance to the backing store.' The verb 'write' and terminology 'durable memory entry' indicate data creation/modification in a persistent store.
Attacks that exploit this kind of access
Write a durable memory entry with provenance to the backing store. It is categorised as a Write tool in the MEMGRAPH-MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MEMGRAPH- MCP server in PolicyLayer and add a rule for write_project_memory: 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 MEMGRAPH-MCP. Nothing to install.
write_project_memory 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 write_project_memory 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 write_project_memory. 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.
write_project_memory is provided by the MEMGRAPH- MCP server (mikeb317/memgraph-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 →