Project memory save (user_id based)
AI agents use project_memory_set to create or update resources in Universal Dev MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Universal Dev MCP environment.
This tool creates or modifies stored project memory data associated with a user. While it doesn't delete data (Destructive) or move money (Financial), it does persistently write/save user-specific information. The reversible nature of a memory/configuration save operation places it in Write rather than Execute.
From the tool's definition Tool name 'project_memory_set' indicates a set/save operation that writes data. Description states 'Project memory save' which is a create/modify action that stores user-specific data (indicated by 'user_id based').
Attacks that exploit this kind of access
Project memory save (user_id based). It is categorised as a Write tool in the Universal Dev MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Universal Dev MCP server in PolicyLayer and add a rule for project_memory_set: 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 Universal Dev MCP. Nothing to install.
project_memory_set 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 project_memory_set 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 project_memory_set. 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.
project_memory_set is provided by the Universal Dev MCP server (kallusuvaidyam/universal_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 →