Set a Redis key with an explicit write guard and optional TTL.
AI agents use set-key to create or update resources in Universal Mcp Toolkit — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Universal Mcp Toolkit environment.
The tool modifies data in Redis by setting key-value pairs, which is a reversible write operation. While it includes a write guard (suggesting some safety), it can still modify or overwrite existing data. The optional TTL parameter allows expiration management but doesn't change the fundamental write nature.
From the tool's definition Tool description states 'Set a Redis key' which is a write operation. The mention of 'explicit write guard' indicates this is a controlled data modification operation.
Attacks that exploit this kind of access
Set a Redis key with an explicit write guard and optional TTL. It is categorised as a Write tool in the Universal Mcp Toolkit MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Universal Mcp Toolkit MCP server in PolicyLayer and add a rule for set-key: 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 Mcp Toolkit. Nothing to install.
set-key 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-key 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-key. 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-key is provided by the Universal Mcp Toolkit MCP server (markgatcha/universal-mcp-toolkit). 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 →