AI agents use install_template_library to create or update resources in Todos — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Todos environment.
This tool creates or populates template records in a local database. While installation is generally reversible and idempotent, it modifies local state and could introduce unwanted templates or overwrite existing configurations if triggered unexpectedly by an agent. This makes it Write rather than Execute (no arbitrary code/commands) or Destructive (idempotent nature suggests reversibility).
From the tool's definition Tool description states 'Install all bundled templates into local database' - the verb 'install' combined with 'into local database' indicates data creation/modification.
Attacks that exploit this kind of access
Install all bundled templates into local database (idempotent). It is categorised as a Write tool in the Todos MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Todos MCP server in PolicyLayer and add a rule for install_template_library: 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 Todos. Nothing to install.
install_template_library 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 install_template_library 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 install_template_library. 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.
install_template_library is provided by the Todos MCP server (@hasna/todos). 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 →