AI agents use create_knowledge_snapshot 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 new project knowledge records by saving and attaching context snapshots. It is reversible (records can be modified or removed later) and has no destructive or code-execution characteristics. It falls into the Write category as it persistently creates or modifies task/project metadata.
From the tool's definition Tool performs 'Save' and 'attach' operations which create and modify data records. The description explicitly states 'Save a local context snapshot and attach it as a project knowledge record' — indicating creation of a new knowledge record (Write) rather…
Attacks that exploit this kind of access
Save a local context snapshot and attach it as a project knowledge record. 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 create_knowledge_snapshot: 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.
create_knowledge_snapshot 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 create_knowledge_snapshot 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 create_knowledge_snapshot. 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.
create_knowledge_snapshot 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 →