AI agents use sync_kg 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.
The tool writes/upserts relationship data into a knowledge graph edges table. It is idempotent (safe to retry), meaning it doesn't destructively overwrite in a harmful way, but it does modify/create records in a database table. This classifies as Write. Severity is medium because syncing the entire knowledge graph could corrupt or overwrite edge data if misused, but the idempotent nature limits blast radius.
From the tool's definition 'Sync all existing relationships into the knowledge graph edges table. Idempotent.'
Attacks that exploit this kind of access
Sync all existing relationships into the knowledge graph edges table. 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 sync_kg: 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.
sync_kg 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 sync_kg 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 sync_kg. 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.
sync_kg 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 →