AI agents use fork_branch to create or update resources in Tages — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tages environment.
The tool creates a new branch/fork of existing memories for experimentation purposes. This is a reversible write operation — it duplicates memory state into a new session branch rather than modifying or deleting the originals. Severity is medium because misuse could create many spurious branches or cause confusion in memory state, but it does not appear to irreversibly destroy data.
From the tool's definition Fork current memories into a session branch for experimentation. Branch writes won\ (description appears truncated)
Attacks that exploit this kind of access
Fork current memories into a session branch for experimentation. Branch writes won\. It is categorised as a Write tool in the Tages MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Tages MCP server in PolicyLayer and add a rule for fork_branch: 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 Tages. Nothing to install.
fork_branch 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 fork_branch 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 fork_branch. 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.
fork_branch is provided by the Tages MCP server (ryantlee25-droid/tages). 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 →