AI agents use oboe_merge_items to create or update resources in Obo — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Obo environment.
The tool creates or appends data to an existing session structure. While appending is reversible (items can be removed or sessions recreated), it modifies the session state. It does not retrieve data (Read), execute arbitrary code (Execute), permanently delete data (Destructive), or handle money (Financial). This is a classic Write operation.
From the tool's definition Tool description states 'Append new items to an existing session' — this modifies session data by adding new items, which is a reversible write operation.
Attacks that exploit this kind of access
Append new items to an existing session. It is categorised as a Write tool in the Obo MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Obo MCP server in PolicyLayer and add a rule for oboe_merge_items: 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 Obo. Nothing to install.
oboe_merge_items 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 oboe_merge_items 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 oboe_merge_items. 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.
oboe_merge_items is provided by the Obo MCP server (warnes-innovations/oboe-mcp). 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 →