AI agents use oboe_complete_session 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.
This tool updates the status of a session object to 'completed', which is a write operation that changes session state. It is not destructive (the session is not deleted), not financial, and not execute (no arbitrary code/command execution).
From the tool's definition Tool description states it 'Mark[s] a session completed' — a state change operation that modifies the session record. The verb 'mark' and context of 'completed' indicate a reversible update rather than deletion or destruction.
Attacks that exploit this kind of access
Mark a session completed when no actionable items remain. 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_complete_session: 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_complete_session 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_complete_session 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_complete_session. 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_complete_session 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 →