AI agents call oboe_get_session to retrieve information from Obo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to fetch or retrieve session information from the OBO (One-By-One) review system. No indication of data creation, modification, deletion, or external execution. The 'get_' prefix is characteristic of read operations. Low severity because retrieval has minimal blast radius unless the session data itself contains sensitive information that should not be exposed.
From the tool's definition Tool name 'oboe_get_session' and sibling tools like 'oboe_list_sessions' and 'oboe_get_item' indicate query/retrieval operations. The description is empty, which limits certainty.
Attacks that exploit this kind of access
oboe_get_session. It is categorised as a Read tool in the Obo MCP Server, which means it retrieves data without modifying state.
Register the Obo MCP server in PolicyLayer and add a rule for oboe_get_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_get_session is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the oboe_get_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_get_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_get_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 →