AI agents use complete_session to create or update resources in Axiom-hub — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Axiom-hub environment.
Without an explicit description, classification relies on semantic analysis of the tool name and server context. 'Complete' suggests state transition or finalization of a session record—a write operation that modifies but does not delete data. The broader Axiom-hub architecture manages decision memory across sessions, so completing a session probably updates session metadata or status.
From the tool's definition Tool named 'complete_session' with empty description. Sibling tools like 'add_decision', 'add_constraint', and 'check_contradictions' indicate this server manages persistent state and decision memory.
Attacks that exploit this kind of access
complete_session. It is categorised as a Write tool in the Axiom-hub MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Axiom-hub MCP server in PolicyLayer and add a rule for 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 Axiom-hub. Nothing to install.
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 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 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.
complete_session is provided by the Axiom-hub MCP server (varunajaytawde28-design/smm-sync). 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 →