AI agents use discussion_archive to create or update resources in Lockstep — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Lockstep environment.
This tool modifies data (changes discussion status to archived) but the change is reversible and non-destructive. While the description mentions 'Archived discussions can be deleted later,' this refers to a future potential action, not an action this tool performs. The immediate effect is a metadata/state modification of a discussion record, classifying it as Write rather than Destructive.
From the tool's definition Tool description states it 'Archive[s] a resolved discussion.' Archiving is a state-change operation that modifies the status of a discussion record from active to archived, which is reversible (discussions can be unarchived in typical systems).
Attacks that exploit this kind of access
Archive a resolved discussion. Archived discussions can be deleted later. It is categorised as a Write tool in the Lockstep MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Lockstep MCP server in PolicyLayer and add a rule for discussion_archive: 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 Lockstep. Nothing to install.
discussion_archive 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 discussion_archive 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 discussion_archive. 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.
discussion_archive is provided by the Lockstep MCP server (tmmoore286/lockstep-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 →