AI agents use coordination_init 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 initializes a coordination session, which involves creating/writing session state and role assignments. It's not purely read-only since it 'sets up' a role and project state. It's not destructive or financial. The blast radius is medium since misuse could disrupt multi-agent coordination sessions, but data loss is unlikely.
From the tool's definition Initialize coordination session... set up your role (planner or implementer)
Attacks that exploit this kind of access
Initialize coordination session. Call this first to set up your role (planner or implementer). Returns guidance based on your role and current project state. 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 coordination_init: 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.
coordination_init 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 coordination_init 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 coordination_init. 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.
coordination_init 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 →