AI agents use artifact_write 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 creates or modifies artifact files within the lockstep coordination system. While reversible (artifacts can be overwritten or deleted), it modifies shared project state that other agents depend on. In a multi-agent environment, careless writes could corrupt collaborative work or introduce malicious content into shared artifacts.
From the tool's definition Tool name 'artifact_write' and description 'Write an artifact file' explicitly indicate creation or modification of data.
Attacks that exploit this kind of access
Write an artifact file. 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 artifact_write: 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.
artifact_write 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 artifact_write 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 artifact_write. 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.
artifact_write 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 →