AI agents use add_artifact to create or update resources in Todos — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Todos environment.
This tool creates or modifies task metadata by attaching file artifacts. It is Write-category because it adds/updates reversible data structures (artifact attachments) without executing code or deleting data. Severity is medium because attachment operations could pollute task records or attach sensitive files if misused by an agent, but the damage is reversible and scoped to metadata/references.
From the tool's definition Tool description states 'Attach a local file as artifact' — the verb 'attach' indicates modification of a task/project/plan/run entity by adding new file metadata/references.
Attacks that exploit this kind of access
Attach a local file as an artifact for a task, project, plan, run, verification, or handoff. Files stay local-only unless explicitly exported. It is categorised as a Write tool in the Todos MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Todos MCP server in PolicyLayer and add a rule for add_artifact: 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 Todos. Nothing to install.
add_artifact 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 add_artifact 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 add_artifact. 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.
add_artifact is provided by the Todos MCP server (@hasna/todos). 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 →