AI agents use file_reserve to create or update resources in Forgespec — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Forgespec environment.
The tool creates advisory locks/reservations on files, which is a reversible write operation (reservations expire after TTL). It modifies coordination state without reading, executing, or destroying data. Misuse could block other agents from accessing files, causing workflow disruption, hence medium severity.
From the tool's definition Reserve files or glob patterns to prevent conflicts between agents. Use check_only=true to check for conflicts without reserving. Reservations expire after TTL.
Attacks that exploit this kind of access
Reserve files or glob patterns to prevent conflicts between agents. Use check_only=true to check for conflicts without reserving. Reservations expire after TTL. It is categorised as a Write tool in the Forgespec MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Forgespec MCP server in PolicyLayer and add a rule for file_reserve: 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 Forgespec. Nothing to install.
file_reserve 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 file_reserve 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 file_reserve. 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.
file_reserve is provided by the Forgespec MCP server (lleontor705/forgespec-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 →