AI agents call tb_unblocked to retrieve information from Forgespec without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves status information about tasks in a task board management system. It performs a read-only query to identify which tasks have their dependencies satisfied and are available for work. There is no creation, modification, deletion, or execution of external operations—only data retrieval. This is a classic Read operation with minimal risk.
From the tool's definition Tool name 'tb_unblocked' and description 'List all tasks that are ready to be worked on (no unresolved dependencies)' indicates a query/retrieval operation with no data modification or side effects.
Attacks that exploit this kind of access
List all tasks that are ready to be worked on (no unresolved dependencies). It is categorised as a Read tool in the Forgespec MCP Server, which means it retrieves data without modifying state.
Register the Forgespec MCP server in PolicyLayer and add a rule for tb_unblocked: 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.
tb_unblocked is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the tb_unblocked 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 tb_unblocked. 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.
tb_unblocked 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 →