AI agents call sdd_validate 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 performs validation and schema checking, which are read-only operations that query and analyze data without side effects. It returns results but does not create, modify, delete, or execute external operations. The validation and confidence check are informational queries only.
From the tool's definition Tool description states it 'Validate[s] an SDD contract against the phase schema' and 'Returns validation result' — purely read and check operations with no data mutation, deletion, or code execution.
Attacks that exploit this kind of access
Validate an SDD contract against the phase schema. Returns validation result with confidence check and allowed transitions. 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 sdd_validate: 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.
sdd_validate 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 sdd_validate 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 sdd_validate. 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.
sdd_validate 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 →