Retrieve a specific engineering standard. Available standards: git, code_review, pr, staff_engineer, testing, rails, frontend, deployment, incident_response, observability, api_design, database_design, architecture_decisions, technical_debt, standup
AI agents call get_standard to retrieve information from Engineering Standards without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns engineering standards documentation based on a selection from a predefined list of standard types. It performs read-only retrieval of configuration or policy information with no capability to modify, execute code, or cause irreversible changes. The low severity reflects minimal blast radius—misuse would only return documentation to an AI agent, which cannot cause operational harm.
From the tool's definition Tool name 'get_standard' and description 'Retrieve a specific engineering standard' indicate a data retrieval operation with no side effects.
Attacks that exploit this kind of access
Retrieve a specific engineering standard. Available standards: git, code_review, pr, staff_engineer, testing, rails, frontend, deployment, incident_response, observability, api_design, database_design, architecture_decisions, technical_debt, standup. It is categorised as a Read tool in the Engineering Standards MCP Server, which means it retrieves data without modifying state.
Register the Engineering Standards MCP server in PolicyLayer and add a rule for get_standard: 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 Engineering Standards. Nothing to install.
get_standard 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 get_standard 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 get_standard. 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.
get_standard is provided by the Engineering Standards MCP server (rajgurung/claude-engineering-standards). 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 →