Get a token-budgeted structural summary of entities impacted by code changes. Returns compact Rails-aware descriptions of each impacted model, controller, and component — enough context for an AI agent to review the change safely. Call get_blast_radius first, or provide files directly.
AI agents call get_review_context to retrieve information from Rails Insight without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
get_review_context is a read-only querying tool that provides structural analysis of code changes to support safe review. It has no capability to modify data, execute code, delete resources, or trigger external operations. The token-budgeted response indicates it is purely informational. Even if misused, an AI agent cannot cause harm by reading structural summaries of Rails components.
From the tool's definition Tool retrieves and returns a 'structural summary' of entities with 'compact Rails-aware descriptions' — it queries and retrieves information without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
Get a token-budgeted structural summary of entities impacted by code changes. Returns compact Rails-aware descriptions of each impacted model, controller, and component — enough context for an AI agent to review the change safely. Call get_blast_radius first, or provide files directly. It is categorised as a Read tool in the Rails Insight MCP Server, which means it retrieves data without modifying state.
Register the Rails Insight MCP server in PolicyLayer and add a rule for get_review_context: 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 Rails Insight. Nothing to install.
get_review_context 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_review_context 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_review_context. 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_review_context is provided by the Rails Insight MCP server (@reinteractive/rails-insight). 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 →