AI agents call arch_context to retrieve information from Paparats without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to retrieve or query architectural context data from the local codebase search system. Given the server's stated purpose (semantic code search for AI assistants) and the absence of mutation language in the name, this is most likely a read-only operation.
From the tool's definition Tool name 'arch_context' in a semantic code search server suggests retrieval of architectural context information.
Attacks that exploit this kind of access
arch_context. It is categorised as a Read tool in the Paparats MCP Server, which means it retrieves data without modifying state.
Register the Paparats MCP server in PolicyLayer and add a rule for arch_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 Paparats. Nothing to install.
arch_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 arch_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 arch_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.
arch_context is provided by the Paparats MCP server (@paparats/cli). 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 →