AI agents use import_claude_md to create or update resources in Tages — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tages environment.
This tool creates and stores new memory entries by parsing and ingesting structured data from a CLAUDE.md file. While reversible (memories can be modified or deleted via sibling tools like 'archive_memory'), it modifies the stored state of the AI agent's knowledge base. The tool does not execute code or trigger external operations—it only transforms file content into memory records.
From the tool's definition Tool description states it will 'auto-create memories from its sections' and 'become typed memories', indicating creation of data records in the persistent memory system.
Attacks that exploit this kind of access
Parse a CLAUDE.md file and auto-create memories from its sections. Conventions, architecture notes, decisions, and anti-patterns become typed memories. It is categorised as a Write tool in the Tages MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Tages MCP server in PolicyLayer and add a rule for import_claude_md: 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 Tages. Nothing to install.
import_claude_md is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the import_claude_md 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 import_claude_md. 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.
import_claude_md is provided by the Tages MCP server (ryantlee25-droid/tages). 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 →