AI agents use mcp_import_claude_config to create or update resources in LocalAnt — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your LocalAnt environment.
This tool creates or modifies MCP server registrations in the local system (even though imported servers are disabled by default). It is a reversible Write operation that changes application configuration.
From the tool's definition Tool description states 'Import MCP servers from Claude Code config' — it reads configuration files and imports server definitions, modifying the local MCP configuration state. The phrase 'Imported servers start disabled' confirms state changes occur.
Attacks that exploit this kind of access
Import MCP servers from Claude Code config (.mcp.json / ~/.claude.json). Imported servers start disabled. It is categorised as a Write tool in the LocalAnt MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the LocalAnt MCP server in PolicyLayer and add a rule for mcp_import_claude_config: 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 LocalAnt. Nothing to install.
mcp_import_claude_config 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 mcp_import_claude_config 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 mcp_import_claude_config. 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.
mcp_import_claude_config is provided by the LocalAnt MCP server (yuga-hashimoto/localant). 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 →