index_conversations · Claude Code History MCP: Risk & Policy

WHAT IT DOES

What index_conversations does on Claude Code History MCP

AI agents use index_conversations to create or update resources in Claude Code History MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude Code History MCP environment.

WHY IT NEEDS A POLICY

Why index_conversations needs a policy

This tool creates or modifies index data structures for conversations. While indexing itself is technically a preparatory operation, it involves writing indexed metadata and potentially storing summaries. It is reversible (indices can be rebuilt or cleared), so it qualifies as Write rather than Destructive. There are no irreversible deletions, financial transactions, or code execution involved.

From the tool's definition The tool is named 'index_conversations' with a description stating it will 'Index conversations with AI summarization (if API key is set)'.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

index_conversations Rate-limited

index_conversations stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "index_conversations": {
      "limits": [
        {
          "counter": "index_conversations_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Claude Code History MCP, so you can run agents against it safely.

FAQ

Questions about index_conversations

What does the index_conversations tool do? +

Index conversations with AI summarization (if API key is set). It is categorised as a Write tool in the Claude Code History MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on index_conversations? +

Register the Claude Code History MCP server in PolicyLayer and add a rule for index_conversations: 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 Claude Code History MCP. Nothing to install.

What risk level is index_conversations? +

index_conversations is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit index_conversations? +

Yes. Add a rate_limit block to the index_conversations 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.

How do I block index_conversations completely? +

Set action: deny in the PolicyLayer policy for index_conversations. 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.

What MCP server provides index_conversations? +

index_conversations is provided by the Claude Code History MCP server (tim0120/claude-code-history-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.