index_sync · Claude Code History MCP: Risk & Policy

WHAT IT DOES

What index_sync does on Claude Code History MCP

AI agents use index_sync 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_sync needs a policy

This tool indexes/ingests conversation data into a searchable store, creating or modifying index entries. It is a Write operation as it populates metadata and indexes but does not delete existing data or execute arbitrary code. The blast radius is medium since it modifies the local index/database with potentially sensitive conversation history and metadata.

From the tool's definition Index conversations from claude-sync repository with rich metadata (git, machine, tokens)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

index_sync Rate-limited

index_sync 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_sync": {
      "limits": [
        {
          "counter": "index_sync_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_sync

What does the index_sync tool do? +

Index conversations from claude-sync repository with rich metadata (git, machine, tokens). 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_sync? +

Register the Claude Code History MCP server in PolicyLayer and add a rule for index_sync: 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_sync? +

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

Can I rate-limit index_sync? +

Yes. Add a rate_limit block to the index_sync 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_sync completely? +

Set action: deny in the PolicyLayer policy for index_sync. 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_sync? +

index_sync 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.