refresh_index

THE RISK

High Risk

Why refresh_index needs a policy

This tool executes an indexing operation that scans and rebuilds the project file index. It is not a simple read (it modifies internal state) nor purely destructive (it rebuilds rather than deletes permanently). It falls under Execute because it triggers an external/internal operation (index rebuild) whose effects depend on the current state of the repository.

From the tool's definition 'Manually rebuild the project file index' and 'Use after git operations or when index seems stale' — triggers an active rebuild/reindex operation

Documented attack patterns abuse exactly the kind of access refresh_index gives an agent:

POLICY

How to control refresh_index

PolicyLayer is an MCP gateway — it sits between your AI agents and Code Index, and nothing reaches the server without passing your rules. This is the rule we recommend for refresh_index:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "refresh_index": {
      "limits": [
        {
          "counter": "refresh_index_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

refresh_index stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register Code Index — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Code Index tools

Destructive clear_settings Clear all settings and cached data. Execute build_deep_index Build the deep index (full symbol extraction) for the current project. This performs Execute refresh_search_tools Manually re-detect the available command-line search tools on the system. This is usef Write configure_file_watcher configure_file_watcher Write create_temp_directory Create the temporary directory used for storing index data. Write set_project_path Set the base project path for indexing. Read check_temp_directory Check the temporary directory used for storing index data. Read find_files Find files matching glob pattern using in-memory index. Supports path patterns (.py, test_

All 14 Code Index tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Code Index → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about refresh_index

What does the refresh_index tool do? +

Manually rebuild the project file index. Use after git operations or when index seems stale. It is categorised as a Execute tool in the Code Index MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on refresh_index? +

Register the Code Index MCP server in PolicyLayer and add a rule for refresh_index: 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 Code Index. Nothing to install.

What risk level is refresh_index? +

refresh_index is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit refresh_index? +

Yes. Add a rate_limit block to the refresh_index 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 refresh_index completely? +

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

refresh_index is provided by the Code Index MCP server (johnhuang316/code-index-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Code Index tool call.

Start from Code Index, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →