Performs a deep scan of the project structure and key files to populate semantic memory.
AI agents call index_codebase to retrieve information from OpenCode MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes project structure and file contents to build an internal semantic model. There are no side effects, code execution, data modification, or destructive operations. It is a read-only indexing operation similar to 'scan' or 'fetch', which are characteristic of the Read category.
From the tool's definition Tool description states it 'Performs a deep scan of the project structure and key files' with the purpose of populating semantic memory for context enrichment. The action is scanning/reading, not modifying or executing external operations.
Documented attack patterns abuse exactly the kind of access index_codebase gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OpenCode MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for index_codebase:
{
"version": "1",
"default": "deny",
"tools": {
"index_codebase": {}
}
}index_codebase is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Performs a deep scan of the project structure and key files to populate semantic memory. It is categorised as a Read tool in the OpenCode MCP Server MCP Server, which means it retrieves data without modifying state.
Register the OpenCode MCP Server MCP server in PolicyLayer and add a rule for index_codebase: 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 OpenCode MCP Server. Nothing to install.
index_codebase is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the index_codebase 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 index_codebase. 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.
index_codebase is provided by the OpenCode MCP Server MCP server (marlondivino/open-code-as-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from OpenCode MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 OpenCode MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.