Write external code index artifacts consumed by the code graph. Prefers SCIP when scip-typescript and scip are installed, then falls back to the built-in LSP-compatible symbol index.
AI agents use kage_code_index to create or update resources in Kage — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Kage environment.
This tool creates or modifies code index artifacts (SCIP or LSP-compatible symbol indices) that feed into the code graph system. While the write is reversible (indices can be regenerated or deleted), the artifacts influence code analysis and understanding across the team, so misuse could corrupt shared understanding or inject false symbol information.
From the tool's definition "Write external code index artifacts consumed by the code graph" — the tool explicitly creates/writes index artifacts that are consumed by other systems.
Documented attack patterns abuse exactly the kind of access kage_code_index gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Kage, and nothing reaches the server without passing your rules. This is the rule we recommend for kage_code_index:
{
"version": "1",
"default": "deny",
"tools": {
"kage_code_index": {
"limits": [
{
"counter": "kage_code_index_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}kage_code_index 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.
Free to start. No card required.
Write external code index artifacts consumed by the code graph. Prefers SCIP when scip-typescript and scip are installed, then falls back to the built-in LSP-compatible symbol index. It is categorised as a Write tool in the Kage MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Kage MCP server in PolicyLayer and add a rule for kage_code_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 Kage. Nothing to install.
kage_code_index 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 kage_code_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.
Set action: deny in the PolicyLayer policy for kage_code_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.
kage_code_index is provided by the Kage MCP server (@kage-core/kage-graph-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Kage, 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.
62 Kage tools catalogued and risk-classified — across an index of 43,000+ MCP servers.