AI agents use index_project to create or update resources in MCP Code Indexer — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Code Indexer environment.
This tool creates a vector index of a code repository, which is a write operation that generates and stores new data (the index). It does not delete or overwrite existing source code, making it reversible and non-destructive. Misuse could cause excessive resource consumption or index corruption, giving it medium severity.
From the tool's definition 索引代码项目，生成向量索引 (Index code project, generate vector index)
Documented attack patterns abuse exactly the kind of access index_project gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Code Indexer, and nothing reaches the server without passing your rules. This is the rule we recommend for index_project:
{
"version": "1",
"default": "deny",
"tools": {
"index_project": {
"limits": [
{
"counter": "index_project_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}index_project 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.
索引代码项目，生成向量索引. It is categorised as a Write tool in the MCP Code Indexer MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Code Indexer MCP server in PolicyLayer and add a rule for index_project: 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 MCP Code Indexer. Nothing to install.
index_project 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 index_project 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_project. 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_project is provided by the MCP Code Indexer MCP server (zxfgds/mcp-code-indexer). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 8 MCP Code Indexer tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
8 MCP Code Indexer tools catalogued and risk-classified — across an index of 42,500+ MCP servers.