AI agents use index_repo_tool to create or update resources in Orihime — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Orihime environment.
The tool name strongly implies it indexes a repository, which based on the server description means parsing source code and writing data into an embedded KuzuDB knowledge graph. This is a Write operation as it creates/populates data in the database. Severity is high because it operates on potentially large codebases and could overwrite existing index data.
From the tool's definition Tool name 'index_repo_tool' and server description: 'Indexes source code into embedded KuzuDB via tree-sitter'
Attacks that exploit this kind of access
index_repo_tool. It is categorised as a Write tool in the Orihime MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Orihime MCP server in PolicyLayer and add a rule for index_repo_tool: 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 Orihime. Nothing to install.
index_repo_tool 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_repo_tool 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_repo_tool. 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_repo_tool is provided by the Orihime MCP server (srinivasan-sundaresan95/orihime). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →