AI agents call detect_version to retrieve information from Ogrid without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
path | string | — | Directory to search from (defaults to current working directory). The tool walks up the directory tree to find the nearest package.json with OGrid dependencies. |
Parameters from the server's own tool schema.
This tool performs a read-only operation that queries project metadata from package.json to determine installed versions. It has no capacity to modify, delete, or execute code. The blast radius of misuse is minimal—an AI agent could at worst retrieve version information it shouldn't see, but cannot alter system state or trigger external operations. This is a straightforward Read category tool.
From the tool's definition Tool description states it reads package.json to 'detect' version information. The verb 'reading' and the data source (package.json) indicate information retrieval with no modification or side effects.
Risk signalsAccepts file system path (path)
Attacks that exploit this kind of access
Detect which OGrid version and framework is installed in the user's project by reading their package.json. It is categorised as a Read tool in the Ogrid MCP Server, which means it retrieves data without modifying state.
detect_version accepts 1 parameter: path. The full parameter table on this page comes from the server's own tool schema.
Register the Ogrid MCP server in PolicyLayer and add a rule for detect_version: 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 Ogrid. Nothing to install.
detect_version 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 detect_version 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 detect_version. 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.
detect_version is provided by the Ogrid MCP server (@alaarab/ogrid-mcp). 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 →