Walk a directory and classify every project inside it by framework (flutter | expo | react-native | next | vite | unity | iosNative | androidNative | swift-package | gradle-jvm). Returns a Monorepo JSON: { root, gitBranch, gitRemote, projects[], frameworks[], isMonorepo, hasManifest }. Use this B...
AI agents call monorepo_detect to retrieve information from Yaver without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
dir | string | — | Directory to classify (absolute path or relative to agent cwd). Defaults to cwd. |
max_depth | integer | — | Maximum recursion depth (1–12). Default 6. |
Parameters from the server's own tool schema.
Even though monorepo_detect only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Risk signalsAccepts file system path (dir) · Bulk/mass operation — affects multiple targets · Admin/system-level operation
Attacks that exploit this kind of access
Walk a directory and classify every project inside it by framework (flutter | expo | react-native | next | vite | unity | iosNative | androidNative | swift-package | gradle-jvm). Returns a Monorepo JSON: { root, gitBranch, gitRemote, projects[], frameworks[], isMonorepo, hasManifest }. Use this BEFORE calling native_build to confirm which frameworks are present and pick the right --target. Skips node_modules, build, .git, vendor, .pub-cache, .next, .turbo, etc. dir defaults to the agent's current work directory when omitted. It is categorised as a Read tool in the Yaver MCP Server, which means it retrieves data without modifying state.
monorepo_detect accepts 2 parameters: dir, max_depth. The full parameter table on this page comes from the server's own tool schema.
Register the Yaver MCP server in PolicyLayer and add a rule for monorepo_detect: 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 Yaver. Nothing to install.
monorepo_detect 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 monorepo_detect 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 monorepo_detect. 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.
monorepo_detect is provided by the Yaver MCP server (yaver-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.