Find dependencies of a file. Args: project: Project name file_path: Path to the file Returns: Dictionary of imports/includes
AI agents call get_dependencies to retrieve information from Tree Sitter without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs static analysis to discover and return dependency information from a file. This is a read-only operation with no side effects—it retrieves data without creating, modifying, deleting, or executing anything. The arguments (project name and file path) are identifiers for lookup only, not code to execute.
From the tool's definition Tool description states it 'Find dependencies of a file' and 'Returns: Dictionary of imports/includes'. These are query operations that retrieve existing code metadata without modification or execution.
Documented attack patterns abuse exactly the kind of access get_dependencies gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Tree Sitter, and nothing reaches the server without passing your rules. This is the rule we recommend for get_dependencies:
{
"version": "1",
"default": "deny",
"tools": {
"get_dependencies": {}
}
}get_dependencies is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Find dependencies of a file. Args: project: Project name file_path: Path to the file Returns: Dictionary of imports/includes. It is categorised as a Read tool in the Tree Sitter MCP Server, which means it retrieves data without modifying state.
Register the Tree Sitter MCP server in PolicyLayer and add a rule for get_dependencies: 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 Tree Sitter. Nothing to install.
get_dependencies 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 get_dependencies 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 get_dependencies. 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.
get_dependencies is provided by the Tree Sitter MCP server (wrale/mcp-server-tree-sitter). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 26 Tree Sitter tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
26 Tree Sitter tools catalogued and risk-classified — across an index of 42,500+ MCP servers.