Lists all files in a directory with their sizes. For JS/TS/TSX/JSX it parses imports/exports/functions and resolves local import edges to summarize dependency entanglement. Also extracts import/export-like declarations for common languages (Python/Java/Kotlin/Go/Rust/C#). Excludes common build di...
AI agents call explore_project to retrieve information from Project Explorer MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool only reads and analyzes the filesystem: listing files, parsing source code for imports/exports, and summarizing dependency relationships. No writes, executions, or deletions occur. The exclusion of build directories is a read-side filter. Severity is low as misuse only leaks project structure information.
From the tool's definition 'Lists all files in a directory with their sizes' and 'parses imports/exports/functions and resolves local import edges to summarize dependency entanglement' — purely analytical/read operations with no data modification
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Lists all files in a directory with their sizes. For JS/TS/TSX/JSX it parses imports/exports/functions and resolves local import edges to summarize dependency entanglement. Also extracts import/export-like declarations for common languages (Python/Java/Kotlin/Go/Rust/C#). Excludes common build directories like node_modules, .git, dist, etc. It is categorised as a Read tool in the Project Explorer MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Project Explorer MCP Server MCP server in PolicyLayer and add a rule for explore_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 Project Explorer MCP Server. Nothing to install.
explore_project 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 explore_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 explore_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.
explore_project is provided by the Project Explorer MCP Server MCP server (mausrundung/mcp-explorer). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
explore_project is one line of Project Explorer MCP Server's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →