project.open
Open and migrate a portable project, returning its canonical resolved path.
This record as markdown: /tools/visionmcp/project.open.md
What project.open does on Visionmcp
AI agents call project.open to retrieve information from Visionmcp without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why project.open is rated Low
The tool opens an existing project and returns its resolved path. This is a retrieval/query operation with no side effects on data creation, modification, or deletion. While 'open' could potentially involve initialization or state changes, the description emphasizes returning a path, which is fundamentally a read operation. The most similar canonical Read operation is 'get' or 'fetch'.
From the tool's definition Tool description states it 'Open[s]...a portable project, returning its canonical resolved path' — a read operation that retrieves and returns path information with no data modification.
Attacks that exploit this kind of access
The rule that runs project.open safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Visionmcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For project.open, this is the rule to start with:
project.open is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Visionmcp, apply this rule, and every project.open call is checked against it from then on.
Questions about project.open
Open and migrate a portable project, returning its canonical resolved path. It is categorised as a Read tool in the Visionmcp MCP Server, which means it retrieves data without modifying state.
Register the Vision MCP server in PolicyLayer and add a rule for project.open: 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 Visionmcp. Nothing to install.
project.open 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 project.open 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 project.open. 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.
project.open is provided by the Vision MCP server (joshuahickscorp/visionmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Vision, and thousands of servers like it.
This server
Across the catalogue