AI agents invoke open_image_locally to trigger actions in Street View MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The name implies triggering a local system action (opening a file), which constitutes an Execute-level operation. However, the empty description significantly lowers confidence. In context of a Street View server, it likely opens a fetched image in a local viewer, which could interact with the local filesystem or OS.
From the tool's definition Tool name 'open_image_locally' suggests executing a local file open operation; description is empty and uninformative.
Documented attack patterns abuse exactly the kind of access open_image_locally gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Street View MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for open_image_locally:
{
"version": "1",
"default": "deny",
"tools": {
"open_image_locally": {
"limits": [
{
"counter": "open_image_locally_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}open_image_locally stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
open_image_locally. It is categorised as a Execute tool in the Street View MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Street View MCP server in PolicyLayer and add a rule for open_image_locally: 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 Street View MCP. Nothing to install.
open_image_locally is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the open_image_locally 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 open_image_locally. 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.
open_image_locally is provided by the Street View MCP server (vlad-ds/street-view-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Street View MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 Street View MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.