提取指定图片的 base64 数据并保存到本地文件。可从 gemini_get_images 获取图片 src URL
AI agents call gemini_extract_image to retrieve information from Gemini Skill without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and encodes existing image data from the Gemini interface. While it involves local file I/O, the core operation is data extraction and reading without side effects on the Gemini service or the images themselves. No data is created, modified, deleted, or executed. The local file save is incidental storage of the read data.
From the tool's definition Tool description states: '提取指定图片的 base64 数据并保存到本地文件' (extract base64 data of specified image and save to local file). The action is retrieval and encoding of image data without modification of the source.
Documented attack patterns abuse exactly the kind of access gemini_extract_image gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Gemini Skill, and nothing reaches the server without passing your rules. This is the rule we recommend for gemini_extract_image:
{
"version": "1",
"default": "deny",
"tools": {
"gemini_extract_image": {}
}
}gemini_extract_image 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.
提取指定图片的 base64 数据并保存到本地文件。可从 gemini_get_images 获取图片 src URL. It is categorised as a Read tool in the Gemini Skill MCP Server, which means it retrieves data without modifying state.
Register the Gemini Skill MCP server in PolicyLayer and add a rule for gemini_extract_image: 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 Gemini Skill. Nothing to install.
gemini_extract_image 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 gemini_extract_image 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 gemini_extract_image. 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.
gemini_extract_image is provided by the Gemini Skill MCP server (wjz-p/gemini-skill). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 21 Gemini Skill tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
21 Gemini Skill tools catalogued and risk-classified — across an index of 42,500+ MCP servers.