Gets a Base64-encoded screenshot of a source. Args: source_name: Name of the source to get a screenshot of image_format: Image format (png, jpeg, bmp, tga, gif) image_width: Screenshot width (0 = source width) image_height: Screenshot height (0 = source height) image_compression_quality: Compress...
AI agents call get_source_screenshot to retrieve information from OBS MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a pure data retrieval operation that captures the current visual state of an OBS source without any ability to modify, delete, or execute operations. The tool simply queries and returns screenshot data in various formats. Even in the context of a broadcast system, capturing a screenshot poses minimal risk as it does not affect streaming, recording, scene management, or any other system state.
From the tool's definition Tool retrieves a Base64-encoded screenshot of a source with no modification or deletion capabilities. Arguments control output format and dimensions but do not alter underlying data or state. No side effects mentioned.
Documented attack patterns abuse exactly the kind of access get_source_screenshot gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OBS MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_source_screenshot:
{
"version": "1",
"default": "deny",
"tools": {
"get_source_screenshot": {}
}
}get_source_screenshot 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.
Gets a Base64-encoded screenshot of a source. Args: source_name: Name of the source to get a screenshot of image_format: Image format (png, jpeg, bmp, tga, gif) image_width: Screenshot width (0 = source width) image_height: Screenshot height (0 = source height) image_compression_quality: Compression quality (1-100, -1 = default) Returns: Base64-encoded screenshot image. It is categorised as a Read tool in the OBS MCP Server MCP Server, which means it retrieves data without modifying state.
Register the OBS MCP Server MCP server in PolicyLayer and add a rule for get_source_screenshot: 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 OBS MCP Server. Nothing to install.
get_source_screenshot 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_source_screenshot 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_source_screenshot. 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_source_screenshot is provided by the OBS MCP Server MCP server (royshil/obs-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 200 OBS MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
200 OBS MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.