Run a pre-render visual QA check on carousel slides before publishing. Predicts text overflow against per-layout font-size/container constraints from services/carousel/templates/*. Does NOT call Gemini Vision OCR (that runs inside the worker on the rendered PNG). Use after generate_carousel and b...
Part of the Socialneuron server.
Free to start. No card required.
AI agents call visual_quality_check to retrieve information from Socialneuron without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though visual_quality_check only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"visual_quality_check": {}
}
}See the full Socialneuron policy for all 100 tools.
These attack patterns abuse exactly the kind of access visual_quality_check gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Run a pre-render visual QA check on carousel slides before publishing. Predicts text overflow against per-layout font-size/container constraints from services/carousel/templates/*. Does NOT call Gemini Vision OCR (that runs inside the worker on the rendered PNG). Use after generate_carousel and before schedule_post to catch clipped text and single-line overflows. Spellcheck is skipped at the MCP layer \u2014 the worker handles it with the brand vocab allowlist.. It is categorised as a Read tool in the Socialneuron MCP Server, which means it retrieves data without modifying state.
Register the Socialneuron MCP server in PolicyLayer and add a rule for visual_quality_check: 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 Socialneuron. Nothing to install.
visual_quality_check 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 visual_quality_check 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 visual_quality_check. 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.
visual_quality_check is provided by the Socialneuron MCP server (@socialneuron/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 100 Socialneuron tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.