AI agents call platform_conditionals to retrieve information from Srclight without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to be a read-only analysis/search function within the srclight code indexing server. The empty description lowers confidence, but the name and server purpose (deep code indexing, symbol search, navigation) strongly indicate it retrieves or queries code structure rather than executing, modifying, or destroying data.
From the tool's definition Tool name 'platform_conditionals' with empty description suggests querying or analyzing conditional logic across platform variants in code, consistent with the srclight server's indexing and exploration functions (search symbols, navigate call graphs, explore…
Documented attack patterns abuse exactly the kind of access platform_conditionals gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Srclight, and nothing reaches the server without passing your rules. This is the rule we recommend for platform_conditionals:
{
"version": "1",
"default": "deny",
"tools": {
"platform_conditionals": {}
}
}platform_conditionals 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.
platform_conditionals. It is categorised as a Read tool in the Srclight MCP Server, which means it retrieves data without modifying state.
Register the Srclight MCP server in PolicyLayer and add a rule for platform_conditionals: 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 Srclight. Nothing to install.
platform_conditionals 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 platform_conditionals 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 platform_conditionals. 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.
platform_conditionals is provided by the Srclight MCP server (srclight/srclight). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 42 Srclight tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
42 Srclight tools catalogued and risk-classified — across an index of 42,500+ MCP servers.