Internal maintenance (requires write). Syncs gte-small (384-dim) vector embeddings for the MCP tool, whiteboard stencil, and architecture icon catalogs into platform_catalog_embeddings, so searchTools, listWhiteboardStencils, and listArchitectureIcons can do semantic search. Incremental: scans ev...
Risk signalsBulk/mass operation — affects multiple targets
Part of the Stable Baseline server.
Free to start. No card required.
AI agents use rebuildPlatformCatalogEmbeddings to create or modify resources in Stable Baseline. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call rebuildPlatformCatalogEmbeddings repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Stable Baseline.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
{
"version": "1",
"default": "deny",
"tools": {
"rebuildPlatformCatalogEmbeddings": {
"limits": [
{
"counter": "rebuildplatformcatalogembeddings_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}See the full Stable Baseline policy for all 184 tools.
These attack patterns abuse exactly the kind of access rebuildPlatformCatalogEmbeddings gives an agent. Each links to the full case and the policy that stops it:
Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Internal maintenance (requires write). Syncs gte-small (384-dim) vector embeddings for the MCP tool, whiteboard stencil, and architecture icon catalogs into platform_catalog_embeddings, so searchTools, listWhiteboardStencils, and listArchitectureIcons can do semantic search. Incremental: scans every catalog, diffs by content hash, and re-embeds ONLY changed rows (cheap no-op when nothing changed). This normally runs automatically every hour (the platform-catalog-sync cron), so manual calls are rarely needed — use it to force an immediate sync after changing tools/stencils/icons. Embeds up to ~120 changed rows per call; if more changed, call again until allDone is true. Not part of normal authoring flows.. It is categorised as a Write tool in the Stable Baseline MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Stable Baseline MCP server in PolicyLayer and add a rule for rebuildPlatformCatalogEmbeddings: 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 Stable Baseline. Nothing to install.
rebuildPlatformCatalogEmbeddings is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the rebuildPlatformCatalogEmbeddings 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 rebuildPlatformCatalogEmbeddings. 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.
rebuildPlatformCatalogEmbeddings is provided by the Stable Baseline MCP server (https://api.stablebaseline.io/functions/v1/cloud-serve/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 184 Stable Baseline 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.