AI agents call embedding_health 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.
The name strongly implies a diagnostic query operation that retrieves health metrics about the embedding system. No description is provided, which lowers confidence slightly, but the naming pattern and context within a code indexing server indicate a read-only operation. Health checks and status queries are non-destructive information retrievals.
From the tool's definition Tool name 'embedding_health' suggests monitoring or querying the status of embeddings. The server provides 'deep code indexing' and 'embedding_status' is listed as a sibling tool, indicating this is likely a status/health check operation with no side effects.
Documented attack patterns abuse exactly the kind of access embedding_health 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 embedding_health:
{
"version": "1",
"default": "deny",
"tools": {
"embedding_health": {}
}
}embedding_health 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.
embedding_health. 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 embedding_health: 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.
embedding_health 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 embedding_health 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 embedding_health. 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.
embedding_health 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.