describe_datasource
AI agents call describe_datasource to retrieve information from SLayer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to retrieve or query descriptive information about datasources—a read-only operation with no side effects. While the description is empty (reducing confidence slightly), the name itself strongly indicates data inspection rather than mutation or execution. Classified as Read with medium-high confidence. Severity is low because describing a datasource poses minimal risk even if misused by an agent.
From the tool's definition Tool name 'describe_datasource' suggests retrieval of metadata/schema information about a datasource. The naming pattern aligns with inspection/query operations (cf. sibling tools like 'get_datasource_priority'). No modification or deletion keywords present.
Documented attack patterns abuse exactly the kind of access describe_datasource gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and SLayer, and nothing reaches the server without passing your rules. This is the rule we recommend for describe_datasource:
{
"version": "1",
"default": "deny",
"tools": {
"describe_datasource": {}
}
}describe_datasource 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.
describe_datasource. It is categorised as a Read tool in the SLayer MCP Server, which means it retrieves data without modifying state.
Register the SLayer MCP server in PolicyLayer and add a rule for describe_datasource: 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 SLayer. Nothing to install.
describe_datasource 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 describe_datasource 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 describe_datasource. 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.
describe_datasource is provided by the SLayer MCP server (motleyai/slayer). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from SLayer, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
20 SLayer tools catalogued and risk-classified — across an index of 43,000+ MCP servers.