Returns the available JSON collections (files in data/) with a sample record from each. Plan authors call this at design time so the LLM uses the actual field names of the data — preventing invented fact names that the tool will never populate.
AI agents call describe-data-sources to retrieve information from Mmc without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about available data sources and sample records to inform LLM planning. It performs no writes, deletions, code execution, or financial operations. The blast radius of misuse is minimal — an agent could only discover what data collections exist and see sample field names, posing no risk to data integrity or system stability.
From the tool's definition Tool description explicitly states it 'Returns the available JSON collections' and 'a sample record from each' — pure retrieval with no modification. The phrase 'Plan authors call this at design time' confirms read-only usage for schema discovery.
Attacks that exploit this kind of access
Returns the available JSON collections (files in data/) with a sample record from each. Plan authors call this at design time so the LLM uses the actual field names of the data — preventing invented fact names that the tool will never populate. It is categorised as a Read tool in the Mmc MCP Server, which means it retrieves data without modifying state.
Register the Mmc MCP server in PolicyLayer and add a rule for describe-data-sources: 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 Mmc. Nothing to install.
describe-data-sources 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-data-sources 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-data-sources. 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-data-sources is provided by the Mmc MCP server (modelmycontext/mmc-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →