inspect_provider_catalog
List the canonical integration provider catalog without loading provider endpoint tools into context. Use category/status/search to narrow before inspecting endpoints.
This record as markdown: /tools/adrata-starfield-mcp/inspect-provider-catalog.md
What inspect_provider_catalog does on Starfield
AI agents call inspect_provider_catalog to retrieve information from Starfield without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
search | string | — | Optional local search across provider name/id/category/runtime/auth |
status | string | — | Optional status filter, for example CredentialOnly |
category | string | — | Optional category filter, for example Outbound |
includeCustom | boolean | — | Deprecated compatibility flag; canonical catalog is returned by default |
Parameters from the server's own tool schema.
Why inspect_provider_catalog is rated Low
Even though inspect_provider_catalog only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
The rule that runs inspect_provider_catalog safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Starfield, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For inspect_provider_catalog, this is the rule to start with:
inspect_provider_catalog is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Starfield, apply this rule, and every inspect_provider_catalog call is checked against it from then on.
Questions about inspect_provider_catalog
List the canonical integration provider catalog without loading provider endpoint tools into context. Use category/status/search to narrow before inspecting endpoints. It is categorised as a Read tool in the Starfield MCP Server, which means it retrieves data without modifying state.
inspect_provider_catalog accepts 4 parameters: search, status, category, includeCustom. The full parameter table on this page comes from the server's own tool schema.
Register the Starfield MCP server in PolicyLayer and add a rule for inspect_provider_catalog: 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 Starfield. Nothing to install.
inspect_provider_catalog 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 inspect_provider_catalog 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 inspect_provider_catalog. 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.
inspect_provider_catalog is provided by the Starfield MCP server (@adrata/starfield-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Starfield, and thousands of servers like it.
This server
Across the catalogue