provider_status

Check health of all configured providers by pinging one model from each.

Server Model Radar srclight/model-radar
Category Read
Risk class Low
Parameters 00 required

What provider_status does on Model Radar

AI agents call provider_status to retrieve information from Model Radar without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why provider_status needs a policy

The tool performs health checks and status queries across providers. Pinging models retrieves status information without creating, modifying, deleting, or executing code/commands. This is a classic Read operation—it gathers state information for inspection purposes only. The blast radius if misused is minimal, as pings cannot corrupt data or trigger unintended side effects.

From the tool's definition Tool description states 'Check health of all configured providers by pinging one model from each.' This is a monitoring/status query operation with no side effects. It retrieves health information via ping operations, which are read-only network diagnostics.

Questions about provider_status

What does the provider_status tool do? +

Check health of all configured providers by pinging one model from each. It is categorised as a Read tool in the Model Radar MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on provider_status? +

Register the Model Radar MCP server in PolicyLayer and add a rule for provider_status: 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 Model Radar. Nothing to install.

What risk level is provider_status? +

provider_status is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit provider_status? +

Yes. Add a rate_limit block to the provider_status 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.

How do I block provider_status completely? +

Set action: deny in the PolicyLayer policy for provider_status. 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.

What MCP server provides provider_status? +

provider_status is provided by the Model Radar MCP server (srclight/model-radar). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.