project_inspect

Inspect a project. op: DETAIL (app list, project config, latest schema metadata, deployment) | METADATA (plan/capability, deployment, app list, schema metadata, RPS summary) | RESOURCES (resource consumption, plan limits, RPS, optional history). includeSecrets applies to DETAIL/METADATA; refresh/...

Server Zion zion-mcp
Category Read
Risk class Low
Parameters 81 required

What project_inspect does on Zion

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

ParameterTypeRequiredDescription
op string Yes
appExId string | null
refresh boolean
projectExId string
resourceType string
appVersionExId string | null
includeSecrets boolean
nonRealTimeDisplayedResourceTypes array

Parameters from the server's own tool schema.

Why project_inspect needs a policy

This is a Read operation—it queries and retrieves project information without modifying or deleting anything. However, the 'includeSecrets' parameter suggests it can expose sensitive authentication or configuration secrets, elevating severity to medium.

From the tool's definition The tool description states it can 'Inspect a project' with operations DETAIL, METADATA, and RESOURCES that retrieve 'app list, project config, latest schema metadata, deployment, plan/capability, resource consumption, plan limits, RPS summary'.

Questions about project_inspect

What does the project_inspect tool do? +

Inspect a project. op: DETAIL (app list, project config, latest schema metadata, deployment) | METADATA (plan/capability, deployment, app list, schema metadata, RPS summary) | RESOURCES (resource consumption, plan limits, RPS, optional history). includeSecrets applies to DETAIL/METADATA; refresh/resourceType/nonRealTimeDisplayedResourceTypes apply to RESOURCES. It is categorised as a Read tool in the Zion MCP Server, which means it retrieves data without modifying state.

What parameters does project_inspect accept? +

project_inspect accepts 8 parameters: op, appExId, refresh, projectExId, resourceType, appVersionExId, includeSecrets, nonRealTimeDisplayedResourceTypes. Required: op. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on project_inspect? +

Register the Zion MCP server in PolicyLayer and add a rule for project_inspect: 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 Zion. Nothing to install.

What risk level is project_inspect? +

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

Can I rate-limit project_inspect? +

Yes. Add a rate_limit block to the project_inspect 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 project_inspect completely? +

Set action: deny in the PolicyLayer policy for project_inspect. 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 project_inspect? +

project_inspect is provided by the Zion MCP server (zion-mcp). 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.