Retrieves the complete schema from the SpiceDB instance. The schema defines all object types, relations, permissions, and caveats in the system. This tool requires no parameters and returns the raw schema text as defined in SpiceDB.
AI agents call read-schema to retrieve information from Spicedb without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a simple retrieval of schema metadata with no side effects, no code execution, no data modification, and no destructive operations. It is analogous to a schema introspection query. The only minor risk is information disclosure of the permission system structure, which is typically low-severity in a properly configured system.
From the tool's definition Tool name 'read-schema' and description 'Retrieves the complete schema from the SpiceDB instance' clearly indicate a read-only operation that queries and returns data without modification.
Attacks that exploit this kind of access
Retrieves the complete schema from the SpiceDB instance. The schema defines all object types, relations, permissions, and caveats in the system. This tool requires no parameters and returns the raw schema text as defined in SpiceDB. It is categorised as a Read tool in the Spicedb MCP Server, which means it retrieves data without modifying state.
Register the Spicedb MCP server in PolicyLayer and add a rule for read-schema: 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 Spicedb. Nothing to install.
read-schema 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 read-schema 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 read-schema. 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.
read-schema is provided by the Spicedb MCP server (samkim/spicedb-mcp-server). 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 →