Finds and retrieves relationships in the SpiceDB system matching the provided filters. All parameters are optional, allowing you to filter with varying levels of specificity - from all relationships in the system to a very specific relationship between two objects.
AI agents call read-relationships 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 queries and retrieves relationship data from SpiceDB without creating, modifying, or deleting anything. It is a passive data retrieval operation with optional filtering parameters. The blast radius of misuse is minimal—an agent could over-query the system but cannot damage or alter permission data. Therefore, this is classified as Read with low severity.
From the tool's definition Tool name 'read-relationships' and description explicitly states it 'Finds and retrieves relationships' with filtering capabilities. The verb 'retrieves' and lack of any modification language indicates a query-only operation with no side effects.
Attacks that exploit this kind of access
Finds and retrieves relationships in the SpiceDB system matching the provided filters. All parameters are optional, allowing you to filter with varying levels of specificity - from all relationships in the system to a very specific relationship between two objects. 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-relationships: 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-relationships 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-relationships 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-relationships. 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-relationships 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 →