Search the Morocco knowledge graph for entities and relationships
AI agents call search_knowledge_graph to retrieve information from Morocco Open Data MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries data from a knowledge graph without creating, modifying, deleting, or executing side-effects. It is a straightforward read operation that returns information about entities and their relationships.
From the tool's definition Tool name contains 'search' and description states it 'Search[es] the Morocco knowledge graph for entities and relationships' — a query operation with no modification or execution of external operations.
Attacks that exploit this kind of access
Search the Morocco knowledge graph for entities and relationships. It is categorised as a Read tool in the Morocco Open Data MCP MCP Server, which means it retrieves data without modifying state.
Register the Morocco Open Data MCP server in PolicyLayer and add a rule for search_knowledge_graph: 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 Morocco Open Data MCP. Nothing to install.
search_knowledge_graph 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 search_knowledge_graph 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 search_knowledge_graph. 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.
search_knowledge_graph is provided by the Morocco Open Data MCP server (kcbdev/morocco-open-data-mcp). 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 →