SEARCH ENTITIES by TEXT or TAGS across names, types, observations, and tags. Supports exact/fuzzy search modes, multiple query batching, tag filtering, and pagination. Returns entities and their relationships. MUST USE BEFORE create_entities, add_observations, and create_relations to verify entit...
AI agents call search_knowledge to retrieve information from KnowledgeGraph MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool is a query/search operation that retrieves data from the knowledge graph without side effects. It returns information about entities and relationships but does not create, modify, or delete any data. The use case described (verifying entity existence before other operations) further confirms it as a read-only operation.
From the tool's definition Tool performs SEARCH ENTITIES and retrieves entities and their relationships. Explicitly described as supporting text/tag search, filtering, and pagination with return values. No modifications, deletions, or execution capabilities mentioned.
Documented attack patterns abuse exactly the kind of access search_knowledge gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and KnowledgeGraph MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for search_knowledge:
{
"version": "1",
"default": "deny",
"tools": {
"search_knowledge": {}
}
}search_knowledge is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
SEARCH ENTITIES by TEXT or TAGS across names, types, observations, and tags. Supports exact/fuzzy search modes, multiple query batching, tag filtering, and pagination. Returns entities and their relationships. MUST USE BEFORE create_entities, add_observations, and create_relations to verify entity existence. PAGINATION: Use page parameter to navigate large result sets (page=0 for first page, page=1 for second, etc.). It is categorised as a Read tool in the KnowledgeGraph MCP Server MCP Server, which means it retrieves data without modifying state.
Register the KnowledgeGraph MCP Server MCP server in PolicyLayer and add a rule for search_knowledge: 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 KnowledgeGraph MCP Server. Nothing to install.
search_knowledge 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 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. 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 is provided by the KnowledgeGraph MCP Server MCP server (n-r-w/knowledgegraph-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from KnowledgeGraph MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
11 KnowledgeGraph MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.