Search the GraphRAG knowledge base with THREE distinct modes:\n\nCRITICAL: For ticker symbols (ASTS, RKLB, NBIS) or acronyms, ALWAYS use
AI agents call search to retrieve information from GraphRAG Llama Index MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a search/query tool that retrieves information from a knowledge base without modifying, deleting, or executing external operations. It performs read-only access to indexed data using hybrid search (BM25 + vector fusion). There are no side effects, data modifications, or irreversible actions. The severity is low because misuse would only retrieve existing data, not alter state or cause harm.
From the tool's definition Tool description explicitly states 'Search the GraphRAG knowledge base' and the server description emphasizes 'query a local knowledge graph' and 'semantic search'. The sibling tools (explore_entity_graph, get_corpus_stats) are also read-only operations.
Attacks that exploit this kind of access
Search the GraphRAG knowledge base with THREE distinct modes:\n\nCRITICAL: For ticker symbols (ASTS, RKLB, NBIS) or acronyms, ALWAYS use. It is categorised as a Read tool in the GraphRAG Llama Index MCP Server MCP Server, which means it retrieves data without modifying state.
Register the GraphRAG Llama Index MCP Server MCP server in PolicyLayer and add a rule for search: 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 GraphRAG Llama Index MCP Server. Nothing to install.
search 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 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. 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 is provided by the GraphRAG Llama Index MCP Server MCP server (t-nhannguyen/graphrag-llamaindex). 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 →