context_rag_context_search
AI agents call context_rag_context_search to retrieve information from IMS MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
RAG-based context search tools retrieve and query stored information without modifying, deleting, or executing external operations. The naming pattern (search operation on a memory/context system) and the server's stated purpose (maintaining long-term memory and context) indicate a read-only retrieval capability.
From the tool's definition Tool name 'context_rag_context_search' contains 'search' and 'rag' (Retrieval-Augmented Generation), indicating a retrieval/query operation. Description is empty, limiting certainty.
Attacks that exploit this kind of access
context_rag_context_search. It is categorised as a Read tool in the IMS MCP Server MCP Server, which means it retrieves data without modifying state.
Register the IMS MCP Server MCP server in PolicyLayer and add a rule for context_rag_context_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 IMS MCP Server. Nothing to install.
context_rag_context_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 context_rag_context_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 context_rag_context_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.
context_rag_context_search is provided by the IMS MCP Server MCP server (jdelon02/ims-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 →