search_with_source_filter
AI agents call search_with_source_filter to retrieve information from Kedro RAG MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a search with filtering capabilities against a local knowledge base of documentation. This is a read-only operation that retrieves data without modifying, deleting, or executing code. No side effects or irreversible actions are possible. Confidence is slightly reduced due to the empty description, but the context makes the intent clear.
From the tool's definition Tool name 'search_with_source_filter' indicates a search operation. The server description emphasizes 'query Kedro framework documentation using retrieval-augmented generation' and 'builds a local knowledge base.' Sibling tools like 'search_kedro_docs'…
Attacks that exploit this kind of access
search_with_source_filter. It is categorised as a Read tool in the Kedro RAG MCP MCP Server, which means it retrieves data without modifying state.
Register the Kedro RAG MCP server in PolicyLayer and add a rule for search_with_source_filter: 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 Kedro RAG MCP. Nothing to install.
search_with_source_filter 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_with_source_filter 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_with_source_filter. 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_with_source_filter is provided by the Kedro RAG MCP server (sajidalamqb/kedro-mcp-rag). 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 →