Redra MCP Server

Return complete stored records for multiple settlement finalists. Retrieve every finalist before presenting it. Use the records and official links to separate evidence-backed leads from plausible or speculative leads. A detail record does not itself prove that the user is eligible. If browsing is available, verify the complete class definition on the official source.

Search settlement records by keywords and structured filters. Every keyword is required: the list uses logical AND, not OR. Use separate searches for unrelated companies, products, or alternative terms. Keywords should describe companies, products, services, employers, incidents, or notices. For a broad eligibility scan, think expansively using relevant context and memory available to the agent and make multiple queries across plausible brands, aliases, parent companies, subsidiaries, purchases, providers, fees, incidents, and eligibility-relevant demographic angles such as age group, occupation, student or veteran status, parent or guardian status, and housing or household situation. Use the state filter for location. Do not invent user facts; speculative associations are search candidates only. Status is the claim lifecycle and defaults to open. Use all only for an intentional search across non-open lifecycle states too. Use settlement_type, not keywords, when the term describes the type of settlement rather than a specific entity or event. Source confidence is returned as objective metadata and quality flags; do not exclude possible matches using the provider's verification tier. Do not send names, addresses, account numbers, health details, or other identifying data. State is a two-letter US postal abbreviation.

Run multiple independent settlement searches in one tool call. Prefer this tool for broad eligibility scans and alternative terms. Each query is evaluated independently. Returned records are deduplicated across queries and include matched_query_indices that point to the query summaries. Do not combine unrelated alternatives in one keywords list: keywords within each query use logical AND, never OR. Speculative associations are search candidates only, not evidence that the user matches a settlement. Choose per-query limits based on expected noise and use max_total_results to bound the unique records placed in model context without reducing search breadth. For current eligibility scans, omit status or set it to open; do not use all merely to broaden recall. The response's executed_query_count is the number of independent searches performed in this call.

Return source, license, freshness, counts, and hosted aggregate metrics.

Return one settlement and its official source links. When web access is available, use the official links to verify the complete class definition and eligibility terms before presenting the record as more than a possible match. Present plausible matches as concise lead cards that separate confirmed terms, relevant user context, and facts still needed. If browsing is unavailable, say the terms could not be independently checked, avoid guessing, and direct the user to the official link.