$ loading_
Enable recursive LLM reasoning and code execution for large-context exploration.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "rlm-mcp-server" yet — see the docs or source repo.
Use a recursive approach to inspect this large codebase: identify major modules first, then drill into key directories layer by layer, use Python code to summarize each module’s responsibilities, dependencies, and risks, and return a structured report.
A clearly layered codebase analysis report with module summaries, dependencies, and risk points.
Recursively read this set of very long technical documents by section, extract key conclusions, term definitions, and open questions step by step, and use Python to assemble a final summary and issue list.
A condensed document summary with terminology notes and a follow-up question list.
Perform a recursive exploration of this complex dataset: start with an overall overview, then investigate anomalous distributions and key fields in batches, using Python to generate statistics, findings, and next-step recommendations.
A data analysis result including overview statistics, anomaly findings, and recommended next steps.
Process arbitrarily long contexts with recursive decomposition, without external LLM APIs.
Analyze large codebases hierarchically and build a queryable knowledge map.
Gives AI coding agents persistent memory and semantic file discovery across sessions.
Search and read indexed local documents with full-text and fuzzy matching.
Delegate low-risk tasks to a cheaper model with main-agent review.
Give AI coding assistants memory, code graph insight, and safe multi-agent coordination.