{"name":"io.github.AsterMindAI/astermind-mcp","slug":"astermindai-astermind-mcp","title":"AsterMind MCP","description":"On-device reranking that cuts RAG context tokens ~67% while keeping a relevant passage.","url":"https://mcp.market/server/astermindai-astermind-mcp","rating":null,"grade":"A","score":91,"certified":false,"status":"active","category":"ai","tags":["ai"],"presence":{"score":18,"stars":0,"forks":0,"downloads_week":null,"last_push_at":"2026-09-25T08:41:58.000Z","license":"MIT"},"uptime":null,"claimed":false,"transport":"npm","callable_via_gateway":false,"default_price_micros":0,"repository":"https://github.com/AsterMindAI/astermind-mcp","website":"https://astermindai.com","version":"0.1.0","remotes":[],"packages":[{"registryType":"npm","registryBaseUrl":"https://registry.npmjs.org","identifier":"@astermind/astermind-mcp","version":"0.1.0","transport":{"type":"stdio"}}],"tools":[{"name":"classify_text","description":"Classify text into your categories using an on-device ELM trained on the labeled examples you provide. Requires at least one example per category. Returns a confidence and honestly flags low-confidence results. Use this to route/label locally instead of paying an LLM to classify.","write_action":false,"price_micros":0,"input_schema":null},{"name":"compare_texts","description":"Cosine similarity (0..1) between two texts using local embeddings. Best for detecting near-duplicates / paraphrase overlap, not fine-grained semantic ranking.","write_action":false,"price_micros":0,"input_schema":null},{"name":"compress_context","description":"One-shot token saver: filter candidate documents to what is relevant and return a compact, numbered context block ready to paste into a prompt, plus token-before/after accounting.","write_action":false,"price_micros":0,"input_schema":null},{"name":"count_tokens","description":"Count tokens in a string or array of strings using an OpenAI-compatible BPE tokenizer (o200k/cl100k family). Useful for measuring context size and budgeting.","write_action":false,"price_micros":0,"input_schema":null},{"name":"detect_language","description":"Coarse language detection over 6 European languages (English, Spanish, French, German, Italian, Portuguese) using an on-device classifier. Runs locally with no API call.","write_action":false,"price_micros":0,"input_schema":null},{"name":"estimate_savings","description":"Given the full context vs the filtered context you plan to send an LLM, compute tokens removed, percent saved, and (optionally) dollars saved per call for a given model input price.","write_action":false,"price_micros":0,"input_schema":null},{"name":"filter_context","description":"Drop documents not relevant to the query so you feed the LLM a small, relevant context instead of everything. Reports exact tokens saved using an OpenAI-compatible tokenizer. This is the core token-reduction tool.","write_action":true,"price_micros":0,"input_schema":null},{"name":"generate_embeddings","description":"Produce deterministic local char-level embeddings for a list of texts. Good for clustering, dedupe, and near-duplicate detection. Not a substitute for large transformer embeddings on nuanced semantics.","write_action":false,"price_micros":0,"input_schema":null},{"name":"rerank_documents","description":"Rank candidate documents/chunks by relevance to a query using an on-device ELM reranker. Best when the query shares vocabulary with the documents (typical RAG). Lexical (TF-IDF) based: strong on keyword overlap, weaker on pure-synonym matches.","write_action":false,"price_micros":0,"input_schema":null},{"name":"semantic_search","description":"Return the top documents matching a query from a provided set, scored by an on-device lexical (TF-IDF) reranker. Strong on keyword overlap; not a transformer embedding search.","write_action":false,"price_micros":0,"input_schema":null}],"scan":{"score":91,"grade":"A","scanned_at":"2026-09-25T12:00:57.709Z","report":{"scannerVersion":"0.1.9","scannedAt":"2026-09-25T12:00:57.408Z","components":{"code":{"score":25,"max":25,"notes":["6 source files scanned"]},"reliability":{"score":-1,"max":20,"notes":["no gateway calls yet and no remote to probe"]},"poisoning":{"score":-1,"max":15,"notes":["tools not inspected (local package is not executed); not counted"]},"auth":{"score":12,"max":15,"notes":["local package, no credentials required"]},"maintenance":{"score":15,"max":15,"notes":["last push 0 days ago"]},"identity":{"score":7,"max":10,"notes":["registry namespace matches repository owner"]}},"findings":[],"inputs":{"packages":[{"registryType":"npm","identifier":"@astermind/astermind-mcp","version":"0.1.0","found":true,"license":"MIT","hasInstallScripts":false,"dependencyCount":3,"publishedAt":"2026-09-25T02:15:21.936Z","repositoryUrl":"git+https://github.com/AsterMindAI/astermind-mcp.git"}],"repo":{"found":true,"owner":"AsterMindAI","repo":"astermind-mcp","archived":false,"pushedAt":"2026-09-25T08:41:58Z","stars":0,"forks":0,"openIssues":0,"ownerType":"Organization","ownerAvatarUrl":"https://avatars.githubusercontent.com/u/255252170?v=4","ownerCreatedAt":"2026-01-16T01:55:49Z","license":"MIT"},"icon":{"url":"https://avatars.githubusercontent.com/u/255252170?v=4&s=128","source":"github"},"presence":{"stars":0,"forks":0,"downloadsWeek":null,"license":"MIT","lastPushAt":"2026-09-25T08:41:58.000Z","score":18}}}},"grade_history":[],"reviews":[]}