About Mnehmos.index Foundry.mcp
Mnehmos.index Foundry.mcp is an MCP server published by Mnehmos in the RAG category: rAG indexing and retrieval MCP server.
The repository has 6 stars and 1 forks, with the last commit 2 months ago. Recent commit activity is the strongest signal that reported issues will get attention.
Install
git clone https://github.com/Mnehmos/mnehmos.index-foundry.mcpThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (25)
indexfoundry_classify_query🔍 Classify a query to determine if RAG retrieval is needed and what type of query it is. Returns query type (factual/procedural/conceptual/navigational/conversational), complexity, confidence, and retrieval hints.
Parameters not published.
indexfoundry_connect_folderLoad files from a local folder using glob patterns. Validates file sizes and content types.
Parameters not published.
indexfoundry_connect_pdfFetch a PDF file from URL or local path with specialized validation and metadata extraction.
Parameters not published.
indexfoundry_connect_sitemapCrawl a sitemap XML file and fetch all linked pages. Supports URL pattern filtering, concurrent fetching, and depth limits.
Parameters not published.
indexfoundry_connect_urlFetch a single URL and store raw content. Supports domain allowlisting, timeout configuration, and content validation.
Parameters not published.
indexfoundry_debug_query🔍 Debug retrieval queries with pipeline tracing, similarity scores, and expected/actual comparison. Diagnose why queries don
Parameters not published.
indexfoundry_extract_documentGeneric document extractor for markdown, plain text, CSV, and JSON files. Normalizes encoding and line endings.
Parameters not published.
indexfoundry_extract_htmlExtract text and structure from HTML content. Preserves headings, tables, and semantic markup. Outputs clean text or markdown.
Parameters not published.
indexfoundry_extract_pdfExtract text from PDF files, producing page-by-page JSONL output. Handles multi-column layouts and embedded fonts.
Parameters not published.
indexfoundry_extract_tables📊 Extract and linearize tables from markdown, HTML, or CSV content. Produces structured table data, linearized text for vector embedding, and chunks for RAG retrieval.
Parameters not published.
Show all 25 tools
indexfoundry_index_build_profileDefine retrieval configuration: top_k, hybrid search settings, reranking, metadata filters, and scoring adjustments.
Parameters not published.
indexfoundry_index_embedGenerate vector embeddings for chunks using OpenAI or local models. Batch processing with retry logic and rate limiting.
Parameters not published.
indexfoundry_index_upsertUpsert vectors to a vector database. Supports local file-based storage and external providers (Pinecone, Weaviate, Qdrant, Milvus, Chroma).
Parameters not published.
indexfoundry_normalize_chunkSplit extracted text into semantic chunks. Supports strategies: recursive (default), hierarchical (parent-child from markdown headings), paragraph, heading, page, sentence, fixed. Produces deterministic SHA256 chunk IDs.
Parameters not published.
indexfoundry_normalize_dedupeDeduplicate chunks by exact content hash or fuzzy similarity (simhash). Preserves the first occurrence and tracks duplicates.
Parameters not published.
indexfoundry_normalize_enrichEnrich chunks with metadata: language detection, regex-based tagging, section classification, and taxonomy mapping.
Parameters not published.
indexfoundry_run_cleanupDelete old runs with optional manifest preservation. Supports age-based and count-based retention policies.
Parameters not published.
indexfoundry_run_diffCompare two runs: configuration differences, source changes, chunk deltas, and timing comparisons.
Parameters not published.
indexfoundry_run_listList all runs with optional filtering by status, date range, and sorting options.
Parameters not published.
indexfoundry_run_statusGet detailed status of a run including phase completion, timing, errors, and artifact counts.
Parameters not published.
indexfoundry_serve_openapiGenerate an OpenAPI 3.1 specification for the index API. Configurable endpoints: search_semantic, search_hybrid, get_chunk, health, stats.
Parameters not published.
indexfoundry_serve_queryQuery a running search server directly (without HTTP). Supports semantic, keyword, and hybrid search modes.
Parameters not published.
indexfoundry_serve_startStart an HTTP search API server for a run. Loads vectors and chunks into memory, serves semantic/hybrid/keyword search endpoints.
Parameters not published.
indexfoundry_serve_statusGet status of running search servers. Shows endpoint, uptime, request count, and loaded vector/chunk counts.
Parameters not published.
indexfoundry_serve_stopStop a running search API server for a run. Returns server uptime and request count.
Parameters not published.
Ask AI
Ask AI about Mnehmos.index Foundry.mcp
Powered by Claude · Grounded in docs
Security checks
6 checks have not been run yet.