"Kingsoft Document Connector" matching MCP servers:

Indexes local documents (PDF, Word, Markdown, text) into a SQLite database for AI agents to search and retrieve bounded, source-located passages. Runs fully locally with optional OCR, preserving privacy.

Verifiable document intelligence for AI agents. Extract text, tables, and structured data from PDFs and URLs. Summarize, answer questions, check claims, and translate — all with cited evidence. Store tamper-evident evidence bundles with cryptographic signatures and on-chain attestation via Base L2. Cross-document semantic search and Q&A across named collections. Pay per call with USDC

Natural language to SQL engine with multi-connector support (PostgreSQL, MySQL, Snowflake, BigQuery, DuckDB), document QA, semantic caching, and self-hosted MCP server.

An MCP server that allows users to efficiently search and reference user-configured documents through document listing, grep searching, semantic searching with OpenAI Embeddings, and full document retrieval.

Stdio MCP server for Cortex, a patent-pending semantic memory for AI agents: seven tools (search, fetch, recall, save with quality gate, write status, conflicts, forget) forwarded to the hosted Cortex service, shared by ChatGPT, Claude and any MCP client.

Local RAG knowledge base for Qwen Code, enabling document indexing and semantic search via MCP tools. Supports metadata filtering and document retrieval without external dependencies.

A local document evidence layer for MCP clients that ingests documents (PDF, Office, images) with optional OCR, indexes them in SQLite FTS, and provides retrieval tools with source coordinates.

MCP server that indexes uploaded PDF, DOCX, and TXT documents into an isolated per-session in-memory vector index and retrieves the exact matching passages behind each answer. It exposes document indexing and search tools to a Q&A backend so every response is grounded in cited, retrieved evidence.

Provides AI agents with multi-format document indexing, hybrid dense and sparse search with reranking, and relational SQL querying over extracted tables.

Provides tools for document conversion, processing, and generation, enabling PDF to structured JSON conversion, document creation, and caching for improved performance.

Enables local semantic search over PDF, DOCX, PPTX, and EPUB documents by converting them to Markdown, indexing them in ChromaDB, and retrieving complete structure-aware sections with tables and equations.

Enables interactive chat with AI models, including document retrieval and command-based prompts via the Model Control Protocol.

An intelligent document management MCP server that leverages mental models and orchestration patterns for context-aware document storage, retrieval, and analysis.

Enables LLMs to interact with Outline wiki for document management, search, and collections, with optional AI-powered features including RAG-based Q\&A, semantic search, and document summarization.

A lightweight document parser MCP server that enables Claude to parse PDFs, Word, Excel, images (OCR), and other document formats with support for chunking and metadata extraction.

Enables LLMs to interact with Rememberizer Vector Store for semantic search, document creation, deletion, and modification.

Bridges AI agents with watsonx.data document libraries, enabling natural language queries and intelligent retrieval from document libraries.

Enables AI agents to search, deep-read, and build knowledge bases from Markdown, PDF, DOCX, and PPTX documents via MCP tools for retrieval, document navigation, and ingestion.

MCP server that exposes NetApp AI Data Engine's RAG search for semantic document retrieval.

Exposes search, passage retrieval, and document listing tools over streamable HTTP so MCP clients can query a security-questionnaire knowledge base and receive results with document, version, and heading provenance.