"A local-only document search tool" matching MCP servers:

Enables an AI assistant to query and browse multiple database engines read-only, with the ability to switch connections and engines dynamically during a session.

Provides read-only, authenticated access to prepared Markdown, images, document structure, and original-file references published as immutable versioned bundles alongside Paperless-ngx source documents. It can also explicitly forward selected prepared Markdown into WeKnora's existing ingestion interface without subscribing to future documents.

Enables conversion between PDF/Office documents and structured JSON, supporting extraction and generation of document content.

Convert PDFs to structured JSON. Extract invoices, bank statements, contracts, and more. Pay per call via x402 USDC.

Provides a stateful local Spark session for running PySpark and SQL cells, enabling local data exploration before deploying to Microsoft Fabric.

Enables agents to extract multi-page financial tables from complex PDFs, rasterize vector pages into crisp 300 DPI images for vision LLMs, flatten interactive AcroForm/XFA forms, and dewarp skewed OCR bounding boxes from photographed or scanned paper documents. Tool invocations are gated by USDC micropayments settled on Base L2 via the x402 protocol.

Enables AI agents to index and search across SQLite databases and CSV files to discover table schemas and column metadata. It provides a unified MCP API for data source management and structural exploration through natural language.

基于Model Context Protocol (MCP) 的A股实时行情查询服务器，支持查询A股实时价格、历史K线数据、财务信息及市场概况。

Converts raster and vector geospatial data into H3-indexed Parquet files and serves them via a local MCP server with DuckDB SQL querying.

Enables AI agents and MCP clients to heuristically parse multi-column document dumps, aligned spacing, and CSV/TSV input, converting them into clean GitHub Flavored Markdown tables and typed JSON. Runs fully offline on the Python standard library with zero external dependencies, returning deterministic results without LLM round-trips.

Enables AI agents and MCP clients to convert ASCII/OCR text dumps, aligned spacing, and CSV/TSV data into clean GitHub Flavored Markdown tables and typed JSON deterministically.

Syncs Google Search Console performance data into a local ClickHouse database and exposes prepared SEO analysis tools to AI agents. Enables diagnosing traffic drops, finding striking-distance keywords, detecting cannibalization, auditing indexing, and generating weekly SEO reports through natural language.

Enables MCP clients to execute validated read-only warehouse queries through a guarded SQL API, with enforced row limits and secret-safe audit metadata.

Transforms CSV and Excel data into Markdown-formatted vector embeddings stored in a local ChromaDB instance for semantic search. It enables MCP clients to retrieve relevant tabular data through single-row, batch, or free-text queries.

Enables document layout parsing, complex table reconstruction, formula auditing, and PII/credential redaction with Luhn verification, reversible salt hashing, and audit logs through MCP-compatible clients.

Minimalistic MCP server that lets AI assistants inspect, quality-check, and clean CSV datasets through tools, resources, and prompts, without needing local file access.

Enables AI agents to safely ingest, inspect, edit, and export manufacturing documents (Excel, PDF, Word, Markdown) with controlled patch workflows and MES entity extraction.

Enables querying open Power BI Desktop models locally, including discovering instances, listing tables and measures, and running DAX queries without cloud login or publishing.

Enables read-only access to Board models through an authenticated Firefox session, listing models, entities, and cubes with their metadata without exposing data editing or API credentials.

Provides cryptocurrency market data using the CoinGecko API