"SearXNG, a privacy-respecting metasearch engine" matching MCP servers:

Provides secure, agentic Excel analysis and calculation capabilities, enabling users to inspect workbook structure, perform statistical computations, write formulas, and generate outputs through whitelisted MCP tools with audit trails and backups.

Lets agents declare what data they need by concept plus entity (e.g. "price.close of Moutai"), then resolves those concepts to physical columns, ranks candidate sources, and fetches with failover. Over 70 tools also cover catalog and binding management, entity identity and graph, semantic and AI search, crawl policy and platform control, coverage reporting, schedules, authenticated-login pools, and governed observation reads.

Enables k-anonymization of tabular data through generalization and suppression, with utility reporting and an MCP interface for field classification and anonymization. Runs entirely in-process with no network access.

Enables AI agents to discover official public data sources, inspect their metadata and endpoint parameters, and execute live queries through a unified response envelope with a 500 ms budget.

Enables local offline machine learning workflows, including CSV profiling and cleaning, classifier and neural network training, hyperparameter optimization, evaluation metrics, confusion matrix plots, Streamlit dashboards, and HTML reports through MCP tools.

Enables an AI client to track a watch list of contacts and retrieve only what changed since the last run — departures, new employers, replacements, and new hires after a role closed — each row carrying match evidence, source dates, and ready-to-use outreach payloads. It runs the analysis on Apify using the caller's own provider keys, supports stored or caller-held state, and can push results to a signed webhook.

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。

Give your AI agent the entire China A-share market: 55 datasets of prices, financials, capital flows, corporate events and futures/options, stored locally and queryable with read-only SQL. Built point-in-time with delisted stocks kept, so backtests don't lie — no account, no API key.

Superhuman data-driven science. Allows agents to upload any tabular dataset, specify a target column, and get validated predictive patterns (with p-values, effect sizes, and context from literature) that surface feature interactions and subgroup effects you'd otherwise miss. Many discoveries already made, free for open data!

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 assistants to read and modify Power BI Desktop files programmatically, including querying models, creating measures, and managing relationships through natural language.

A lightweight, powerful, and flexible workflow engine that executes tasks defined in YAML configuration files.

The world's first dual-engine Airtable MCP server: programmatic control of both Airtable REST/Metadata APIs and Interface Designer (Dashboards, Kanbans, Column Edit Locks, and Publishing) via Chrome CDP.

MCP server for DTS Engine 6.1 that enables agents to create, validate, and run 3D digital-twin tile publishing pipelines from shapefiles, photogrammetry, DEM/DOM, BIM, and point clouds, with tools for pipeline introspection, error resolution, and OSGB publishing.

An MCP server that enables AI assistants to interact with Tenzir, a data pipeline engine for security operations, including executing pipeline queries, managing OCSF schemas, and generating parsers.

Autonomous cross-source inconsistency and contradiction intelligence engine for AI agents. Detects specification drift, SemVer conflicts, and infrastructure mismatches across code, docs, and deployments.

Enables AI agents to work with a real Excel-compatible spreadsheet engine, allowing them to create and manipulate structured data blocks, write and evaluate formulas, and save genuine .xlsx files with live formulas for human verification and reuse.

A privacy-first MCP server that searches, normalizes, and deduplicates job listings across multiple providers, enabling trustworthy discovery without scoring or applying.

Enables AI agents to protect, unprotect, and search sensitive data using Kustodyan's contextual transform engine with role-based access controls.

An MCP server for the Octopus Energy Japan GraphQL API that allows users to retrieve electricity consumption, cost estimates, and contract details. It enables 30-minute interval usage analysis and postal code area searches while ensuring privacy by excluding personal address information.

An MCP server that enables LLMs to detect and anonymize over 25 types of Personally Identifiable Information (PII) using Microsoft Presidio. It supports various redaction strategies and can process both plain text and structured data to help ensure data privacy.

A Model Context Protocol server that enables large language models to access database metadata and perform cross-engine data querying across diverse database ecosystems.

A minimal MCP server that provides a persistent DuckDB SQL engine to AI assistants, enabling natural-language querying of CSVs, Parquet, and cloud data with 12 tools and optional read-only mode.

Enables auditing of .xlsx workbooks locally and read-only, flagging formula errors, broken references, inconsistent formulas, typed-over values and other risks through both static checks and an independent Python recalculation engine, with tools to run a full audit or inspect a single cell.

Enables AI assistants to interact seamlessly with IBM watsonx.data lakehouses using natural language for operations like querying, catalog browsing, engine management, and data ingestion.

Enables harnesses to record supplied GUI actions, inspect trajectory statistics, and export privacy-filtered datasets through MCP tools without executing device actions.

Declarative BIM and Building-as-Code engine for AI agents: model buildings in YAML, compute deterministic QTO and cost estimations, compile to IFC4, and view interactive 3D WebGL models.

Enables AI assistants to perform financial reconciliation with a deterministic proof engine: intake files, match transactions, verify proofs, resolve exceptions, and sign off on balanced journals under the user's authority.

A comprehensive MCP server that turns any AI assistant into a powerful mathematical computation engine, providing 52 advanced functions, 158 unit conversions, financial calculations, and secure AST-based evaluation.

Read-only MCP server for FP&A & management reporting — governed metrics, financial statements and drill-down over a SQL semantic layer. Your own financials on your own warehouse, not market data. Open core of Précis. (metric engine · ClickHouse · OIDC · Docker)