"Understanding the concept of 'handle' in different contexts" matching MCP servers:

Exposes a governed dbt MetricFlow semantic layer to AI agents through three tools — list metrics, list dimensions and query metrics — so questions about federal contract spend are answered from defined metrics rather than raw tables. Guardrails reject undefined metrics, raw columns, SQL in filters and bulk exports, and no tool can execute SQL.

Enables AI agents to discover and query data federated across MySQL/MariaDB, PostgreSQL, ClickHouse, S3 and Kafka with SQL, exposing tools to list databases, schemas, tables and connections, describe columns, search objects, inspect table statistics, run EXPLAIN, and execute arbitrary statements. It runs locally over stdio against a PostgreSQL-wire endpoint and returns structured results or SQLSTATE-coded errors.

MCP server for configuring the konsol Frappe app via the CLI. Enables AI clients to manage dimensions, measures, fact tables, connectors, and schemas using natural language.

MCP server that archives Decent DE1 espresso shots from Visualizer.coffee into SQLite and provides analysis tools for shots, beans, and profiles via MCP.

Enables AI agents to inspect schemas, walk Delta table history, run read-only DuckDB queries, and check data-quality and job-run status safely.

Enables AI agents to inspect, query, test, and safely fix dbt projects and BigQuery warehouses under policy-enforced controls, with read-only direct queries and dbt-only allowlisted writes.

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.

Enables looking up mobile phone numbers for a list of contacts by chaining your own Prospeo, Lusha, ContactOut, and FullEnrich keys until a provider returns a number. Returns one row per contact with the number in E.164 format, line type, country, a Do Not Call flag where reported, and the provider credits spent.

Read-only SQL across PostgreSQL, MySQL, S3-compatible buckets and folders of Parquet, CSV and JSON files — and one query can join across all of them, federated in-process by DuckDB. Sources are given as connection strings at startup, and no tool writes: they are absent rather than disabled.

A portfolio analysis MCP server that enables AI agents to manage investment portfolios, fetch financial data from Yahoo Finance and CoinGecko, and perform advanced analysis like weight optimization and Monte Carlo simulations. It utilizes reference-based caching to efficiently handle large datasets without bloating the LLM's context window.

Creates compact skeleton representations of large JSON files by preserving structure while truncating string values and deduplicating arrays, helping users understand JSON structure without processing the full data payload.

Enables AI assistants to upload clinical documents and medical device images for health data extraction, normalization, and retrieval of structured coded results in formats such as JSON, FHIR, HL7, CSV, and Parquet.

An MCP server that allows users to interact with YNAB data, enabling access to account balances, transactions, and the creation of new transactions through the Model Context Protocol.

MCP server for Sophtron financial data aggregation that allows clients to search banks, connect accounts, handle MFA, and retrieve accounts, balances, and transactions.

Enables AI agents and their users to ask business questions in plain language and receive governed metric values, breakdowns, share-of-total figures, and the exact parameterized SQL behind them, drawn from a single semantic model rather than ad-hoc SQL. It also lets clients inspect available metrics and their definitions, and preview optimized queries without executing them.

Read-only-by-default MCP server for Datanika, an open-source dlt + dbt-core data pipeline platform: browse connections, introspect and preview source tables, compile and run dbt transformations, and monitor pipeline runs. 25 tools (17 read-only, plus 8 write tools gated behind --allow-write); source lives in the datanika-mcp/ subdirectory of the repo.

Enables comprehensive CSV file management including creating, editing, analyzing, and transforming CSV data anywhere in the filesystem. Provides statistical analysis, data validation, filtering, and grouping capabilities through MCP protocol over stdio transport.

Enables read-only access to market data and analytics through one vendor-neutral schema, with Alpaca built in and other providers pluggable. Large results are kept out of the model's context in a local DuckDB store the model queries with read-only SQL, and common analytics such as returns, volatility, correlation, drawdown and beta are computed on those stored results.

Enables intelligent property data analysis through the Rentcast API with optimized API call allocation. Provides comprehensive real estate market insights, property valuations, rental estimates, and listings data with built-in rate limiting and fallback mechanisms.

A server that provides tools and utilities to support the implementation of Jij Modeling, featuring easy configuration and an extensible architecture for custom modeling workflows.

Enables structured document understanding of local PDFs via a dual-extract MCP server, combining MinerU text/layout and Qwen3-VL vision with fusion adjudication for field extraction, tables, formulas, and validation. Fully local and offline.

Enables MCP clients to discover processor and controller service types, build and wire Apache NiFi 2.x process groups, schedule them, and debug queues and bulletins through the NiFi REST API. Supports flow spec application, automatic canvas layout, parameter contexts, and an optional read-only mode that blocks all writes.

A Model Context Protocol (MCP) server that provides tools for reading Excel (xlsx) files, enabling extraction of data from entire workbooks or specific sheets with results returned in structured JSON format.

Exposes SAP BW/4HANA ADT operations as MCP tools for LLM clients, with a local-file buffering layer to handle large XML payloads and table data efficiently.

Enables natural language management of Apache Airflow workflows, including DAG monitoring, task control, and configuration, via the Model Context Protocol.

Enables high-precision detection, anonymization, encryption and decryption of personally identifiable information (PII) in text using GPT-4o-based detection and advanced cryptographic methods. Supports both deterministic encryption for searchable data and format-preserving encryption for structured identifiers.

Connects MCP clients to databases like Snowflake, BigQuery, and Databricks through Alkemi's data platform, enabling natural language database queries with proper schema understanding and metadata management for consistent team-wide access.

Connects MCP clients such as Claude Desktop and Claude Code to Opteryx so users can ask questions about their data in plain English, discovering datasets, reading schemas, running queries, profiling columns, and validating SQL. Every call runs as the token's own user and against only the data that user can see.

Enables an AI agent to verify a single email address in real time, clean an entire uploaded list file with per-address verdicts, and download the results as CSV with the addresses that are safe to send to. It runs on npm with zero dependencies and includes built-in credit reporting and spending limits so agents cannot overspend without approval.

Let LLMs analyze sensitive data safely by querying a tokenized, join-preserving copy of the database, with fail-closed PII scanning and provable numeric equivalence.