"How to check differences between files" matching MCP servers:

Read-only Supabase RLS check: explains in Arabic which tables anyone can read or change. No keys.

Runs SQL statements in memory against real PostgreSQL 18 and SQLite 3.49 engines after loading your schema and sample rows, returning each statement's own verdict: errors with line, column, and hints, constraint violations, or the resulting rows. It also compares both dialects to expose portability differences, all with no database server, network, or API key.

Enables AI coding agents to audit Supabase or Postgres databases for Row Level Security and multi-tenant isolation holes, reading tables, grants, policies and functions for static findings and optionally probing those policies inside a rolled-back transaction. It reports each hole with an explanation and a fix, so an agent can verify the migrations it just wrote before declaring them done.

Read-only Supabase Row Level Security review. Analyzes an exported catalog query (no keys needed) for RLS turned off, policies that are just true, anon-callable SECURITY DEFINER functions, views exposing auth.users, public Storage buckets and more, and explains each rule.

Enables AI assistants to query PostgreSQL, MySQL, SQL Server, Oracle, and MongoDB databases through MCP with read-only, audited access.

Turns any OData V2 or V4 service, SAP Gateway included, into MCP tools that AI clients such as Claude, ChatGPT, Copilot, and Cursor can call without code by reading $metadata. It lets models discover entity sets and fields, then query services through built-in read-only tools.

Enables discovery of Fabric/Power BI workspaces and semantic models, execution of DAX queries, and generation of executive HTML reports with visualizations.

MCP server that translates natural-language questions into SQL, validates every query structurally, and executes approved read-only queries against a SQLite database, returning results and rejections.

Enables Claude to translate natural-language business questions into safe, read-only SQL queries by exposing tools for listing tables, inspecting schemas, and executing row-capped SELECT statements against PostgreSQL.

A secure database query service built on FastMCP framework that allows users to query MySQL databases using natural language, with comprehensive permission management and security controls.

MCP server enabling natural-language querying of SQLite databases via schema discovery, GraphRAG retrieval, and safely guarded read-only SQL execution.

Transforms SAP S/4HANA or ECC systems into conversational AI interfaces by exposing all OData services as dynamic MCP tools. Enables natural language interactions with ERP data including querying, creating, updating, and deleting entities through SAP BTP integration.

This read-only MCP Server allows you to connect to CSV Files data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out our MCP Server for CSV Files (https://www.cdata.com/drivers/csv/download/mcp).

Transforms SAP S/4HANA or ECC systems into conversational AI interfaces by exposing all OData services as dynamic MCP tools. Enables natural language interactions with ERP data for querying, creating, updating, and deleting business entities through SAP BTP integration.

Enables natural-language querying of a mock legacy healthcare database and returns validated FHIR resources (Patient, Observation, Condition).

AI-powered expense tracking MCP server that connects LLM clients to PostgreSQL for natural language expense management.

Exposes any SQLite database as read-only MCP tools for AI assistants, enabling listing tables, describing schemas, and running SELECT queries with filtering, ordering, and pagination.

Translates plain English questions about infrastructure operations into SQL queries, executes them against a database, and returns the real answer.

Transforms SAP S/4HANA or ECC systems into conversational AI interfaces by exposing OData services as dynamic MCP tools. Enables natural language interactions with ERP data for querying, creating, updating, and deleting business entities.

Enables MCP clients such as Claude Desktop or Cursor to inspect a coffee-shop sales database schema, validate SQL, and run guarded read-only queries. It supports natural-language questions by exposing tools for schema description, SQL checking, and safe query execution.

An open-source MCP server that imports HR CSV data into an in-memory SQLite database for structured querying and metadata retrieval. It enables users to perform read-only SQL queries and structured searches on employee data through natural language.

Enables Claude to list Iceberg tables and run read-only DuckDB SQL queries, including time travel by snapshot, with per-caller token authentication and audit logging.

Enables secure, read-only querying of Google BigQuery datasets through a stateless MCP server with OAuth 2.1 authorization, designed for integration with Atlassian Rovo.

Enables users to inspect database schemas, validate SQL syntax, and execute queries against PostgreSQL and Apache Hive through standardized Model Context Protocol tools for safe query generation and validation.

Enables natural language querying of Apache Iceberg lakehouse by exposing typed tools for namespace discovery, table metadata inspection, snapshot history, time travel SQL generation, and partition pruning explanation.

Enables natural-language querying and authenticated CRUD operations against SAP S/4HANA or ECC OData services through dynamic MCP tools with progressive service and entity discovery.

Enables secure SQL query execution on MySQL databases with authentication and permission control, allowing users to explore database tables and run read-only queries.

Enables Claude Desktop to connect to PostgreSQL databases, allowing users to query, explore schemas, and analyze data using plain English without writing SQL.

MCP server that enables Google ADK agents to triage solar fault signals, retrieve Salesforce diagnostics via hosted MCP prompt templates, and create WorkOrder records when replacements are needed.

Enables Claude Desktop to interact with PostgreSQL databases through natural language for schema exploration, data analysis, and query execution. Users can search schemas, describe tables, and perform read or write operations without needing to write manual SQL.

Captures checkpoints of project files and SQLite tables before an AI agent makes risky changes, then reports differences and rolls them back byte-for-byte, including dropped tables and agent-created junk. Enables agents to snapshot, diff, list, and restore working state with explicit confirmation required before any destructive action.

Enables coding agents to determine whether Postgres/Supabase migration files were truly applied by parsing each migration and comparing every object it should create against the live pg_catalog. It also surfaces discrepancies between repository files and the recorded migration history, all through read-only tools.

Lets Claude or any MCP client query a Neo4j index of a markdown vault, answering what is connected to a note and how far, how two notes relate, which notes are orphans or dangling links, and running read-only Cypher.

Enables agents to query imported dated CSV/JSON exports to cross-check values across sources, trace observations to raw files, and surface anomalies such as missing fields, disappeared records, and collection gaps before concluding.

Enables AI agents to query and compare paint-contracting quotations and estimates, explaining price differences by materials, labor, or profit, summarizing projects, searching work items, and running read-only SQL against the Postgres data.

Self-healing MCP server that monitors database schema changes, detects differences, and automatically updates ontology mappings using AI to ensure agents continue working without manual intervention.

Enables teams to structure metric definitions, compare semantic differences, detect JOIN fanout and drift, reconcile mismatched numbers layer by layer, and persist metric contracts as YAML.

An MCP server that provides targeted PostgreSQL schema access to AI agents, retrieving only relevant tables for a question and enforcing read-only access through multiple layers.

A read-only DuckDB MCP server offering context-efficient analytics tools (list_datasets, describe_table, profile_column, explain, query) with a semantic layer for business rules, security guards, and disclosed truncation to help LLMs produce correct answers while minimizing token usage.

An MCP server that provides a USDA-accurate food database with deterministic macro math, enabling tools like list_foods, get_food, calculate_macros, filter_by_diet, build_meal, and list_available_tags. It allows Claude to look up nutrition facts and solve for exact macro targets offline, without AI or network.