"Understanding Prompts or Prompt Engineering" matching MCP servers:

Enables AI clients to investigate data engineering workflows by exposing tools for job status, logs, schema lookup, read-only SQL, and searching documentation/incidents, along with resources and prompts for ETL failure analysis.

A local-only MCP server that uses SQLite to store, search, and manage a personal library of AI prompts. It enables developers to organize and reuse prompts across multiple AI clients like Claude and Cursor while keeping all data on their local machine.

A public MCP server demonstrating how an AI agent can retrieve database schemas and manage local OpenAPI contracts via tools for CRUD operations.

Enables LLMs to query real job data and summarize backend job failures using MCP tools backed by a SQLite database.

Enables AI agents to inspect a mock data platform locally via SQLite, using read-only tools for schemas, row counts, freshness, queries, and pipeline status without cloud credentials.

MCP server for snowflake that doesn't allow write operations under any circumstances, and includes a system prompt.

Enables natural language interaction with a GeoServer instance for managing workspaces, datastores, feature types, layers, styles, and OGC services (WMS/WFS) via an LLM-powered agent.

Provides an MCP-native operational interface for diagnostics, explainability, regression checks, and operational memory on data-system internals like PostgreSQL and Databricks toy engines.

An MCP server that enables listing and querying Trino tables using Python, providing access to data resources through the Model-Control-Protocol.

Enables LLMs to access corporate project and employee workload data via MCP, offering read-only tools, resources, and prompts, and highlighting prompt injection risks.

MISP (Malware Information Sharing Platform) MCP server with built-in prompt injection defense via prompt-defense-audit

Provides sub-millisecond access to organizational and engineering data by pre-materializing data into a read-only SQLite database. Enables agents to query people, teams, issues, features, and governance documents without upstream latency or auth.

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.

Read-only MCP server for Grafana Loki: lets AI agents (Claude Code, Cursor, Copilot) discover labels, read bounded LogQL pages, count lines by label or time, and export logs — across several Loki stands

IBAN validation across 89 countries, BIC/SWIFT and Swiss clearing lookup, batch validation, payment-reference, postal-address and Swiss QR-bill checks for AI agents. Connect via MCP or the REST API. Includes free quotas, paid credits and a Pro subscription. SEPA and country-risk indicators support payment-data checks; they do not confirm account ownership or replace beneficiary AML/KYC screening.

A read-only MCP server that reports BI pipeline readiness, blockers, and the next allowed action for governed Power BI workflows. It never writes files, executes warehouse work, or grants human approvals.

Enables natural language querying of SQL databases by allowing the agent to explore schema, write SQL, and self-correct errors. It integrates with MCP-compatible assistants like Claude Desktop or Cursor.

A cooperative guardrail for AI agents that blocks destructive shell commands, SQL statements, or cloud operations until a human approves them out-of-band, with a tamper-evident local ledger.

Enables read-only SQL queries and schema inspection for legacy MySQL 5.0–5.6 deployments using SHOW-based metadata tools, without write operations or modern authentication support.

Enables an LLM to read and write NetBox data through its REST API, supporting listing endpoints, inspecting schemas, and creating, updating, or deleting objects.