"Servers Offering MCP Prompts as Prompt Primitives" matching MCP servers:

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.

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

CTX is a tool made to solve a big problem when chatting with LLMs like ChatGPT or Claude: giving them enough context about your project.

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

An MCP server that demonstrates the Model Context Protocol using a mock SQLite database of an online store, offering tools for product search, sales analysis, and reviews, along with resources and prompts for learning MCP integration.

Enables AI assistants to interact with Coda docs, pages, tables, rows, formulas, and more via the Coda API, offering 54 tools, 12 resources, and 5 prompts for comprehensive document management.

Enables AI agents to manage plain .jsonl files as tables, offering tools to list libraries and tables, query data, and upsert rows while preserving byte-for-byte fidelity on unchanged rows.

Enables AI applications to integrate with Tableau through developer primitives including tools, resources and prompts. Supports querying data from datasources, exploring content like workbooks and views, and retrieving visualizations using the Tableau REST API.

MCP server offering tools to add numbers and fetch GitHub repos, a resource for apartment rules, and a prompt to explain SQL queries.

Enables LLMs to interact with small business data systems through tools for document processing, data queries, and report generation, using MCP primitives for structured context.

Enables natural-language querying of a SQLite database through a locally served, fine-tuned text-to-SQL model exposed as an MCP tool, offering fast and cost-free SQL generation and execution.

Enables LLM-based agents and MCP-compatible clients to query and manipulate FHIR-compliant clinical data using natural-language prompts, offering full CRUD operations on FHIR resources, semantic document search, RAG pipelines, and LOINC terminology lookup.

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.

SchemaBrain is an MCP server that sits between AI agents (Claude, Cursor, Windsurf) and your SQL database as a read-only trust + intelligence layer. The agent never writes SQL — 12 tools compile it from definitions you control, PII and secret categories are refused before the query runs, and every call lands in a tamper-evident (SHA-256-chained) audit log. Postgres today.

Enables secure interaction with MySQL databases through MCP, offering tools for SQL queries, schema inspection, and data sampling, with support for multiple databases, SSH tunnels, and safe write operations.

Read-only SQL Server tool that recovers deleted and changed rows from the transaction log (fn_dblog) when there is no backup, Audit or CDC. Undo SQL is returned as text and never executed.

An MCP server that exposes a dbt project's run state as tools, enabling AI assistants to answer questions like 'is the warehouse healthy?' or 'what broke and why?' via plain English, using read-only access to dbt artifacts and warehouse data.

Enables MCP clients such as GitHub Copilot, Codex, Claude... to explore a SQL Server 2017+ database read-only: databases, schemas, tables, views, procedures, functions, indexes and dependency graphs, plus filtered, grouped, sampled and paginated queries capped by row limits.

Guardrail proxy for AI agents on SQL Server. Each statement runs as the caller's own login, a T-SQL parser blocks dangerous statements, and every statement is audited. Local stdio mode or a central Docker service.

Gives an AI agent a database's tables, columns, value lists, null shares and joins from a dbprint snapshot committed to your repo, with no database connection or credentials. Tools list and search tables and columns, render prompt-ready context for a table, resolve a filter value to its stored spelling, and report what changed since the last snapshot.

An MCP server that lets an LLM query a DuckDB warehouse of EuroLeague and EuroCup basketball data in natural language, offering tools for player and team stats, shot charts, boxscores, and fantasy draft analysis without contacting upstream APIs.

MCP server that exposes the Timetta OData API as a universal query gateway, allowing users to list, describe, and query OData entities through natural language.

Enables full-text search of macOS iMessages including link preview metadata. Works as an MCP server for Claude Desktop to search your messages locally.

An MCP server for Oracle that won't get you fired... This MCP server does not expose a SQL prompt, and can't tell you how to log into Oracle. Only the selected objects and SQL statements are usable.

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.

MCP server enabling text-to-SQL on PostgreSQL databases using a CrewAI multi-agent system. It generates and executes read-only SQL queries from natural language, with security layers against prompt injection.

Enables read-only querying of Moodle as a student, including courses, assignments, grades, forums, and files, using a personal web services token.

Enables estimating a BigQuery query's cost before running it, using a free dry run to report bytes processed and the estimated on-demand USD charge. It also flags common sources of wasted spend, such as SELECT * and missing partition filters on partitioned tables.

Enables an AI assistant to read form structures and submissions from a Coletum account (read-only) and to produce Excel/CSV exports, Coletum-style or user-template PDFs, and photographic reports on request. It also stores preferences such as logo and company name and reports where each generated file was saved.

Developers are constantly feeding context files to AI tools like Cursor, Windsurf, Copilot Workspace, and Claude Code. If your agent doesn't understand your real database schema, it writes code that fails in production. LintBase acts as the bridge. It connects directly to your database, reads the ground truth of your live documents, and generates structured context optimized for AI. 🤖 Stops AI