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

MCP server providing 26 visual tools for text-only LLMs, enabling description, coordinate location, OCR, annotation, cropping/zooming, anomaly scanning, and computer control with switchable VLM backends.

A tutorial demonstrating how to build reusable, parameterized MCP prompt templates using FastMCP, including patterns for research, summarization, and code review.

Enables users to manage, search, render, version, and regression-test local Markdown templates with typed variables, and to expose them as MCP tools and native prompts without requiring a model API, account, or cloud service.

Enables searching, inspecting, auditing, and composing AI video prompts using 150 verified prompts that were each rendered into real Seedance 2 videos.

Automatically extracts actionable methodologies from articles and URLs, stores them in a vector database, and retrieves relevant methods to enhance user prompts for more effective AI interactions.

A simple MCP server for utilizing prompts defined in YAML files.

MCP server providing on-demand access to official prompting guides for building robust meta-prompts.

Provides a local MCP interface to query captured, PII-scrubbed prompt telemetry from coding agents and browser chats, enabling time summaries, prompt search, and activity analysis without data leaving the machine.

Run DeepSeek as a real sub-agent inside Claude Code / Codex CLI — not just a single LLM call. DeepSeek gets its own 7-tool agent loop (Read/Write/Edit/Bash/Glob/Grep/NotebookEdit) inside a sandboxed workspace.

Deterministic SNAP eligibility logic, exposed as auditable Model Context Protocol tools. An AI agent can read, reason, and orchestrate, but the eligibility determination itself is made by versioned, tested, cited code that a caseworker, an auditor, or a court can inspect.

Transforms rough or follow-up prompts into self-contained, model-ready prompts by profiling the task and conversation, applying research-backed techniques, and returning citations, assumptions, and clarifying questions.

Delegates work from MCP clients (like Claude Code) to the Codex CLI, allowing spawning of autonomous Codex subagents for tasks.

Provides a SQLite-backed MCP server that records agent memory as history, enabling explicit consolidation, source checks, revisions, narrative versions, and accountable forgetting.

Exposes product-style completion tools (OpenAI chat-completions-shaped and Anthropic messages-shaped) that are fulfilled by sampling the host agent's own LLM over MCP, so no model API keys are ever needed. Also offers a model listing endpoint aliasing the host's model.

Enables dynamic prompt management by automatically discovering and serving markdown prompt files with YAML frontmatter via the Model Context Protocol.

A Model Context Protocol server that generates prompts based on Git repository content, including a command to generate PR descriptions from diffs.

A lightweight MCP server that provides a unified interface to various LLM providers including OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama.

An MCP server that allows agents to test and compare LLM prompts across OpenAI and Anthropic models, supporting single tests, side-by-side comparisons, and multi-turn conversations.

Smart AI workflow for Cursor teams with intelligent prompt routing, real-time cost optimization, and team analytics.

Enables management and invocation of AWS Bedrock managed prompts with support for variable substitution, streaming responses, batch processing, and multiple AI models including Claude, Titan, Llama, and Mistral.

This MCP server provides research-backed prompt optimization tools and professional domain templates designed to improve AI performance through strategies like Tree of Thoughts and Medprompt. It enables users to analyze, auto-optimize, and refine prompts using advanced reasoning patterns and safety-critical alignment techniques.

Enables dispatching entire autonomous multi-agent engineering swarms directly from IDEs like Cursor and Windsurf via a single MCP endpoint, with streaming progress updates and verified git diffs returned to the editor.

A deterministic prompt optimization middleware for AI coding agents that preserves intent, compresses context, and detects drift, available as an MCP server with tools for optimize_prompt, classify_prompt, and more.

Enables querying a modular RAG knowledge base via MCP, with hybrid retrieval, reranking, and document summary tools.

MCP server exposing prompt-shield's prompt-injection firewall for LLM applications. Four tools — scan_input, scan_output, scan_tool_result (with optional sanitization), and list_detectors — backed by 34+ detectors and a federated ed25519-signed threat feed.

Retrieval-grounded prompt refinement engine that repairs and polishes prompts via a single LLM call, exposing a refine_prompt tool for integration with MCP-compatible hosts.

A standalone MCP server that enforces clean prompt structure, strips model‑invented instructions, and detects capability hallucinations before they propagate through your system.

Converts REST APIs into MCP tools using Gradio, demonstrated with a local IBM Granite model via Ollama. Enables LLM clients to interact with any REST API endpoint through the MCP protocol.

Fetches web pages and converts them to clean, readable markdown format by extracting main content while removing navigation, ads, and other non-essential elements to minimize token usage.

Provides real-time and scheduled bus information for Montevideo's public transport system.