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

A Model Context Protocol server for managing prompt templates as markdown files with YAML frontmatter, allowing users and LLMs to easily add, retrieve, and manage prompts.

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.

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.

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

MCP server for managing tasks with a resource to read all tasks, a tool to add tasks, and a prompt to analyze tasks, using stdio transport.

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.

Lightweight MCP server for providing user prompts defined in Markdown with argument support.

Enables querying normalized real-world asset data through MCP tools, including listing assets, retrieving asset details, comparing yields against SOFR, and checking eligibility by jurisdiction.

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

Enables MCP-compatible agents to retrieve Chinese expert documents, prompt examples, and task skeletons before writing Chinese prompts.

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.

Enables Codex to delegate review and implementation tasks to the local Qoder CN CLI as background jobs, with two permission tiers and polling-based status updates.

Exposes the local Claude Code CLI as a subagent for Codex, enabling background review and implementation jobs with two fixed permission tiers.

Turns a prompt-engineering workflow into a workbench: it suggests candidate prompts with live sample replies, gives them LangGPT structure, rewrites them over multiple rounds, and proves the result against test cases with promptfoo-style assertions, model graders and DSPy-style train/dev search. Runs on any OpenAI-compatible provider using your own API key.

Local MCP server that uses a local Ollama model to rewrite rough prompt drafts into structured, optimized prompts for paid APIs, saving tokens and improving output quality.

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

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.

Bridges a remote, cloud-hosted agent to your local machine, exposing Pi's coding tools (read, write, edit, ls, grep, find, bash, powershell) rooted at a directory you choose. It also adds a human channel so the agent can message, question, and wait on you through tool calls instead of a platform chat UI, with OAuth 2.1 or bearer-token authorization and no persistence between runs.

The control plane for AI prompts that scores, enforces policy, locks config, and audits every prompt decision.

Maps shell commands to standard MCP tools using single-file YAML specs.

Enables AI models like Claude to manage local prompt files with CRUD operations, fuzzy search, categorization, templates, version control, and favorites.

An MCP server that registers customizable prompt templates as tools for natural language interaction. It supports hot-reloading and easy extension via YAML or JSON files to automate tasks like code review, refactoring, and content summarization.

MCP server for managing AI prompts with CRUD operations, categorization, and tagging. Enables users to store, organize, and retrieve their favorite prompts efficiently.

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

Enables security researchers to evaluate AI system defenses against prompt injection attacks through a comprehensive set of test vectors and analysis tools.

A Model Context Protocol server that saves prompts with timestamps and allows users to list previously saved prompts for Claude Desktop.

Provides custom prompts for Amazon Q by serving markdown files from the local filesystem as prompt templates through the Model Context Protocol.

A validation layer for AI coding assistants that enforces explicit LLM evaluations on plans, code diffs, and tests to ensure safer and higher-quality code.