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

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

Enables hot-reloadable prompt templates with structured reasoning frameworks, quality gates, and multi-step chain workflows that can be version-controlled and executed immediately without restarts.

Self-hosted prompt library with an MCP server: list, fetch, save and version prompt templates with {{variables}} from ChatGPT or any MCP client, with OAuth sign-in. Also available as a hosted service on neadlab.com.

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.

Provides agents with real Linux VMs to run commands, manage files, expose ports, and track costs, all through an ephemeral sandbox service.

Enables LLM application builders and security teams to detect and strip prompt injections, scan for secrets, obfuscate PII, and audit synthetic datasets for bias using deterministic tools.

Stateful interactive HTTP REPL and Agentic MCP engine for API navigation and testing.

WAF for AI agents — block prompt injection before it reaches the LLM.

Enables agents to scan untrusted text for jailbreak markers, prompt-override exploits, and indirect injection payloads, then cleanse it by replacing hostile command sequences with safe placeholders before the text reaches a prompt. Exposes tools for sanitizing input and itemizing detected threat patterns.

Cross-chain cryptocurrency swaps via Chainflip. Get quotes, execute swaps, and track progress. No API key required to get started.

This MCP server enables clients to reduce oversized prompts by selecting task-relevant context, removing lexical duplicates, and pruning to a token budget while preserving critical system invariants.

Enables clients to optimize prompt prefix caching by matching longest common token prefixes with a radix trie, eliminating redundant prefill computation and reducing time-to-first-token.

Compresses multi-turn conversation history by stripping verbose boilerplate and filler tokens while preserving critical tool parameters and named entities, deterministically cutting inference costs by 40-60%. Runs as a zero-dependency Python MCP server or importable module, compatible with Claude Desktop, Cursor, and other MCP runtimes.

Enables deterministic detection and neutralization of adversarial prompt injections and override attempts in AI agent workflows via a zero-dependency MCP server, providing structured telemetry and low-latency validation.

Enables MCP clients and autonomous agents to screen incoming prompts for system overrides, delimiter breakouts, and encoded payload evasion, helping block prompt injection and jailbreak attempts before execution.

Enables autonomous agents and MCP-compatible clients to route inputs through a deterministic firewall that flags and sanitizes prompt injection, jailbreaks, system prompt exfiltration, and tool hijacking. It supports JSON-RPC stdio integration for tools like Claude Desktop, Cursor, and multi-agent frameworks.

Analyzes, refines, and optimizes prompts for AI assistants by fixing grammar, improving clarity, applying best practices like chain-of-thought and few-shot learning, and scoring prompt quality across multiple dimensions.

Enables running deterministic multi-model prompt regression and golden dataset benchmark suites, exposing structured results and telemetry through the Model Context Protocol for integration with MCP-compliant clients.

Provides tools to retrieve the GodPrompt universal system prompt and its components (core skill, protocols, gates, anti-patterns) for AI software development, plus task classification. Designed for progressive context usage.

Enables developers to repair malformed JSON, synthesize ReDoS-safe regexes, compile XML system prompts, enforce JSON Schema, verify context compaction, audit hallucinations, and sanitize CSV/JSON data through a scoped streamable-http endpoint.

Connects AI assistants to Beamtrace's remote MCP for read-only visibility insights, offering tools to retrieve visibility scores, topic rollups, prompt metrics, competitor leaderboards, and content improvement suggestions.

Art-directed website prompts delivered as slash commands in Claude Code, Claude Desktop and Cursor: hero sections, landing pages, SaaS, portfolio, e-commerce and 3D/WebGL scenes. Each build is registered as a real MCP prompt and written natively for the tool you are in (Lovable, Bolt, Cursor or Claude), with a live demo you can scroll before spending a token.

Enables searching and retrieving prompts from the NerdyChefs.ai prompt library, including pack listings and random prompt selection.

Enables converting Markdown and HTML tables into structured JSON records with automatic column type inference and format normalization. It also offers supporting web-agent primitives such as DOM semantic pruning, form field auto-mapping, and execution trajectory evaluation, all via a zero-dependency MCP server.

Plugged.in MCP Server acts as a proxy server that combines multiple MCP servers into a single interface. It retrieves tool, prompt, and resource configurations from Plugged.in and directs requests for tools, prompts, and resources to the appropriate underlying server.

MCP server that enforces single-use human confirmations for sensitive tool calls, sanitizes prompts against prompt injection, and re-validates file paths before destructive actions.

Provides Arabic UI/UX design tools as an MCP server, offering RTL conversion, Arabic typography validation, cultural palettes, and anti-AI-slop auditing for AI-assisted design workflows.

MCP server for the QxBin Prompt Generator that uses binary probability matrices to collapse optimal prompts from a library of prompt atoms.

Run free live audience Q&A and polls from your agent: start an AskOne room, add and launch a poll, approve or hide questions and mark them answered, close the room, then read the questions as a FAQ draft and get the results. Free AI moderation. Uses an organization API token from askone.org

Enables AI clients to transcribe YouTube links and uploaded audio or video files, then retrieve the resulting transcripts as text, SRT, VTT, or JSON with timestamps and optional speaker labels. Also supports paging through long transcripts, checking upload progress, listing or deleting jobs, and viewing remaining account minutes.