MCP Servers Directory — Page 644

KYB API: company registry data from 27 countries, insolvency notices and sanctions screening

GEO platform: track brand visibility, citations, sources and measurement verdicts across AI answers.

Evidence-backed follow-through memory for what you owe, await, and need to remember.

Prometheus MCP server for AI agents: PromQL queries, alert explanations, series discovery.

Hungarian VAT, payroll, KATA/flat-rate tax, late interest, workdays and website legal checks.

Music promo platform: email campaigns, Instagram DMs, Spotify discovery, SmartLinks, analytics.

Headless MCP: author and render PromoShot .promo video projects (stills, GIFs, video).

Search your private marketing email archive and organize collections with optional write access.

Contextual prompts and agent skills for 140+ AI platforms.

A framework for defining, managing, and applying prompt decorators to enhance interactions with LLMs

Generate app icons, favicons, OG images, and logos by routing across 30+ image models.

Local MCP server that optimizes rough prompt drafts using a local Ollama model

Decorator-based integration testing for LLM prompts

Read Promptafire's AI-for-marketers lessons and blog. Optional sign-in unlocks Pro lessons.

Search and use 300,000+ AI prompts and skills for images, video, writing, games, apps and websites.

Search published AI prompt products on PromptBase.art: titles, prices, ratings, URLs.

MCP server for Notion prompts database

Free AI test helpers: injection inputs, OWASP mapping, release plans, response and tool-call packs.

Local-first MCP server for versioning, searching, evaluating, and improving AI prompts.

Token-budget-aware text handling: count, truncate, and chunk for LLM prompts.

MCP server for Prompt Builder — search, retrieve, and compile prompt components from a community vault using semantic search (pgvector) and

prompt-character-mcp-server is an MCP server on MCP.so — view details, tools, and install instructions.

Decision-only prompt routing and firewall checks for local/cloud routing, PII and jailbreak risk.

Community library of composable AI prompt blocks for search, composition, and contribution.

Stdio MCP server for PromptEden projects, monitors, answers, and analytics.

Connect the Prompteneering library of expert AI agents directly to your editor or chat.

A server for the prompt engineer MCP

This Model Context Protocol (MCP) server provides a tool to rewrite coding prompts for optimal results with Cursor AI and other AI IDEs, using Claude by Anthropic.

一个功能完备的AI提示词管理MCP服务器，支持Secret-Key认证、提示词管理、公共广场访问等功能。

Send a one-off fax from inside ChatGPT or Claude. Pay-per-use, $2-$4.50 per delivered fax.

Free Companies House deadline checks for UK companies: due dates, penalties, dormancy signals.

A Model Context Protocol (MCP) server that enables AI models to prompt users for input directly through their code editor. This creates an

Find a tested AI image or video prompt — toy, LEGO, plushie, portrait, poster — and render it.

A lightweight MCP (Model Context Protocol) server for Garak.

Transform simple questions into comprehensive, context-aware prompts using advanced prompt engineering techniques fetched from PromptGen API and your local code context.

Scan prompts for injection attacks, redact PII, and audit LLM SDK usage from any MCP client

Scans untrusted web pages, emails, or tool outputs for prompt injections and returns sanitized tex

PromptGuard Scan MCP is a paid remote Model Context Protocol server for LLM security testing. It helps teams inspect AI apps for prompt injection, jailbreaks, hidden instruction leakage, unsafe…

Remote MCP for prompt injection scans, jailbreak checks, leakage review, and LLM release gates.

result = refine_prompt("Write a technical blog post", skip_questions=True) print(result["refined_prompt"]) ```

Your agent thinks Midjourney still uses --v 5. It doesn't — that flag was dropped at v7. It assumes DALL-E 3 and FLUX Schnell cost the same. They differ by ~50×. It confidently writes [Verse] tags…

Scans RAG content/scraped pages for indirect prompt injection

Prompt injection is the 1 security risk for LLM applications. aco-prompt-shield catches known jailbreak patterns, understands semantic intent via ML, and detects obfuscation — all locally, all…

PromptLab is a free, lightweight, open-source experimentation tool for Gen AI applications.

Prompt optimization loops and regression test suites for Claude Code, with a companion web UI.

Prompt optimization loops and regression test suites for Claude Code, with a companion web UI.

Catches leaked credentials and PII in outbound LLM prompts

Your PromptLikeEngineer prompt library as MCP tools, slash prompts and resources. Add-only saves.

Static linter for AI prompts: contradictions, redundancy, ambiguity, and fluff.

A single-file Model Context Protocol (MCP) server for Amazon Q Developer CLI that manages prompt files (.md) from local directories.

MCP Server for managing LLM prompts

A powerful Model Context Protocol (MCP) server for managing, organizing, and reusing prompt templates with variable substitution and multi-message conversation structures.

Manage, version, and publish LLM prompts with blocks, variables, and evaluations.

Generate images, video, and audio directly in Claude Code, Cursor, Windsurf, or any MCP-compatible AI agent.

Scan prompts, tool definitions and model output for injection, and guard agent tool calls.

Status: Unstable and only for PromptQL v1. Alpha release coming soon for PromptQL v2.

Convert PDF/CSV to Markdown with AI-powered OCR via the PromptReady cloud API.

Generative prompt optimizer for Midjourney, Sora, and DALL-E.

A Model Context Protocol server for managing prompts via stdio.

Security gateway for AI agents: detects prompt injections, jailbreaks, and common vulnerabilities.