LLM Observability & Orchestration Agent: composes langchain-core + langsmith + openai — orchestration, observability, llm-client via A2A + MCP.

Free AI prompt API with 185 expert role contexts and 1,741 prompt templates across 24 professional domains. No auth required. Works with any AI agent.

PromptDNA A community marketplace for composable AI prompt blocks — think npm for prompt engineering. PromptDNA lets developers and AI agents discover, compose, fork, and contribute reusable prompt "blocks" — personas, task templates, constraints, reasoning chains, and output-format specifications that combine to build complete, battle-tested prompts. Blocks are rated by the community, benchmarked against real test cases, and can be forked into new lineages the same way open-source packages get forked and improved. Website: https://promptdna.org MCP endpoint: https://mcp.promptdna.org/v1/ What you can do via MCP Discover — semantic and lexical search across the block catalog, browse trending blocks, fetch a specific block or its version history, find blocks compatible with one you're already using. Compose — assemble a complete prompt from multiple blocks in one call. Contribute — submit new blocks, fork existing ones into your own variant, r

Turn any AI assistant into an expert prompt engineer. Ultra Prompt gives your AI a library of 1,000+ professionally written prompts for real, everyday work, writing, marketing, business, creative, coding, and more. Just describe what you're trying to do, and it finds the right template, fills in the details, and hands back a polished, ready-to-run prompt, expert-quality results without wasting time writing the best prompt yourself. It can also chain templates into multi-step workflows and save them to reuse. Tools: searchtemplates · gettemplate · buildprompt · suggestvocab · recommendnext · listenhancements · buildpipeline (Pro) · saveplaybook (Pro) Free key: ultraprompt.co → Account → MCP Server. Free: 5 calls/mo · Pro: unlimited.

PromptRefiner is a premium micro-service from the M2MCent factory, configured as a Model Context Protocol (MCP) server. Functionality: Generative prompt optimizer for Midjourney, Sora, and DALL-E. Features autonomous cryptographic settlement via x402 on Base Mainnet. Fee: $0.02 USDC per execution.

IA-QA as an MCP Server Use IA-QA's developer tools to test your llm agents RAG ai tools, directly from Cursor, Claude Desktop, Windsurf, or any AI agent without leaving your IDE. Many classical testing tools too ! Enjoy ! No API key. No signup. Free.

Transform basic instructions into high-quality prompts with optimized structure and clear constraints. Evaluate existing prompts for clarity and specificity while receiving actionable improvement suggestions. Access a library of production-ready templates and convert formats to streamline development workflows.

LangSmith Traced OpenAI Agent: composes langchain-core + langchain-openai + langsmith + openai — orchestration, observability, llm-client via A2A + MCP.

Prompt infrastructure for AI agents—resolve, compose, and manage reusable prompts and briefs through OAuth-secured MCP tools.

Prompt injection detection and PII scanning for AI agents. Analyze any input before sending it to an LLM — returns a CLEARED/BLOCKED verdict, matched injection signatures, detected PII entities (SSN, IBAN, email, passport...), and a SHA-256 signed audit report. 2,000 free requests/month, no credit card required.

Generate PDFs from HTML templates via AI agents or API. List templates, submit jobs with JSON data, check credits, and generate watermarked previews — all through MCP tools. Templates support LiquidJS templating with conditionals, loops, and raw variable injection.

Prompt improver for people who never know what to type into AI. Rewrites a rough request (Thai or English) into a sharp prompt structured as Role, Task, Context, Format. Hosted server, free tier included: 5 credits/day, no sign-up. Tools: improveprompt, buildprompt. Website: https://rtcf.happlen.com

Reduce LLM API costs via semantic caching, prompt compression, model routing and context pruning. Zero code changes required.

PQS is the fastest way to get better output from any AI model. Score any prompt before it hits the model. Get a grade (A-F), score out of 80, percentile, and dimension breakdown across 8 quality dimensions. Built on PEEM, RAGAS, MT-Bench, G-Eval, and ROUGE frameworks. Pre-flight, not post-hoc. The AI input quality problem is real. PQS solves it. MCP Tools: scoreprompt: Free. Returns grade (A-F), score out of 80, percentile, and full 8-dimension breakdown. No API key needed. optimizeprompt: $0.025 USDC. Returns a rewritten, higher-scoring version of your prompt with before/after dimension deltas. HTTP API (x402-native on Base): /api/score/free: Free. Grade, percentile, and 8-dimension breakdown. No payment required. /api/score: $0.025 USDC. Single score, pay-per-call. /api/score/full: $0.125 USDC. Grade, percentile, dimension breakdown, and rewrite. /api/score/batch: $0.25 USDC. Score multiple prompts in a single call. /api/preflight: $0.05 USDC. Lightweight pre-flig

Promethic is a prompt library: store versioned prompts where you set the model, switch models, and dial API-only settings (reasoning, verbosity, and other dials). Text, image, and JSON. Edit the output as you work; it tracks those edits and successful copy/download. Refine proposes the next version. Available as a Mac and Windows desktop app, iOS, web, and MCP tools. Standard $10/mo includes $10 at-cost across Grok, Claude, ChatGPT, and Gemini; BYOK for local storage. Hosted MCP: https://mcp.getpromethic.com/v1

Lint and generate AI agent context files (CLAUDE.md, AGENTS.md, Cursor rules, Copilot instructions) from any MCP client. The linter is free, needs no account, and applies ~30 research-backed rules; generation uses a PromptArch API key.

Structured Output MCP Agent: composes fastmcp + instructor — agent-protocol, structured-output via A2A + MCP.

One workspace for your prompts, documents, and collections — accessible from every AI client you use. Context Repo is an AI context management platform for capturing, organizing, versioning, and searching the knowledge artifacts you use with AI tools. This MCP server exposes 28 tools that give Claude, Cursor, ChatGPT, Factory, Windsurf, Codex, Claude Code, and any other MCP-compatible client direct read-and-write access to your personal workspace — no copy-paste, no context loss between conversations. Features Prompts — Full CRUD with version history, rollback, and semantic search across your prompt library Documents — Markdown and plain-text storage with automatic chunking and 1536-dim vector embeddings Collections — Named folders that group prompts and documents into project-scoped contexts Catalog Search — find_items returns ranked results across prompts, documents, and collections in a single call (semantic by default, literal fallback) **Dee

Production-ready prompt injection detection for AI agents. Scan user input, retrieved docs, and tool outputs before passing them to an LLM. Returns injectiondetected, score, attacktype, and sanitized text.

Generate optimized prompts for over 140 platforms using Prompeteer's Contextual AI platform. Manage and organize your creations within a personal vault for easy retrieval and storage. Evaluate prompt quality across multiple dimensions to ensure high-performance results.

reportflow-mcp

An MCP (Model Context Protocol) server that turns your ReportFlow templates into PDF reports — invoices, contracts, statements, anything you've designed — straight from Claude or any other MCP-compatible AI agent. What it does Generate PDFs from natural-language requests like "create an invoice for Acme Corp totalling $300" Expose your ReportFlow designs and their parameter schemas directly to the AI as MCP Resources Bulk-generate many PDFs and download them as a single ZIP Save outputs to whichever workspace folder the user is currently in (Claude Desktop / Claude Code / Cursor / VS Code all supported) Setup Claude Desktop / Claude Code / Cursor Add the following to your config file (.mcp.json, claudedesktopconfig.json, ~/.cursor/mcp.json, etc.): { "mcpServers": { "reportflow": { "command": "npx", "args": ["-y", "reportflow-mcp"] } } } That's the whole setup. No env vars, no API keys, no secrets to manage. VS Code (MCP-enabled builds) Same JSON in .vs