"An introduction to prompt engineering" matching MCP servers:

MCP server for managing and serving dynamic prompt templates using elegant and powerful text template engine. Create reusable, logic-driven prompts with variables, partials, and conditionals that can be served to any compatible MCP client like Claude Code, Claude Desktop, Gemini CLI, etc.

An MCP front-end for AnB. The tool surface is "use-don't-reveal": no tool returns a plaintext secret. Reveal paths require a TTY the server doesn't have, so the no-reveal guarantee is structural, not prompt-based — it holds even against a prompt-injected agent. Runs as a dedicated, narrowly-scoped AnB identity; exec is default-deny (only allowlist rules tagged scope=mcp run); command output

Security proxy that wraps any MCP server with bidirectional scanning for credential leaks, prompt injection, and tool description poisoning. Also provides an HTTP fetch proxy with a 9-layer scanner pipeline for capability-separated agent deployments.

Description: Introduce Beelzebub, an MCP‑based honeypot framework that enables creating decoy tools to detect prompt injection and malicious agent behavior. Motivation: Strengthen the security of LLM workflows by adding a non‑intrusive detection mechanism.

Enables Claude to interact with WhatsApp: read chats, search messages, send messages with a mandatory confirmation step, and transcribe voice notes locally, all with encrypted storage and prompt-injection scrubbing.

Zero-dependency local proxy that wraps any MCP server to redact secrets, strip hidden-Unicode prompt injection, and block writes to protected paths like ~/.ssh and .env.

Enforces structured, evidence-guided software engineering tasks with cognitive actions (investigate, plan, verify, remember) and persistent state for LLM-based coding agents.

A self-hosted MCP server that retrieves git-backed engineering experience records (issues, fixes) to inform LLM coding agents, preventing repeated mistakes with a relevance floor.

A memory, docs, and repo context layer for engineering agents, providing typed persistent memory, RAG document retrieval, and repository-aware tools to recall decisions, runbooks, and operational knowledge across sessions.

Use Nano Banana Pro to generate image from text prompt and edit image

Enables coding agents to interact with Frida for reverse engineering: connect to local, USB, and remote devices; inspect apps and processes; manage sessions; and load, evaluate, and exchange messages with JavaScript instrumentation scripts, including fetching community scripts from Frida CodeShare.

Enables ChatGPT on Windows to securely access codebases, Git, terminals, language servers, debuggers, SQLite, local HTTP services, adaptive project memory, engineering skills, checkpoints, audit logs, and sandboxed command execution through MCP tools.

An MCP server for Android's Tasker automation app

An MCP server for prompt and RAG evaluation workflows, enabling users to register, create API keys, and run evaluations via Claude Desktop, Cursor, or other MCP clients, with a hosted backend for heavy evaluation work.

Haft is an MCP server that enforces engineering discipline for AI-assisted software delivery, providing tools for problem framing, decision contracts, and commission-based execution harnesses.

An MCP server for querying Grafana Loki directly with a discovery-first workflow — labels, values, series, and LogQL queries without requiring Grafana.

ContextLattice is an HTTP-first, MCP-compatible memory/context/task orchestrator that persists writes and returns fused recall from specialized stores with local-first defaults. Primary URL: https://contextlattice.io/ Install: https://contextlattice.io/installation.html Troubleshooting: https://contextlattice.io/troubleshooting.html

Fetches documents by URL, DOI, ISBN, PMID or PMCID, and reports a block as a block, never as an empty success.

Records your terminal sessions per command (PTY + OSC 133) into local SQLite, so AI agents can search, retrieve, and diff what commands actually printed. Secret redaction is applied by default to everything served over MCP.

Your agents, briefed. Not flooded. Self-hosted context compiler: git-backed team knowledge served to coding agents as token-budgeted bundles over MCP.