Detects hidden prompt injection in tool descriptions: file read, exfiltration, instruction override, system prompt extraction, social engineering. Returns findings with pattern and severity.
MIT
342,025 tools. Last updated 2026-07-30 11:44
"Enhancing Prompt Engineering with MCP" matching MCP tools:
- Retrieve prompt templates for common engineering reasoning workflows, enabling structured step-by-step problem solving without external LLM calls.Apache 2.0
- Discover available prompt engineering techniques with acceptance statistics to enhance AI interactions through optimized method selection.MIT
- Improve prompt quality by applying optimal engineering techniques like chain-of-thought reasoning based on intent analysis.MIT
- Transforms user requests into optimized prompts using advanced prompt engineering techniques like chain-of-thought and role-based prompting.MIT
- Provide answers to clarifying questions to continue prompt engineering for Claude Code, enabling interactive refinement of optimized prompts.MIT
Matching MCP Servers
- AlicenseAqualityBmaintenanceAn MCP server that gives an AI assistant a set of real mechanical-engineering tools. Provides deterministic tools like material properties, beam analysis, unit conversion, and curve fitting for engineering calculations.Last updated5MIT
- AlicenseAqualityBmaintenanceEnables AI agents to generate, view, and analyze engineering diagrams (RF, PCB, EMC) in draw.io using natural language prompts, with auto-layout and 269 engineering stencils.Last updated108AGPL 3.0
Matching MCP Connectors
27 engineering compliance and calculation tools for the built environment (UK, EU, UAE).
Ground your AI with deterministic mechanical engineering tools. Prevent hallucinations in dynamics, thermal fluids, and solid mechanics via strict validation.
- Describe an engineering challenge to find guides with matching answers and action items.MIT
- Inspect runtime state of executed Prompt Director nodes: final prompt, model context, edit plan, and warnings. Use with graph inspection for workflow audit.MIT
- Records engineering-task dispatches with a full audit trail. Use when delegating parallelizable work to a subagent, capturing intent, assignee, and constraints.MIT
- Analyze a system prompt for context engineering issues and get top findings ranked by severity. Use for reviewing, improving, or debugging AI agent prompts.MIT
- Analyzes prompt template versions against labeled examples and customer feedback to generate improved versions, with optional automated testing.Apache 2.0
- Analyze a Git repository for 14 security vulnerability classes, including prompt injection and secret exposure, before running it as an MCP server.MIT
- Submit feature requests, report documentation gaps, or escalate issues to the engineering team through a direct email.ISC
- Search open bounties for paid engineering work across software, hardware, MCP servers, CAD, EDA. Filter by category, status, and payout to discover tasks matching your capabilities.MIT
- Find available calculators and engineering models on MetaModel, returning project names, descriptions, tokens, and model names.MIT
- Send a prompt to Claude via the local CLI, enabling cross-validation of AI outputs from other backends or use when the MCP client is not Claude.Apache 2.0
- Fetch a specific prompt version by tag name, returning the template, model configuration, and invocation parameters.Apache 2.0
- Retrieve a workflow's flow steps and their complete prompt stacks, including step IDs, names, and ordered user/system prompt snippets, to discover flowStepIds and view prompt composition.MIT
- Lists Engineering Change Notices (ECNs) in a project, with optional filters by severity, status, and type.Apache 2.0
- Retrieve a specific prompt version by its ID, including its template, model configuration, and invocation parameters.Apache 2.0