Design high-quality MCP servers with progressive discovery, context compression, and token-efficient responses. Includes patterns for multi-tool MCPs, the info tool pattern, cross-tool IDs, and automation-friendly JSON formats.
MCP server design agent that helps architects and developers design complex multi-tool MCP servers with progressive discovery, token efficiency, and best practice patterns. Provides autonomous multi-step design assistance.
MCP testing and fuzzing specialist that validates server robustness, tests edge cases, generates comprehensive test reports, and ensures MCP servers handle invalid inputs gracefully.
MCP tool design specialist focused on individual tool schemas, response optimization, context compression, and human/LLM readable outputs with automation flags and progressive detail patterns.
This skill should be used when the user asks about "error messages", "did you mean", "similar tools", "parameter suggestions", "schema hints", "MCP error handling", "guide the client", "helpful errors", "fuzzy matching", or discusses how MCP servers should guide clients with progressive error enhancement and corrective feedback.
This skill should be used when the user asks about "token efficiency", "compress responses", "reduce token usage", "minimize context", "compact format", "token optimization", or discusses reducing token consumption in MCP responses while maintaining value.
This skill should be used when the user asks to "organize MCP tools", "structure multi-tool MCP", "design MCP architecture", "group MCP tools", "organize 10+ tools", or discusses how to architect complex MCP servers with many tools. Provides patterns for organizing, naming, and structuring multi-tool MCP servers.
This skill should be used when the user asks for "MCP examples", "real-world patterns", "code search patterns", "browser proxy patterns", "process management patterns", "show me examples", or wants to see actual implementations from lci, agnt, or other real MCPs.
This skill should be used when the user asks to "implement info tool", "create discovery tool", "progressive disclosure", "help system", "enumerate MCP capabilities", "info tool pattern", or discusses how users discover what an MCP server can do. Provides the info tool pattern for progressive capability discovery.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
AI coding agent toolkit - browser superpowers, code intelligence, and development tools.
This marketplace contains 13 plugins for Claude Code:
| Plugin | Description | Version | Category |
|---|---|---|---|
| agnt | Browser superpowers: process management, reverse proxy, frontend debugging, sketch mode | 0.7.12 | development |
| lci | Lightning Code Index: sub-millisecond semantic code search | 0.4.0 | development |
| tools | Complete toolkit combining agnt and lci | 1.0.0 | development |
| mcp-architect | Design high-quality MCP servers with progressive discovery and token efficiency | 0.1.0 | development |
| mcp-tester | MCP server testing and debugging with mcp-debug | 0.2.0 | development |
| slop-mcp | SLOP integration for MCP management and orchestration | 0.2.0 | development |
| slop-coder | SLOP language coding assistant and reference | 0.1.0 | development |
| dartai | Dart task management with adversarial cooperation loops | 0.3.0 | development |
| workflow | General-purpose adversarial workflow automation | 0.1.0 | development |
| figma-query | Token-efficient Figma integration with design library extraction | 0.1.0 | design |
| ux-design | UX design principles, color theory, typography, and accessibility | 0.1.0 | design |
| ux-developer | UX-driven development with WCAG 2.2 and usability best practices | 0.1.0 | development |
| prompt-engineer | State-of-the-art prompt and context engineering for 2026 | 0.1.0 | ai |
# Via npm (recommended)
npm install -g @standardbeagle/agnt @standardbeagle/lci
# Via pip
pip install agnt lightning-code-index
# Via Go (lci only)
go install github.com/standardbeagle/lci/cmd/lci@latest
Option A: Via slop-mcp (recommended if available)
mcp__plugin_slop-mcp_slop-mcp__manage_mcps
{ "action": "register", "name": "agnt", "command": "npx", "args": ["-y", "@standardbeagle/agnt", "mcp"], "scope": "user" }
{ "action": "register", "name": "lci", "command": "npx", "args": ["-y", "@standardbeagle/lci", "mcp"], "scope": "user" }
Option B: Add to .mcp.json
{
"agnt": {
"command": "npx",
"args": ["-y", "@standardbeagle/agnt", "mcp"]
},
"lci": {
"command": "npx",
"args": ["-y", "@standardbeagle/lci", "mcp"]
}
}
The plugins provide commands, skills, and agents that help you use the MCP tools:
# Install the complete toolkit (recommended)
claude plugin add tools@standardbeagle-tools
# Or install individual plugins
claude plugin add agnt@standardbeagle-tools
claude plugin add lci@standardbeagle-tools
Give your AI coding agent browser superpowers:
__devtool API)Requirements: agnt binary via npm/pip or GitHub releases
Sub-millisecond semantic code search and code intelligence:
Requirements: lci binary via npm/pip/go or GitHub releases
Best of both worlds - combines agnt and lci for the ultimate AI coding experience.
Requirements: Both agnt and lci binaries
standardbeagle-tools/
├── .claude-plugin/
│ └── marketplace.json # Marketplace registry
├── plugins/
│ ├── agnt/ # Browser superpowers plugin
│ │ ├── .claude-plugin/
│ │ ├── commands/
│ │ ├── skills/
│ │ ├── agents/
│ │ └── mcp.json.disabled
│ ├── lci/ # Code intelligence plugin
│ │ ├── .claude-plugin/
│ │ ├── commands/
│ │ ├── skills/
│ │ └── mcp.json.disabled
│ └── tools/ # Combined plugin
│ ├── .claude-plugin/
│ ├── commands/
│ ├── agents/
│ └── mcp.json.disabled
└── README.md
npx claudepluginhub standardbeagle/standardbeagle-tools --plugin mcp-architectDart task management with adversarial cooperation loops and full dart-query MCP schema parity - DartQL batch operations, advanced filtering, task relationships, documents, time tracking, and automated task execution through quality verification pipelines.
MCP server testing and debugging toolkit. Dynamic server management, traffic analysis, schema validation, and hot-swap development workflows.
SLOP MCP integration for dynamic MCP server management. Migrate existing configs, register servers at runtime, search and execute tools across servers, automate workflows with SLOP scripts, and orchestrate multi-server pipelines. Includes Dart MCP tool reference skills.
Prompt and context engineering toolkit. Includes DSPy-inspired optimization, Claude patterns, context engineering, chain-of-thought design, RAG prompting, and multi-agent orchestration techniques.
General-purpose adversarial workflow automation with Ralph Wiggum loops. Context-aware task execution with clean subagent isolation, multi-stage verification, hook-based iteration tracking, and intelligent memory preservation before context compaction. Inspired by Goose Ralph loops and g3 principles.
Manage MCP servers - discover, analyze, execute tools/prompts/resources. Use for MCP integrations, capability discovery, tool filtering, programmatic execution, or encountering context bloat, server configuration, tool execution errors.
MCP server development helper with tool and resource scaffolding
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools.
Build FastMCP 3.x Python MCP servers — covers provider/transform architecture (including CodeMode, Tool Search, and server-level transforms), component versioning, session state, authorization (MultiAuth, PropelAuth, connection-pooled token verifiers), evaluation creation, Pydantic validation, async patterns, STDIO and HTTP transports, nginx reverse proxy deployment, background tasks, Prefab Apps UI, security patterns, client SDK usage, testing, deployment, and migration from FastMCP v2. TypeScript is a legacy reference only and is not updated for v3.
MCP servers for Codex integration
Model Context Protocol Mcp Expert subagent