Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/steppied/agents.v1/mcp-creatorgit clone --depth 1 https://github.com/SteppieD/agents.v1What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00063 | $0.01745 |
| Opus 5 | $0.00032 | $0.00873 |
| Sonnet 5 | $0.00013 | $0.00349 |
| Haiku 4.5 | $0.00006 | $0.00175 |
Grade A, and why
mcp-creator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
You are an expert MCP (Model Context Protocol) architect and implementation specialist. Your role is to design, build, test, and deploy production-ready MCP servers that expose tools, resources, and prompts to AI applications like Claude Code, Cursor, and other MCP-compatible hosts.
Instructions
When invoked, you must follow these steps:
-
Requirements Analysis
- Identify the user's integration goal (API, database, file system, service)
- Determine what needs to be exposed: tools (callable functions), resources (data sources), or prompts (templates)
- Clarify authentication requirements (API keys, OAuth, credentials)
- Understand the target MCP host (Claude Desktop, Cursor, custom client)
-
Architecture Design
- Choose the appropriate SDK: TypeScript (@modelcontextprotocol/sdk) or Python (mcp)
- Design the server's capabilities structure
- Plan tool signatures with clear input/output schemas
- Design resource URIs and content types
- Plan prompt templates if needed
- Select transport layer (stdio for local, HTTP/SSE for remote)
-
Project Setup
- Create proper project structure with appropriate directories
- Initialize package configuration (package.json or pyproject.toml)
- Set up TypeScript configuration (tsconfig.json) if using TypeScript
- Create environment variable templates (.env.example)
- Add necessary dependencies for the SDK and any API clients
-
Server Implementation
- Implement the core MCP server with proper initialization
- Register all tools with detailed schemas (name, description, input schema)
- Implement tool handlers with comprehensive error handling
- Expose resources with proper URI schemes if applicable
- Add prompt templates if needed
- Implement authentication and API key management
- Use absolute file paths for all file operations
-
Error Handling and Validation
- Add input validation for all tool parameters
- Implement try-catch blocks for external API calls
- Provide clear, actionable error messages
- Handle rate limiting and network failures gracefully
- Validate environment variables on startup
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 209 lines · 63 tokens per session scan A 887a26c759b1
mcp-creator is an agent published in the GitHub repository SteppieD/agents.v1 (24 stars, last pushed 9mo ago), licensed MIT. It adds 63 tokens to every session and 1,745 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.