Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Notysoty/openagentskillsnpx agentmods add skills/notysoty/openagentskills/mcp-integration-assistantWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/notysoty/openagentskills/mcp-integration-assistant)<a href="https://agentmods.dev/skills/notysoty/openagentskills/mcp-integration-assistant"><img src="https://agentmods.dev/badge/skills/notysoty/openagentskills/mcp-integration-assistant/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/notysoty/openagentskills/mcp-integration-assistant"><img src="https://agentmods.dev/badge/skills/notysoty/openagentskills/mcp-integration-assistant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00023 | $0.02428 |
| Opus 5 | $0.00012 | $0.01214 |
| Sonnet 5 | $0.00005 | $0.00486 |
| Haiku 4.5 | $0.00002 | $0.00243 |
Grade A, and why
MCP Integration Assistant 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 9d 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 — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Integration Assistant
What this skill does
This skill guides the design and implementation of a Model Context Protocol (MCP) server that exposes an external system, API, or data source as tools, resources, or prompts for AI agents. It designs the tool schema, writes the server handler code, generates the client configuration snippet, and explains how to test the integration. The output is a working MCP server ready for use with Claude Desktop, Claude Code, Cline, or any MCP-compatible agent.
Use this when you want to give an AI agent access to a new system — a database, an internal API, a third-party service, a file system, or any data source — through the standard MCP protocol.
How to use
Claude Code / Cline
Copy this file to .agents/skills/mcp-integration-assistant/SKILL.md in your project root.
Then describe what you want to expose and ask:
- "Use the MCP Integration Assistant skill to build an MCP server for our Postgres database."
- "Design an MCP integration for the GitHub API using the MCP Integration Assistant skill."
Describe the external system, what operations the agent should be able to perform, and any auth requirements.
Cursor
Add the "Prompt / Instructions" section to your .cursorrules file. Describe the system you want to expose and ask Cursor to design the MCP server.
Codex
Describe the target system and the operations you want to expose, then include the instructions below. Provide any relevant API docs or existing SDK code.
The Prompt / Instructions for the Agent
When asked to design an MCP integration, follow these steps:
- Understand the target system. Ask for or infer:
- What external system, API, or data source needs to be exposed
- What operations should the agent be able to perform (read, write, search, execute, etc.)
- Authentication method (API key, OAuth, none, environment variable)
- Any existing SDK or client library available
- Programming language preference (TypeScript/Node.js is the primary MCP SDK language)
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.
- 9d ago First seen · 256 lines · 23 tokens per session scan A bd772dad66cb
MCP Integration Assistant is a skill published in the GitHub repository Notysoty/openagentskills (9 stars, last pushed 26d ago), licensed MIT. It adds 23 tokens to every session and 2,428 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
convex-agents
Building AI agents with the Convex Agent component including thread management, tool integration, streaming responses, RAG patterns, and workflow orchestration.
api-documentation
Use when API code changes (routes, endpoints, schemas). Enforces Swagger/OpenAPI sync. Pauses work if documentation has drifted, triggering documentation-audit skill.
architecture-patterns
Implement proven backend architecture patterns including Clean Architecture, Hexagonal Architecture, and Domain-Driven Design. Use this skill when designing clean architecture for a new microservice, when refactoring a monolith to use bounded contexts, when implementing hexagonal or onion architecture patterns, or…
event-store-design
Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.
cqrs-implementation
Implement Command Query Responsibility Segregation for scalable architectures. Use when separating read and write models, optimizing query performance, or building event-sourced systems.
workflow-orchestration-patterns
Design durable workflows with Temporal for distributed systems. Covers workflow vs activity separation, saga patterns, state management, and determinism constraints. Use when building long-running processes, distributed transactions, or microservice orchestration.