Borrowing it
Nothing to install: this file belongs to sandraschi/observability-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sandraschi/observability-mcp/master/.cursor/skills/mcp-server-developer/SKILL.mdgit clone --depth 1 https://github.com/sandraschi/observability-mcpWrote 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/sandraschi/observability-mcp/mcp-server-developer)<a href="https://agentmods.dev/skills/sandraschi/observability-mcp/mcp-server-developer"><img src="https://agentmods.dev/badge/skills/sandraschi/observability-mcp/mcp-server-developer/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/sandraschi/observability-mcp/mcp-server-developer"><img src="https://agentmods.dev/badge/skills/sandraschi/observability-mcp/mcp-server-developer.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 | $0.00040 | $0.03116 |
| Opus 5.5 | $0.00016 | $0.01246 |
| Sonnet 5.5 | $0.00008 | $0.00623 |
| Haiku 4.5 | $0.00004 | $0.00312 |
Grade A, and why
mcp-server-architect 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 1mo 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.
This is a copy
100% identical to mcp-server-architect — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 434 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Server Architect
Overview
Master the complete MCP server development lifecycle with FastMCP 2.14.3, covering architecture design, implementation best practices, ecosystem integration, and production deployment across Claude Desktop, Cursor, Windsurf, and all agentic IDEs.
When to Use This Skill
Activate for:
- Designing MCP server architecture and tool organization
- Implementing FastMCP 2.14.3 features (sampling, cooperative patterns)
- Following Anthropic MCP standards and best practices
- Integrating with MCPB packaging and distribution
- Publishing to Glama.ai, LobeHub, and MCP marketplaces
- Supporting multiple IDEs (Claude, Cursor, Windsurf, Zed)
- Troubleshooting MCP server deployment and compatibility
Core Capabilities
🏗️ Architecture & Design
- FastMCP 2.14.3 Architecture: Latest framework features and patterns
- Tool Design Patterns: Portmanteau tools, cooperative patterns, sampling workflows
- Security & Reliability: Error handling, authentication, rate limiting
- Performance Optimization: Async patterns, connection pooling, caching
🛠️ Development Workflow
- MCPB Packaging: Build, distribution, and installation standards
- IDE Integration: Claude Desktop, Cursor, Windsurf, Zed compatibility
- Testing Strategies: Unit tests, integration tests, MCP protocol testing
- Debugging Tools: MCP Inspector, logging, error diagnostics
🌐 Ecosystem Integration
- Marketplace Publishing: Glama.ai, LobeHub, skillsmp.com submission
- Community Standards: Following established MCP patterns and conventions
- Cross-Platform Support: Windows, macOS, Linux deployment
- Version Management: Semantic versioning, backward compatibility
📊 Production Operations
- Monitoring & Observability: Health checks, metrics, logging
- Scaling Strategies: Connection handling, resource management
- Update Mechanisms: Auto-updates, migration strategies
- Support & Maintenance: User feedback, bug fixes, feature requests
What ships with it
14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- _toc.md 807 B
- modules/ai-ide-development.md 3.4 KB
- modules/architecture-and-standards.md 5.0 KB
- modules/core-guidance.md 23 KB
- modules/development-workflow.md 3.6 KB
- modules/distribution-and-installation.md 5.2 KB
- modules/ecosystem-and-publishing.md 2.8 KB
- modules/innovation-playbook.md 3.2 KB
- modules/known-gaps.md 830 B
- modules/mcp-history-and-outlook.md 5.3 KB
- modules/minimal-mcp-server.md 7.1 KB
- modules/release-readiness.md 2.7 KB
- modules/research-checklist.md 11 KB
- modules/tooling-strategy.md 3.4 KB
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.
- 1mo ago First seen · 434 lines · 40 tokens per session scan A cfcf152fc92f
mcp-server-architect is a skill published in the GitHub repository sandraschi/observability-mcp (1 stars, last pushed 8d ago), licensed MIT. It adds 40 tokens to every session and 3,116 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to mcp-server-architect, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
clawmetry-selfcheck
Read your own agent telemetry from ClawMetry (waste, progress, cost) and act on it before finishing a task. Use when ClawMetry is installed on this machine and you want to check whether you are re-reading files, spinning in loops, or burning budget.
clawmetry
Real-time observability for OpenClaw agents — local dashboard + optional encrypted cloud sync. Tracks costs, tokens, sessions, tool calls, memory, crons, and system health. Access from anywhere via ClawMetry Cloud.
agent-kill-switch
Give the human an off switch and a cost meter for the coding agents on this machine, using ClawMetry. Use when the user asks to stop or kill a runaway agent, see what an agent is doing or spending, cap agent spend, gate risky tool calls behind approval, or "set up a kill switch" for Claude Code, Codex, Cursor, Gemini…
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
dd-code-generation
Use pup CLI for immediate Datadog operations or generate code for integration into applications.