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 skills add ashish7802/awesome-api-skills --skill anthropic-mcpgit clone --depth 1 https://github.com/ashish7802/awesome-api-skillsWrote 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/ashish7802/awesome-api-skills/anthropic-mcp)<a href="https://agentmods.dev/skills/ashish7802/awesome-api-skills/anthropic-mcp"><img src="https://agentmods.dev/badge/skills/ashish7802/awesome-api-skills/anthropic-mcp/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/ashish7802/awesome-api-skills/anthropic-mcp"><img src="https://agentmods.dev/badge/skills/ashish7802/awesome-api-skills/anthropic-mcp.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 | $0.00000 | $0.00322 |
| Opus 5.5 | $0.00000 | $0.00129 |
| Sonnet 5.5 | $0.00000 | $0.00064 |
| Haiku 4.5 | $0.00000 | $0.00032 |
Grade A, and why
anthropic-mcp 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 yesterday.
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.
What it actually says
Model Context Protocol (MCP) Skill
Overview
The Model Context Protocol (@modelcontextprotocol/sdk) standardizes how AI applications and coding agents connect to external data sources, tools, and prompt templates over stdio or HTTP SSE/Streamable transports.
Installation
npm install @modelcontextprotocol/sdk zod
Core Concepts
McpServer: High-level server coordinator for registering tools, resources, and prompts.StdioServerTransport: Standard input/output JSON-RPC transport used by Claude Desktop, Claude Code, and Cursor.server.tool(): Registers an executable tool with a Zod input schema.
AI Pitfalls
- Corrupting
stdiowithconsole.log(): When usingStdioServerTransport,process.stdoutcarries JSON-RPC 2.0 messages. Callingconsole.log()breaks the protocol parser. Always useconsole.error()for logging. - Unstructured Tool Errors: Catch errors inside tool handlers and return
{ content: [{ type: "text", text: err.message }], isError: true }so the LLM can self-correct.
Production Checklist
- Zero
console.logcalls instdioserver path (console.erroronly) - Tool schemas validated with
zodraw shape objects - Graceful shutdown on
SIGINT/SIGTERM
Last Verified: 2026-10-21
What ships with it
2 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.
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.
- yesterday First seen · 27 lines · 0 tokens per session scan A 9f65eb8380a2
anthropic-mcp is a skill published in the GitHub repository ashish7802/awesome-api-skills (13 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 322 tokens. 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 2026-10-22.
Other skills, from other repositories
switch
Switch current session to codex. UltraContext keeps your original context.
iii-sandbox
Ephemeral microVM sandboxes for running untrusted or agent-generated code in isolation — a one-call run path, a create/exec/stop lifecycle, and a set of filesystem operations.
iii-error-handling
Handle iii engine and SDK errors across Node, Python, Rust, and browser workers. Use when interpreting error codes, retryability, RBAC denial, timeouts, handler failures, or SDK-specific exception surfaces.
composio
Build AI agents and apps with Composio - access 200+ external tools with Tool Router or direct execution.
heygen-cli
Create AI videos, manage avatars, translate videos, and download results via the HeyGen API. Use when an agent needs to generate videos from text prompts, create avatar-based videos, translate existing videos, or automate video production workflows.
claude-api-cost-optimization
Save 50-90% on Claude API costs with Batch API, Prompt Caching & Extended Thinking. Official techniques, verified.