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 tenequm/skills --skill mcp-best-practicesgit clone --depth 1 https://github.com/tenequm/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/tenequm/skills/mcp-best-practices)<a href="https://agentmods.dev/skills/tenequm/skills/mcp-best-practices"><img src="https://agentmods.dev/badge/skills/tenequm/skills/mcp-best-practices/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/tenequm/skills/mcp-best-practices"><img src="https://agentmods.dev/badge/skills/tenequm/skills/mcp-best-practices.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00060 | $0.08219 |
| Opus 5 | $0.00030 | $0.04110 |
| Sonnet 5 | $0.00012 | $0.01644 |
| Haiku 4.5 | $0.00006 | $0.00822 |
Grade B, and why
mcp-best-practices scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
- **v1.30.0 stamps every tool schema `"$schema": "http://json-schema.org/draft-07/schema#"`**, and a strict 2020-12 client rejects the whole tool: *"JSON Schema declares an unsupported dialect ... The default validator s How it starts
The opening of the file, as written. The whole thing — 399 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Best Practices
Decision reference for building production MCP servers with the TypeScript SDK. Not a tutorial - assumes you already have a working server and need to make it correct, fast, and secure.
Quick Reference
| Component | Current | Notes |
|---|---|---|
| Spec (released) | 2026-07-28 (specification) | Stateless/sessionless overhaul - see "Spec 2026-07-28" below and references/spec-2026-07-28.md |
| Spec (still deployed) | 2025-11-25 | What most shipped clients and servers actually speak today; the v2 SDK's default |
| TS SDK (current) | v2.0.0 (2026-07-27), nine packages in lockstep: /server, /client, /core, /hono, /express, /node, /fastify, /codemod, /server-legacy |
Speaks 2025-era by default; 2026-07-28 is opt-in |
| TS SDK (legacy) | v1.30.0 (@modelcontextprotocol/sdk) |
Bug + security fixes for >=6 months after v2 GA; source on the v1.x branch |
| JSON Schema | 2020-12 default (2019-09 / draft-07 accepted since v2.0.0) | - |
| Transport | Streamable HTTP (remote), stdio (local) | SSE + WebSocket removed in v2 |
| Extensions | MCP Apps (Stable, SEP-1865), Auth Extensions (official), Tasks (ext-tasks) | Domain-specific WGs |
| Registry | Preview with v0.1 API freeze since 2025-10-24 (registry) | GA pending |
v2 imports (current):
import { McpServer } from "@modelcontextprotocol/server";
import { WebStandardStreamableHTTPServerTransport } from "@modelcontextprotocol/server";
import { ProtocolError, ProtocolErrorCode } from "@modelcontextprotocol/core";
v1 imports (legacy line, still widely deployed):
import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { WebStandardStreamableHTTPServerTransport } from "@modelcontextprotocol/sdk/server/webStandardStreamableHttp.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
What ships with it
11 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.
- CHANGELOG.md 30 KB
- LICENSE.txt 8.9 KB
- references/error-handling.md 12 KB
- references/extensions-registry.md 16 KB
- references/mcp-apps.md 12 KB
- references/sdk-bugs.md 6.9 KB
- references/security-auth.md 24 KB
- references/spec-2026-07-28.md 29 KB
- references/tool-schema-guide.md 29 KB
- references/transport-patterns.md 17 KB
- references/v2-migration.md 25 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.
- 2d ago Changed · +15 lines · -27 tokens per session scan A → B f74376d01d2e
- 12d ago First seen · 384 lines · 87 tokens per session scan A 6c3d17d90a2d
mcp-best-practices is a skill published in the GitHub repository tenequm/skills (36 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 8,219 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
debridge
Complete deBridge Protocol SDK for building cross-chain bridges, message passing, and token transfers on Solana. Use when building cross-chain applications, bridging assets between Solana and EVM chains, or implementing trustless external calls.
lifi
Integrate LI.FI for cross-chain swaps, bridging, payments, route discovery, and transfer status tracking across Solana, EVM, Bitcoin, and Sui. Use when building Solana applications or AI agents that need quotes, routes, executable transactions, supported chains/tokens/tools, or cross-chain transfer monitoring.
ct-alpha
Crypto Twitter intelligence and alpha research. Search X/Twitter for real-time crypto narratives, trending tokens, yield strategies, smart money signals, and protocol research. Features TweetRank (PageRank-inspired credibility scoring), multi-signal token detection, coordinated raid detection, and dynamic tool…
switchboard
Complete Switchboard Oracle Protocol SDK for Solana - the permissionless oracle solution for price feeds, on-demand data, VRF randomness, and real-time streaming via Surge. Covers TypeScript SDK, Rust integration, Oracle Quotes, and all Switchboard tools.
raydium
Complete Raydium Protocol SDK - the single source of truth for integrating Raydium on Solana. Covers SDK, Trade API, CLMM, CPMM, AMM pools, LaunchLab token launches, farming, CPI integration, and all Raydium tools.
helius
Skill "helius" from helius-labs/core-ai, covering helius — build on solana, prerequisites, 1. helius mcp server, 2. mcp router surface and 3. api key.