MCP Integration

A guide to connecting an agent to outside services through MCP, a standard way for agents to use external tools and data sources.

In plain words
What is it for?
Use it to add and configure MCP servers in a plugin, including servers connected over SSE, standard input/output, HTTP, or WebSocket.
Why use it?
It explains the configuration needed to connect services instead of leaving the agent isolated from them.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/ssdeanx/agentstack/mcp-integration
Any agent
npx skills add ssdeanx/AgentStack --skill mcp-integration
Clone the repo
git clone --depth 1 https://github.com/ssdeanx/AgentStack

Made for: Claude Code, Codex.

Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,053 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin unknown No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00097 $0.03053
Opus 5 $0.00048 $0.01527
Sonnet 5 $0.00019 $0.00611
Haiku 4.5 $0.00010 $0.00305

Measured 2d ago against content hash 2c94e2d33655, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

MCP Integration 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.

- ❌ Pre-allow all tools with wildcards
.github/skills/mcp-integration/SKILL.md · 594 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

Files

What ships with it

6 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.

Changes

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.

  1. 2d ago First seen · 594 lines · 97 tokens per session scan B 2c94e2d33655

Subscribe to this mod's changes

MCP Integration is a skill published in the GitHub repository ssdeanx/AgentStack (44 stars, last pushed 4mo ago), with no licence file. It adds 97 tokens to every session and 3,053 once invoked, about $0.0005 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.