mcp CLAUDE.md

A set of project instructions for using smplkit, a hosted platform that lets an AI agent run HTTP jobs and manage operational settings through MCP tools.

In plain words
What is it for?
Reading job runs, changing feature flags and configuration, adjusting log levels, searching audit logs, scheduling jobs, and connecting the hosted MCP server when needed.
Why use it?
It tells the agent which connected tools to use for platform operations instead of improvised commands or scripts.

Instructions file

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 instructions/smplkit/mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/smplkit/mcp
Per session 221 This file is loaded in full into every session.
When invoked 221 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
Origin original 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 $0.00221 $0.00221
Opus 5 $0.00111 $0.00111
Sonnet 5 $0.00044 $0.00044
Haiku 4.5 $0.00022 $0.00022

Measured 2d ago against content hash b8222d0595c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp CLAUDE.md scanned grade A 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

smplkit runs a **hosted MCP server** at `https://mcp.smplkit.com/api/mcp` that operates the whole platform — feature flags, config, log levels, audit search, and scheduled jobs — exposed as MCP tools (source: the `mcp` r
CLAUDE.md · 11 lines

What it actually says

smplkit MCP server — operate the platform via MCP

smplkit runs a hosted MCP server at https://mcp.smplkit.com/api/mcp that operates the whole platform — feature flags, config, log levels, audit search, and scheduled jobs — exposed as MCP tools (source: the mcp repo). When a task means operating the platform (reading job runs, flipping a flag, changing a config value, setting a log level, searching the audit log) rather than editing service source, prefer these MCP tools over ad-hoc curl or one-off SDK scripts.

If it isn't connected yet, tell the user and offer to add it:

claude mcp add --transport http smplkit https://mcp.smplkit.com/api/mcp

First connect does a one-time browser sign-in (Google/Microsoft, WorkOS AuthKit OAuth) and refreshes itself after that. A committed .mcp.json at each repo root advertises the same server so Claude Code / Cursor auto-detect it.

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 · 11 lines · 221 tokens per session scan A b8222d0595c3

Subscribe to this mod's changes

mcp CLAUDE.md is an instructions file published in the GitHub repository smplkit/mcp (0 stars, last pushed 4d ago), licensed MIT. It adds 221 tokens to every session, about $0.0011 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.