mcp-security

A set of rules about securing MCP implementations. MCP, or Model Context Protocol, is a standard for connecting AI systems with external tools and data.

In plain words
What is it for?
Developing or reviewing MCP integrations with security considerations in mind.
Why use it?
It adds security guidance to work involving MCP tools. The description does not provide enough detail to identify the specific risks or checks covered.

Cursor rule for Cursor

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 rules/datai-network/datai-mcp-server/mcp-security
Clone the repo
git clone --depth 1 https://github.com/Datai-Network/datai-mcp-server

Made for: Cursor.

Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,157 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 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 $0.00008 $0.05157
Opus 5 $0.00004 $0.02579
Sonnet 5 $0.00002 $0.01031
Haiku 4.5 $0.00001 $0.00516

Measured 2d ago against content hash eaa9c3bd98b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-security 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.

const requests = this.requests.get(key) || [];
.cursor/rules/MCP/mcp-security.mdc · 714 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

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 · 714 lines · 8 tokens per session scan A eaa9c3bd98b7

Subscribe to this mod's changes

mcp-security is a cursor rule published in the GitHub repository Datai-Network/datai-mcp-server (3 stars, last pushed 1y ago), with no licence file. It adds 8 tokens to every session and 5,157 once invoked, about $0.0000 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.