use-profile

use-profile is a cursor rule for coding agents from paladini/mcp-me. It costs 394 tokens per session, scanned A, original, MIT.

A rule requiring an AI assistant to consult the user's mcp-me personal profile before answering requests that could benefit from personal context.

In plain words
What is it for?
Use it for writing, code review, career questions, recommendations, and other tasks where the user's skills, projects, preferences, or goals matter.
Why use it?
It reduces answers based on missing or assumed information about the user. The rule depends on the mcp-me server and profile being available.

Cursor rule

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/paladini/mcp-me/use-profile
Clone the repo
git clone --depth 1 https://github.com/paladini/mcp-me

Wrote 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.

agentmods badge for use-profile

README.md
[![agentmods](https://agentmods.dev/badge/rules/paladini/mcp-me/use-profile.svg)](https://agentmods.dev/rules/paladini/mcp-me/use-profile)
Your own site
<a href="https://agentmods.dev/rules/paladini/mcp-me/use-profile"><img src="https://agentmods.dev/badge/rules/paladini/mcp-me/use-profile.svg" alt="Measured on agentmods" height="20"></a>
Per session 394 This file is loaded in full into every session.
When invoked 394 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.00394 $0.00394
Opus 5 $0.00197 $0.00197
Sonnet 5 $0.00079 $0.00079
Haiku 4.5 $0.00039 $0.00039

Measured 4d ago against content hash 634007926c5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

use-profile 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 4d 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.

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.

rules/use-profile.mdc · 39 lines

What it actually says

You have access to an MCP server called me that exposes the user's personal profile.

Always use ask_about_me or read the MCP resources below before answering any request that could benefit from knowing who the user is — writing, code review, documentation, career questions, open-source contributions, etc.

Available MCP resources

Resource Contains
me://identity Name, bio, location, contact, social links
me://career Work history, job titles, companies
me://skills Programming languages, tools, proficiency levels
me://projects Open-source repos, articles (with full text), books, npm packages
me://interests Hobbies, topics of interest
me://personality Traits, values, work style
me://goals Short and long-term goals
me://faq Pre-answered facts about the user

When to proactively load the profile

  • Writing or editing any text (articles, READMEs, cover letters, bios)
  • Answering questions about skills, experience, or projects
  • Generating code in a language or framework the user uses
  • Recommending tools, libraries, or approaches
  • Any task where knowing the user's background would improve the answer

The ask_about_me tool

Use this tool for natural-language questions. Example invocations:

  • ask_about_me("What open-source projects has this person published?")
  • ask_about_me("What articles has this person written? Include full content.")
  • ask_about_me("What are this person's strongest programming languages?")
  • ask_about_me("What are this person's career goals?")
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. 4d ago First seen · 39 lines · 394 tokens per session scan A 634007926c5d

Subscribe to this mod's changes

use-profile is a cursor rule published in the GitHub repository paladini/mcp-me (18 stars, last pushed 23d ago), licensed MIT. It adds 394 tokens to every session, about $0.0020 per session on Opus 5. 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 2026-08-30.