with-my-team

with-my-team is a cursor rule for Cursor from zackiles/cursor-mcp-manager. It costs 0 tokens per session (479 once invoked), scanned A, original, MIT.

A project rule requiring background information from a context/ folder before making MCP tool calls. MCP is a standard for connecting software to AI tools and services.

In plain words
What is it for?
Use it before calling MCP tools that search or work with company systems such as Jira, Confluence, Google Drive, or GitHub.
Why use it?
It helps tool calls use the right people, teams, projects, repositories, and search terms for the user's organization.

Cursor rule for Cursor

Written for Cursor: installed under .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/zackiles/cursor-mcp-manager/with-my-team
Clone the repo
git clone --depth 1 https://github.com/zackiles/cursor-mcp-manager

Made for: Cursor.

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 with-my-team

README.md
[![agentmods](https://agentmods.dev/badge/rules/zackiles/cursor-mcp-manager/with-my-team.svg)](https://agentmods.dev/rules/zackiles/cursor-mcp-manager/with-my-team)
Your own site
<a href="https://agentmods.dev/rules/zackiles/cursor-mcp-manager/with-my-team"><img src="https://agentmods.dev/badge/rules/zackiles/cursor-mcp-manager/with-my-team.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 479 The whole file, excluding the scripts and references it only reads on demand.
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 5.1 $0.00000 $0.00479
Opus 5 $0.00000 $0.00239
Sonnet 5 $0.00000 $0.00096
Haiku 4.5 $0.00000 $0.00048

Measured 6d ago against content hash dcfd801bcd8e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

with-my-team 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 6d 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.

.cursor/rules/local/with-my-team.mdc · 71 lines

What it actually says

Context for MCP Tool Calls

Before making tool calls with MCP first review the files in the context/ folder which provides context on who I am, my team, my department, and my company. It will provide valuable details in order to craft your tool calls with the right arguments.

Examples of Context

All of these things could potentially be in a file in the context/ folder.

  • Names of colleagues
  • Emails of colleagues
  • Jira
    • Boards
    • Tickets
    • Project Keys
    • Terms to search within tickets
      • Names or emails or usernames or user IDs of colleagues
      • Names of teams
      • Names of projects
      • ...
  • Confluence
    • Spaces
    • Page IDs
    • Terms to search within pages
      • Names or emails or usernames or user IDs of colleagues
      • Names of teams
      • Names of projects
      • ...
  • Google Drives
    • Folder names
    • File names
    • Terms to search within files
      • Names or emails or usernames or user IDs of colleagues
      • Names of teams
      • Names of projects
      • ...
  • Github
    • Org names
    • Repositories
    • Usernames
    • Groups
  • Applications, Services, and Systems
    • Names of these typically map 1:1 for repositories on Github under the company's github Org name e.g https://github.com/{Github Org Name}/some-service-name
  • Slack
    • Channel IDs
    • Usernames
    • Groups
    • Colleagues to check DMs with

Examples of User Queries That Benefit From Context

Finding Jira Tickets

USER QUERY: List all Jira tickets for my teams which are blocked and have been updated in the last month.

SEARCH context/ FOR:

  • Their team's Project Keys

CONTEXT FOUND:

  • Project Keys: PROJA, PROJB, PROJC

MCP TOOL CALL WITH CONTEXT:

{
  "jql": "status = \"Blocked / On hold\" AND updated >= -30d AND (project IN (PROJA, PROJB, PROJC)) ORDER BY updated DESC",
  "limit": 50
}
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. 6d ago First seen · 71 lines · 0 tokens per session scan A dcfd801bcd8e

Subscribe to this mod's changes

with-my-team is a cursor rule published in the GitHub repository zackiles/cursor-mcp-manager (3 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 479 tokens. 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 2026-08-31.