31-mcp-integration

31-mcp-integration is a cursor rule for Cursor from bybren-llc/safe-agentic-workflow. It costs 14 tokens per session (606 once invoked), scanned A, original, MIT.

Configuration guidance for MCP, a standard that lets AI tools connect to outside services and project resources. It explains how to configure those connections in Cursor, including services for tickets, documentation, code hosting, files, and databases.

In plain words
What is it for?
Use it when setting up Cursor connections to Linear, Confluence, GitHub, the filesystem, or PostgreSQL. These connections can support ticket work, documentation, code review, file access, and database queries.
Why use it?
It removes the guesswork from connecting an AI coding session to the tools and information a project uses. It also shows where project-level connection settings can be stored.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: reads .claude/ paths; mentions Claude Code; mentions Codex.

Good fit Use it when setting up Cursor connections to Linear, Confluence, GitHub, the filesystem, or PostgreSQL. These connections can support ticket work, documentation, code review, file access, and database queries.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/bybren-llc/safe-agentic-workflow/31-mcp-integration
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.

Clone the repo
git clone --depth 1 https://github.com/bybren-llc/safe-agentic-workflow

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 31-mcp-integration

README.md
[![agentmods](https://agentmods.dev/badge/rules/bybren-llc/safe-agentic-workflow/31-mcp-integration/github.svg)](https://agentmods.dev/rules/bybren-llc/safe-agentic-workflow/31-mcp-integration)
Your own site
<a href="https://agentmods.dev/rules/bybren-llc/safe-agentic-workflow/31-mcp-integration"><img src="https://agentmods.dev/badge/rules/bybren-llc/safe-agentic-workflow/31-mcp-integration/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for 31-mcp-integration

Your own site · 80×15
<a href="https://agentmods.dev/rules/bybren-llc/safe-agentic-workflow/31-mcp-integration"><img src="https://agentmods.dev/badge/rules/bybren-llc/safe-agentic-workflow/31-mcp-integration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 606 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00014 $0.00606
Opus 5 $0.00007 $0.00303
Sonnet 5 $0.00003 $0.00121
Haiku 4.5 $0.00001 $0.00061

Measured 6d ago against content hash 67f1cf90a0fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

31-mcp-integration 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.cursor/rules/31-mcp-integration.mdc · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Integration Guidelines

Cursor supports the Model Context Protocol (MCP) natively. MCP servers provide additional tools and context to AI sessions, enabling interaction with external services.

Configuring MCP Servers in Cursor

MCP servers are configured in Cursor's settings. Navigate to:

Settings > Features > MCP Servers

Or add them to your project-level .cursor/mcp.json:

{
  "mcpServers": {
    "linear": {
      "command": "npx",
      "args": ["-y", "@linear/mcp-server"],
      "env": {
        "LINEAR_API_KEY": "your-api-key"
      }
    },
    "filesystem": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-filesystem", "/path/to/project"]
    }
  }
}

Common MCP Servers for SAFe Workflow

MCP Server Purpose When to Use
Linear Ticket management, comments, status updates All workflow (TDM, QAS, RTE agents)
Confluence Documentation publishing Tech Writer agent, BSA specs
GitHub PR management, issue tracking RTE agent, code review
Filesystem Extended file access Background agents needing broad access
PostgreSQL Direct database queries Data Engineer agent

SAFe Agent MCP Usage

Different agent roles use different MCP capabilities:

  • TDM: Linear MCP for ticket coordination and status updates
  • QAS: Linear MCP for posting validation evidence as comments
  • RTE: GitHub MCP for PR creation and CI monitoring
  • Tech Writer: Confluence MCP for publishing documentation
  • BSA: Linear MCP for creating tickets, Confluence MCP for specs

Security Considerations

  • Never commit API keys or tokens to the repository
  • Use environment variables for MCP server credentials
  • Review MCP server permissions before granting access
  • Prefer read-only access where write access is not needed
  • MCP servers in background agents use the repository-level config only

Cross-Provider MCP Compatibility

Read the full file on GitHub · 76 lines

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 · 76 lines · 14 tokens per session scan A 67f1cf90a0fc

Subscribe to this mod's changes

31-mcp-integration is a cursor rule published in the GitHub repository bybren-llc/safe-agentic-workflow (406 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 606 once invoked, about $0.0001 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 2026-09-03.