mcp-setup

A setup guide for configuring XcodeBazelMCP, a tool server that lets an AI assistant work with Xcode and Bazel projects. It covers the server command, configuration file, and background service.

In plain words
What is it for?
Use it when connecting XcodeBazelMCP to a project, choosing enabled workflows, setting project profiles, or checking the daemon's status.
Why use it?
It explains where configuration belongs and how to make the server available to other projects without relying on unclear paths or settings.

Skill for Claude CodeCodex

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 skills/debugswift/xcodebazelmcp/mcp-setup
Any agent
npx skills add DebugSwift/XcodeBazelMCP --skill mcp-setup
Clone the repo
git clone --depth 1 https://github.com/DebugSwift/XcodeBazelMCP

Made for: Claude Code, Codex.

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 683 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 $0.00046 $0.00683
Opus 5 $0.00023 $0.00342
Sonnet 5 $0.00009 $0.00137
Haiku 4.5 $0.00005 $0.00068

Measured yesterday against content hash b50400854f59, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-setup 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 yesterday.

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.

.agents/skills/mcp-setup/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Setup & Configuration

Using in Other Projects

The package is not published to npm (private: true). Use the local dist/cli.js path in .cursor/mcp.json:

{
  "XcodeBazelMCP": {
    "command": "node",
    "args": ["/Users/matheus.gois/Projects/XcodeBazelMCP/dist/cli.js", "mcp"],
    "env": { "BAZEL_IOS_WORKSPACE": "/path/to/your/workspace" }
  }
}
  • After source changes, run npm run build to update dist/.
  • Prefer absolute paths — ~ may not expand in all MCP clients.
  • Local Bazel execution is the default. BITRISE_BUILD_CACHE_AUTH_TOKEN is not required. Bitrise RBE configs (bitrise, remote_linux) are stripped automatically unless the token is set.

Config File

.xcodebazelmcp/config.yaml (in workspace root or ~/.xcodebazelmcp/):

  • enabledWorkflows — comma-separated workflow IDs (e.g. build, test, simulator)
  • profiles: — nested blocks for per-project defaults
  • activateProfile merges profile defaults into session defaults

Per-Workspace Daemon

  • Unix socket: /tmp/xbmcp-daemon-<sha256(wsPath)[0:12]>.sock
  • PID file: ~/.xcodebazelmcp/daemons/<hash>.json
  • JSON protocol: ping, status, list_ops, register_op, unregister_op, shutdown
  • Client spawns detached child via child.unref() with XBMCP_DAEMON=1 env, polls up to 5s for socket.
  • Auto-cleanup on SIGTERM/SIGINT: removes socket and PID file.

Project Scaffolding

6 templates: ios_app, ios_test, ios_app_with_tests, macos_app, macos_test, macos_app_with_tests.

  • Guards against overwriting — fails if MODULE.bazel or WORKSPACE already exists.
  • Test-only templates generate BUILD.bazel under ${name}Tests/ subdirectory.
  • Scaffold name validated with ^[A-Za-z][A-Za-z0-9_-]*$ to prevent path traversal.

Doctor

Reports: system info (platform, arch, CPUs, memory, Node), workspace details (path, config, MODULE.bazel/WORKSPACE/.bazelrc), dependency versions (bazel, xcode, simctl), full tool inventory by workflow with enabled/disabled status.

Read the full file on GitHub · 62 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. yesterday First seen · 62 lines · 46 tokens per session scan A b50400854f59

Subscribe to this mod's changes

mcp-setup is a skill published in the GitHub repository DebugSwift/XcodeBazelMCP (7 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 683 once invoked, about $0.0002 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 2026-08-31.