
axiom-xcode-mcp
Use when connecting to Xcode via MCP, using xcrun mcpbridge or the headless mcp-server, or working with ANY Xcode MCP tool (XcodeRead, BuildProject, RunSomeTests, RenderPreview). Covers setup, tool reference, workflows, troubleshooting.
- Installs
- 1.4K
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/charleswiltgen/axiom --skill axiom-xcode-mcp- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads axiom-xcode-mcp automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Xcode MCP
You MUST use this skill for ANY Xcode MCP interaction — setup, tool usage, workflow patterns, or troubleshooting.
Bundled tools on Claude Code: if command -v <tool> finds nothing (hooks off or --bare), use <plugin-root>/tools/<tool> in place of the bare name; <plugin-root> is two levels above this skill's Base directory for this skill: path.
Xcode ships an MCP server exposing IDE tools to external AI clients. xcrun mcpbridge is the stdio transport clients register, available since Xcode 26.3. Xcode 27 adds an explicit "Allow External Agents to Use Xcode Tools" setting, the run-agent launch path, an agent-extension model (custom MCP servers, skills, plug-ins), and a headless server. This skill suite covers setup, tool reference, workflow patterns, and troubleshooting.
On Xcode 26.x, mcpbridge requires a running Xcode with a project open. If that's a liability, the device/simulator half of these operations has a fully Xcode-independent CLI path: devicectl + simctl + Axiom's xcui/xclog/xcsym/xcprof. See axiom-tools (skills/device-control-ref.md).
That constraint is gone on Xcode 27. xcrun mcp-server runs the tool service with Xcode.app closed — sudo xcrun mcp-server enable, then xcrun mcp-server open <project-or-workspace-path>, which launches the service if needed. Clients still register xcrun mcpbridge; the bridge is the transport, mcp-server is the service. Apple's tool schemas describe workspaceIdentifier as "used in headless mode", so headless is a supported model rather than a workaround.
Choose between MCP and the CLI tools (devicectl, simctl, and Axiom's xcui/xclog/xcsym/xcprof) on capability, not uptime. xcui asserts, waits, toggles accessibility settings, and computes VoiceOver announcements, and none of them need sudo — which still matters in CI, where the headless server's sudo opt-in may not be available. The IDE-authoring tools (build state, render previews) remain MCP-only; xcodebuild builds and tests but does not render previews.
When to Use
Use this skill when:
- Setting up Xcode MCP for the first time
- Configuring
xcrun mcpbridgefor any MCP client - Using any Xcode MCP tool (file ops, build, test, preview)
- Building, testing, or previewing via MCP tools
- Troubleshooting mcpbridge connection issues
- Workspace targeting questions
- Permission dialog confusion
- Driving simulator input with AXe (
tap/type/swipe) -> readskills/axe-ref.md
Routing Logic
1. Setup/Connection → xcode-mcp-setup
Triggers:
- First-time Xcode MCP setup
- Client-specific config (Claude Code, Cursor, Codex, VS Code, Gemini CLI)
- Connection errors ("Connection refused", "No workspaces are currently open.")
- Permission dialog confusion
- Multi-Xcode targeting (
MCP_XCODE_PID) - Schema compliance issues with strict clients
- Giving external agents access to Xcode (Intelligence settings gate)
- Launching an agent via Xcode config (
xcrun mcpbridge run-agent) - Exporting Xcode's skill bundles (
xcrun agent skills export) - Extending Xcode's agent (per-agent config files, MCP servers, plug-ins)
Read: skills/xcode-mcp-setup.md
2. Using Tools & Workflows → xcode-mcp-tools
Triggers:
- How to build/test/preview via MCP
- Workflow patterns (BuildFix loop, TestFix loop)
- Tool gotchas and anti-patterns
- Workspace targeting strategy; headless bootstrap (open or create a workspace)
- When to use MCP tools vs CLI (
xcodebuild) - Destructive operation safety (
XcodeRM,XcodeMV)
Read: skills/xcode-mcp-tools.md
3. Tool API Reference → xcode-mcp-ref
Triggers:
- Specific tool parameters and schemas
- Input/output format for a tool
- "How does XcodeGrep work?"
- "What params does BuildProject take?"
- Tool category listing
Read: skills/xcode-mcp-ref.md
Decision Tree
digraph xcode_mcp_router {
rankdir=TB;
"User has Xcode MCP question" [shape=ellipse];
"Setup or connection?" [shape=diamond];
"Using tools or workflows?" [shape=diamond];
"Need specific tool params?" [shape=diamond];
"xcode-mcp-setup" [shape=box];
"xcode-mcp-tools" [shape=box];
"xcode-mcp-ref" [shape=box];
"User has Xcode MCP question" -> "Setup or connection?";
"Setup or connection?" -> "xcode-mcp-setup" [label="yes"];
"Setup or connection?" -> "Using tools or workflows?" [label="no"];
"Using tools or workflows?" -> "xcode-mcp-tools" [label="yes"];
"Using tools or workflows?" -> "Need specific tool params?" [label="no"];
"Need specific tool params?" -> "xcode-mcp-ref" [label="yes"];
"Need specific tool params?" -> "xcode-mcp-tools" [label="general question"];
}
Anti-Rationalization
| Thought | Reality |
|---|---|
| "I'll just use xcodebuild directly" | MCP gives IDE state, filtered compiler diagnostics, and rendered previews that CLI doesn't expose |
| "I already know how to set up MCP" | Client configs differ. Permission dialog behavior is specific. Check setup skill. |
| "I can figure out the tool params" | Tool schemas have required fields and gotchas. Check ref skill. |
| "One workspace is open, so I can skip the identifier" | workspaceIdentifier is required anyway, despite being absent from every required list. |
| "This is just file reading, I'll use Read tool" | XcodeRead sees Xcode's project view including generated files and resolved packages |
Conflict Resolution (vs Other Routers)
| Domain | Owner | Why |
|---|---|---|
| MCP-specific interaction (mcpbridge, mcp-server, MCP tools, workspace identifiers) | axiom-xcode-mcp | MCP protocol and tool-specific |
| Xcode environment (Derived Data, zombie processes, simulators) | axiom-build | Environment diagnostics, not MCP |
| Apple's bundled documentation (for-LLM guides/diagnostics) | axiom-apple-docs | Bundled docs, not MCP tool |
DocumentationSearch MCP tool usage specifically | axiom-xcode-mcp | MCP tool invocation |
| Build failures diagnosed via CLI | axiom-build | Traditional build debugging |
| Build failures diagnosed via MCP tools | axiom-xcode-mcp | MCP workflow patterns |
Example Invocations
User: "How do I set up Xcode MCP with Claude Code?"
-> Read: skills/xcode-mcp-setup.md
User: "How do I build my project using MCP tools?"
-> Read: skills/xcode-mcp-tools.md
User: "What parameters does BuildProject take?"
-> Read: skills/xcode-mcp-ref.md
User: "My mcpbridge connection keeps failing"
-> Read: skills/xcode-mcp-setup.md
User: "How do I target a specific workspace?" / "How do I run this without Xcode open?"
-> Read: skills/xcode-mcp-tools.md
User: "Can I render SwiftUI previews via MCP?"
-> Read: skills/xcode-mcp-tools.md (workflow), then skills/xcode-mcp-ref.md (params)
User: "Cursor can't parse Xcode's MCP responses"
-> Read: skills/xcode-mcp-setup.md (schema compliance section)
Resources
Skills: skills/xcode-mcp-setup.md, skills/xcode-mcp-tools.md, skills/xcode-mcp-ref.md, skills/axe-ref.md
FAQ
What does the axiom-xcode-mcp skill do?
Use when connecting to Xcode via MCP, using xcrun mcpbridge or the headless mcp-server, or working with ANY Xcode MCP tool (XcodeRead, BuildProject, RunSomeTests, RenderPreview). Covers setup, tool reference, workflows, troubleshooting.
How do I install axiom-xcode-mcp?
Run npx skills add https://github.com/charleswiltgen/axiom --skill axiom-xcode-mcp in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/axiom-xcode-mcp/ (personal) or .claude/skills/axiom-xcode-mcp/ (project).
Which AI agents can use axiom-xcode-mcp?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is axiom-xcode-mcp safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains axiom-xcode-mcp?
It is published by charleswiltgen in charleswiltgen/axiom. It has 1,424 recorded installs.
More from charleswiltgen/axiom
axiom-vision
charleswiltgen/axiom
Use when implementing ANY computer vision feature — image analysis, pose detection, person segmentation, subject lifting, text recognition, barcode scanning.
axiom-swiftui
charleswiltgen/axiom
Use when building, fixing, or improving ANY SwiftUI UI — views, navigation, layout, animations, gestures, debugging, iOS 26 features, iPhone Duo, view-level performance, feature architecture.
axiom-networking
charleswiltgen/axiom
Use when implementing or debugging ANY network connection, API call, or socket in an Apple app. Covers URLSession, Network.framework, NetworkConnection, connection diagnostics.
axiom-apple-docs
charleswiltgen/axiom
Use when you need Apple's own documentation or a Swift compiler diagnostic explained rather than recalled.
axiom-shipping
charleswiltgen/axiom
Use when preparing an app for App Store submission, handling rejections or appeals, managing App Store Connect and Xcode Cloud, or triaging TestFlight/Sentry crash corpora. Covers checklists, metadata, privacy manifests, age ratings, export compliance.
axiom-design
charleswiltgen/axiom
Use when making visual or interaction design decisions for an Apple app — HIG patterns, Liquid Glass, SF Symbols, typography, app entry-point and auth-flow structure.
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available