apple-docs-mcp
MCP server for Apple Developer Documentation - Search iOS/macOS/SwiftUI/UIKit docs, WWDC videos, Swift/Objective-C APIs & code examples in Claude, Cursor & AI assistants
Runssource: GitHubhomepageTypeScriptMITcommit 28c06cbaa896
TypeScript, MIT licensed. The project labels itself: ai assistant, api documentation, apple, apple developer docs mcp, apple developer documentation, apple docs mcp, apple documentation and claude.
apple-docs-mcp runs. An Argusic agent installed it in 2 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
npm install and tsc build succeed, all 462 tests pass, the MCP server binary launches on stdio and correctly responds to initialize, tools/list, and tools/call with bundled WWDC data (1266 videos, 12 years).
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 100 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- [email protected] (dep of [email protected]) references global 'File' class only available in Node 20+, but Node 18.19.1 is installed13 minutes
- Install time
- 2 minutes
- Cold machine to finish
- 4 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- npm test exited 0, 462 passed across 31 suites; server answered MCP initialize and tools/list on stdio
- Model tokens used
- 39,474
- Exact commit tested
- 28c06cbaa896
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
{"result":{"content":[{"type":"text","text":"# Available WWDC Years\n\n**Total Years:** 12\n\n## Ye…
All tests pass and the server launches and responds correctly. Let me compile the final result.
exec
/bin/sh -lc 'cd /work/repo && npm test 2>&1 | grep -E "''^Test Suites:|''^Tests:|''^Time:"' in /wor…
succeeded in 13642ms:
Test Suites: 31 passed, 31 total
Tests: 462 passed, 462 total
Time: 13.087 s
All 462 tests pass, and the MCP server launches and responds to tool calls. Here's the report:
tokens used
39,474
All 462 tests pass, and the MCP server launches and responds to tool calls. Here's the report:Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Installed in 2 minutes.
- Recovered from all 1 error without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 2 minutes after the clone.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
Topics (from GitHub)
ai-assistantapi-documentationappleapple-developer-docs-mcpapple-developer-documentationapple-docs-mcpapple-documentationclaudeclaude-codecursordocumentationios-developmentmacos-developmentmcpmodel-context-protocolobjective-cswiftswift-mcpswiftui
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/apple-docs-mcp)Questions
- Does apple-docs-mcp run?
- Yes. apple-docs-mcp runs. Argusic installed and launched it on a clean machine in 2 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test apple-docs-mcp?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 28c06cbaa896. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test apple-docs-mcp?
- The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does apple-docs-mcp take to install?
- 2 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does apple-docs-mcp need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing apple-docs-mcp?
- 1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for apple-docs-mcp?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.