SwiftSkills
by swiftskills.dev · remote · no sign-in to list tools · v0.1.0 · published by dev.swiftskills
Search a curated catalog of agent skills, MCP servers and rules for Swift, SwiftUI, Xcode and iOS.
4 tools: 4 only read.
Scanned Oct 21, 2026
- Deletes or cancels0Claude Code: deny
- Can't be undone0Claude Code: ask
- Changes things0Claude Code: ask
- Only reads4Claude Code: allow: see these tools
No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.
claude mcp add --transport http catalog https://swiftskills.dev/mcpTools
Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.
4 tools
Only reads 4Claude Code: allow
get_entryFetch one public catalog entry by slug.No findings
Why it is in this group
- The name "get_entry" says "get": a word for reading.
Description, as the server wrote it Fetch one public catalog entry by slug. Includes source_url, the install command, copied_at when the catalog recorded the day the command was copied, compatible tools, license when known, and the day the entry was added. URLs include utm_source=mcp and utm_medium=tool.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_categoriesList catalog categories with slug, name, and url.Reads text others writeNo findings
Why it is in this group
- The name "list_categories" says "list": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "list" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it List catalog categories with slug, name, and url. The url includes utm_source=mcp and utm_medium=tool.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_newList entries added within the last days (default 7, maximum 90), newest first.No findings
Why it is in this group
- The name "list_new" says "list": a word for reading.
Description, as the server wrote it List entries added within the last days (default 7, maximum 90), newest first. Each row has name, slug, type, category, summary, url, and added. The url includes utm_source=mcp and utm_medium=tool.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_entriesSearch the public SwiftSkills catalog.No findings
Why it is in this group
- The name "search_entries" says "search": a word for reading.
Description, as the server wrote it Search the public SwiftSkills catalog. query is a case-insensitive substring (max 200 characters). category is an optional category slug. type is an optional kind: skill, mcp, rules, docs, or sdk. Returns name, slug, type, category, summary, and url. Every url includes utm_source=mcp and utm_medium=tool. At most 50 rows are returned; total counts the rest.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write1
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Oct 22, 2026, 14:46 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 0
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- none
- RFC 9728 protected resource metadata
- none
- Authorization servers
- none
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
Install
Pinned to version 0.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http catalog https://swiftskills.dev/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__catalog__search_entries",
"mcp__catalog__get_entry",
"mcp__catalog__list_categories",
"mcp__catalog__list_new"
],
"ask": [],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as catalog. Review it before you use it.
Capability tags behind 1 rule
- mcp__catalog__list_categories untrusted-input