SkillsPicker MCP server
com.skillspicker/recommendskillspicker.comstreamable-httpv1.0.0Scanned
Recommends open-license agent skills (SKILL.md) for a project from its stack and task tags.
3 tools: 1 change things and 2 only read.
- Reads private data · 0
- Reads text others write · 3
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here changes things. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the SkillsPicker MCP server can do
The SkillsPicker MCP server is published by skillspicker.com, a domain the MCP Registry verified. It has 3 tools. It can create or change data (1 tool: recommend_skills), but cannot delete data. 2 tools only read.
3 tools bring in text other people can write (recommend_skills, search_skills and list_skill_tags).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 14, 2026, version 1.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
3 tools
Changes things 1Claude Code: ask
recommend_skillsRecommend agent skills (SKILL.md) that fit a coding project, for Claude Code, Cursor, Codex, Copilot or Gemini CLI.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Recommend agent skills (SKILL.md) that fit a coding project, for Claude Code, Cursor, Codex, Copilot or Gemini CLI. Pass stack tags (best), a one line description, or a public GitHub repo URL. With no input it returns a sample for a Next.js project. Returns how many of 90,454 indexed skills fit, 2 free picks with license and install command, and a link to the full ranked list ($9 once). Read-only, no account.
Annotations the server declares
- title: Recommend agent skills for a project
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Only reads 2Show 2 read-only tools
list_skill_tagsList the stack tags (frameworks, languages, services) and task tags (testing, code-review, security and more) that recommend_skills accepts, with the size of the skill index.Reads text others writeNo findings
Why it is in this group
- The name "list_skill_tags" says "list": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "list" and "review": it reads comments, which other people can write.
Description, as the server wrote it List the stack tags (frameworks, languages, services) and task tags (testing, code-review, security and more) that recommend_skills accepts, with the size of the skill index. No input needed. Read-only.
Annotations the server declares
- title: List stack and task tags
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
search_skillsSearch 90,454 open-license agent skills (SKILL.md) by task, tool or framework, for example "stripe webhooks", "playwright tests", "django admin" or "terraform aws".Reads text others writeNo findings
Why it is in this group
- The name "search_skills" says "search": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Search 90,454 open-license agent skills (SKILL.md) by task, tool or framework, for example "stripe webhooks", "playwright tests", "django admin" or "terraform aws". Returns the match count, the top 2 skills with license and install command, and a link to the full ranked list ($9 once). Read-only, no account.
Annotations the server declares
- title: Search agent skills by task or tool
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
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 write3
- 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 Nov 20, 2026, 18:47 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
- 1
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://skillspicker.com/mcp: tools/list returned 3 tools to an anonymous client, including recommend_skills (write)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools2 added, 1 changed.+2 added~1 changedView diff
- Added:list_skill_tagsOnly reads
- Added:search_skillsOnly reads
- Changed:recommend_skillsChanges thingsdescriptioninputSchema
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http recommend https://skillspicker.com/mcpclaude mcp add --transport http recommend https://skillspicker.com/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__recommend__search_skills",
"mcp__recommend__list_skill_tags"
],
"ask": [
"mcp__recommend__recommend_skills"
],
"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 recommend. Review it before you use it.
Capability tags behind 3 rules
- mcp__recommend__recommend_skills untrusted-input
- mcp__recommend__search_skills untrusted-input
- mcp__recommend__list_skill_tags untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/com.skillspicker/recommend/verify?hash=07517c82e8ffb036874ab7ca67c9b7b6ee5397903683adb96a9f6ceb200411e8" | jq -e '.changed == false'Pinned hash 07517c82e8ff, from Nov 14, 2026, 09:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.skillspicker/recommend/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.skillspicker/recommend)Source: MCP Registry. Synced Oct 21, 2026, 18:04 UTC.
SkillsPicker MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the SkillsPicker MCP server safe?
- No scan can promise that. What its definitions show: 3 tools, 1 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the SkillsPicker MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the SkillsPicker MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the SkillsPicker MCP server have?
- 3 tools: 1 write, 2 read. recommend_skills, search_skills and list_skill_tags.
Does the SkillsPicker MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the SkillsPicker MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the SkillsPicker MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 1, 2026. Every change is on this page and in its Atom feed.