Skillshop MCP server
io.github.McCoyLab87/skillshopMcCoyLab87streamable-httpv0.1.7Scanned
Expert skills plus server-side checks for grant writing, home labs and AI agents
9 tools: 5 change things and 4 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
5 tools here change things. Govern them.
- 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 Skillshop MCP server can do
The Skillshop MCP server is published by the GitHub account McCoyLab87. It has 9 tools. It can create or change data (5 tools: audit_handoff, audit_grant_proposal, audit_grant_budget, audit_compose and 1 more), but cannot delete data. 4 tools only read.
None of its tools reads private data, brings in text other people write, or sends data out.
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.
Last scanned Nov 21, 2026, version 0.1.7.
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.
9 tools
Changes things 5Claude Code: ask
audit_backup_planCheck a backup plan against 3-2-1 with tested restores (paid, metered).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Check a backup plan against 3-2-1 with tested restores (paid, metered). datasets: [{name, copies: [{type: original|backup|snapshot|raid|sync, location, medium, offsite: bool, encrypted: bool, last_restore_test: 'YYYY-MM-DD'}]}]. Count the original as a copy.
audit_composeReview a docker-compose file for security and reliability (paid, metered): unpinned images, exposed databases/admin panels, plaintext secrets, Docker socket mounts, privileged cont…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Review a docker-compose file for security and reliability (paid, metered): unpinned images, exposed databases/admin panels, plaintext secrets, Docker socket mounts, privileged containers, missing volumes, restart policies and health checks. Send the whole file as text.
audit_grant_budgetCheck a grant budget's math and rules (paid, metered).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Check a grant budget's math and rules (paid, metered). budget: {lines: [{category, item, amount, justification, salary?, fte?, months?}], total_request, indirect?: {rate, base: 'tdc'|'mtdc', amount?}, max_indirect_rate?, fringe_rate?, match?: {required_ratio, amount}, participants?}. Checks totals, personnel and fringe math, indirect cap and base, match, missing justifications; returns cost per participant.
audit_grant_proposalReview a grant narrative the way a reviewer scores it (paid, metered).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Review a grant narrative the way a reviewer scores it (paid, metered). sections: {heading: text}. requirements: {required_sections: [..], word_limits: {heading: n}, total_word_limit: n}. request_amount: dollars requested. Returns findings by level (error/warning/nit): missing sections, word limits, unsourced need data, objectives that are not SMART, outputs posing as outcomes, no measurement plan, vague sustainability, request amount mismatch, vague words, placeholders.
audit_handoffCheck a task/handoff record against the agent-handoff protocol (paid, metered).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Check a task/handoff record against the agent-handoff protocol (paid, metered). record: {id, owner, state, revision, history[], artifact?, blocker?, delivery?, summary?} Returns ok, errors (protocol breaks), warnings (claims not yet supported by evidence), billing.
Only reads 4Show 4 read-only tools
accountShow this caller's license status, unlocked packs and credit balance.No findings
Why it is in this group
- The description's first verb is "show": a word for reading.
Description, as the server wrote it Show this caller's license status, unlocked packs and credit balance.
audit_status_reportCheck a status update before it goes to a person: flags completion claims with no evidence, hedged results, and missing blockers (paid, metered; pairs with the free honest-status s…No findings
Why it is in this group
- The name "audit_status_report" says "status": a word for reading.
Description, as the server wrote it Check a status update before it goes to a person: flags completion claims with no evidence, hedged results, and missing blockers (paid, metered; pairs with the free honest-status skill).
get_skillLoad a skill's full instructions by name.No findings
Why it is in this group
- The name "get_skill" says "get": a word for reading.
Description, as the server wrote it Load a skill's full instructions by name. Follow them for the current task.
list_skillsList every skill and paid check, with pack, price, and whether this caller can use it.No findings
Why it is in this group
- The name "list_skills" says "list": a word for reading.
Description, as the server wrote it List every skill and paid check, with pack, price, and whether this caller can use it.
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 untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- 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 21, 2026, 19:19 UTC, unchanged since Nov 21, 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
- 5
- 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 5 tools that change things (5 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://skillshop.duckdns.org/mcp: tools/list returned 9 tools to an anonymous client, including audit_handoff (write), audit_grant_proposal (write), audit_grant_budget (write), audit_compose (write), audit_backup_plan (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.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.1.7. Values in angle brackets are yours to fill in.
claude mcp add --transport http skillshop https://skillshop.duckdns.org/mcpclaude mcp add --transport http skillshop https://skillshop.duckdns.org/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__skillshop__list_skills",
"mcp__skillshop__get_skill",
"mcp__skillshop__account",
"mcp__skillshop__audit_status_report"
],
"ask": [
"mcp__skillshop__audit_handoff",
"mcp__skillshop__audit_grant_proposal",
"mcp__skillshop__audit_grant_budget",
"mcp__skillshop__audit_compose",
"mcp__skillshop__audit_backup_plan"
],
"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 skillshop. Review it before you use it.
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/io.github.McCoyLab87/skillshop/verify?hash=b5631403bf31e2fe695a1b593f088e2a550a69c9021bbbc75ee9fa55ee9d4b5f" | jq -e '.changed == false'Pinned hash b5631403bf31, from Nov 21, 2026, 01:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.McCoyLab87/skillshop/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.McCoyLab87/skillshop)Source: MCP Registry. Synced Nov 21, 2026, 01:17 UTC.
Skillshop MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Skillshop MCP server safe?
- No scan can promise that. What its definitions show: 9 tools, 5 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 Skillshop MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Skillshop 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 Skillshop MCP server have?
- 9 tools: 5 write, 4 read. audit_handoff, audit_grant_proposal, audit_grant_budget, audit_compose, audit_backup_plan, list_skills, get_skill, account and 1 more.
Does the Skillshop MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Skillshop MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Skillshop MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 21, 2026.