PlugMCP directory MCP server
ai.plugmcp/directoryplugmcp.aistreamable-httpv0.1.4Scanned
Search MCP servers and agent skills, compare them, and get install configs for your client.
9 tools: 1 change things and 8 only read.
- Reads private data · 3
- Reads text others write · 2
- 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 PlugMCP directory MCP server can do
The PlugMCP directory MCP server is published by plugmcp.ai, a domain the MCP Registry verified. It has 9 tools. It can create or change data (1 tool: whats_new), but cannot delete data. 8 tools only read.
3 tools read private data (get_install, list_categories and get_skill); 2 tools bring in text other people can write (get_install and get_skill).
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 19, 2026, version 0.1.4.
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 1Claude Code: ask
whats_newServers added to the directory recently, best first, plus health changes.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.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Servers added to the directory recently, best first, plus health changes. Defaults to the last 7 days.
Annotations the server declares
- title: New MCP servers
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 8Show 8 read-only tools
compare_serversCompare two to five servers side by side by slug: trust signals, auth, hosting, transport, tools count, license.No findings
Why it is in this group
- The name "compare_servers" says "compare": a word for reading.
Description, as the server wrote it Compare two to five servers side by side by slug: trust signals, auth, hosting, transport, tools count, license.
Annotations the server declares
- title: Compare MCP servers
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_installThe exact config or command to install one server in one client: Cursor, Claude Code, Claude Desktop, VS Code, Windsurf, ChatGPT, Codex, Gemini CLI, Grok Build, Grok Bot, or plain …Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_install" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "chat": it reads messages.
- untrusted-inputThe description's first sentence says "chat": it reads messages, which other people can write.
Description, as the server wrote it The exact config or command to install one server in one client: Cursor, Claude Code, Claude Desktop, VS Code, Windsurf, ChatGPT, Codex, Gemini CLI, Grok Build, Grok Bot, or plain JSON. For Grok Bot the value is the message to send in its chat. Includes the config file path and a one-click deeplink when the client has one.
Annotations the server declares
- title: Get install config
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_serverDetails for one server by slug: description, tools, auth, transport, health, packages, and links.No findings
Why it is in this group
- The name "get_server" says "get": a word for reading.
Description, as the server wrote it Details for one server by slug: description, tools, auth, transport, health, packages, and links. include_readme adds the README (trimmed).
Annotations the server declares
- title: Get one MCP server
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_skillOne skill by slug: what it does, where the SKILL.md lives, and the install command for Cursor, Claude Code, Codex and Grok Build, plus the chat message that installs it in Grok Bot…Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_skill" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "chat": it reads messages.
- untrusted-inputThe description's first sentence says "chat": it reads messages, which other people can write.
Description, as the server wrote it One skill by slug: what it does, where the SKILL.md lives, and the install command for Cursor, Claude Code, Codex and Grok Build, plus the chat message that installs it in Grok Bot. include_body adds the SKILL.md text (trimmed).
Annotations the server declares
- title: Get one agent skill
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_categoriesDirectory categories with listing counts.Reads private dataNo findings
Why it is in this group
- The name "list_categories" says "list": a word for reading.
What it can reach
- private-dataThe description's first sentence says "directory": it reads files.
Description, as the server wrote it Directory categories with listing counts. Use a slug as the category filter in search_servers.
Annotations the server declares
- title: List categories
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
recommend_serversDescribe what the user wants to do in plain words.No findings
Why it is in this group
- The description's first verb is "describe": a word for reading.
Description, as the server wrote it Describe what the user wants to do in plain words. Returns the best three servers, each with why it fits, auth, remote or local, health, and the install snippet for the client.
Annotations the server declares
- title: Recommend MCP servers for a task
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_serversFind MCP servers by product name, publisher, or topic.No findings
Why it is in this group
- The name "search_servers" says "search": a word for reading.
Description, as the server wrote it Find MCP servers by product name, publisher, or topic. Ranked by relevance (exact name, then publisher, then tags and description); the product's own server comes first when there is one (jira finds Atlassian's), duplicates merged. Returns compact cards with trust signals; call get_install next. When the user describes a job rather than a product, recommend_servers is one call instead of two.
Annotations the server declares
- title: Search MCP servers
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_skillsFind agent skills (SKILL.md packs for Claude Code, Cursor, Codex, Grok Build and Grok Bot) by name, publisher or topic.No findings
Why it is in this group
- The name "search_skills" says "search": a word for reading.
Description, as the server wrote it Find agent skills (SKILL.md packs for Claude Code, Cursor, Codex, Grok Build and Grok Bot) by name, publisher or topic. Call get_skill for the install command.
Annotations the server declares
- title: Search agent skills
- 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 outbound.
- Reads private data3
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write2
- 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 19, 2026, 17:22 UTC, unchanged since Nov 5, 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://plugmcp.ai/mcp-server: tools/list returned 9 tools to an anonymous client, including whats_new (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 changed.~2 changedView diff
- Changed:recommend_serversOnly readsinputSchema
- Changed:search_serversOnly readsdescriptioninputSchema
Install
Pinned to version 0.1.4. Values in angle brackets are yours to fill in.
claude mcp add --transport http directory https://plugmcp.ai/mcp-serverclaude mcp add --transport http directory https://plugmcp.ai/mcp-serverRun 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__directory__search_servers",
"mcp__directory__get_server",
"mcp__directory__get_install",
"mcp__directory__list_categories",
"mcp__directory__compare_servers",
"mcp__directory__recommend_servers",
"mcp__directory__search_skills",
"mcp__directory__get_skill"
],
"ask": [
"mcp__directory__whats_new"
],
"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 directory. Review it before you use it.
Capability tags behind 3 rules
- mcp__directory__get_install private-data, untrusted-input
- mcp__directory__list_categories private-data
- mcp__directory__get_skill private-data, 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/ai.plugmcp/directory/verify?hash=cd6d733f24be06e186a622dc2ceefc35402eecb13785a929e4e2bb1a47bf40e3" | jq -e '.changed == false'Pinned hash cd6d733f24be, from Nov 19, 2026, 11:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ai.plugmcp/directory/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ai.plugmcp/directory)Source: MCP Registry · repository. Synced Nov 5, 2026, 14:17 UTC.
PlugMCP directory MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the PlugMCP directory MCP server safe?
- No scan can promise that. What its definitions show: 9 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 PlugMCP directory MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the PlugMCP directory 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 PlugMCP directory MCP server have?
- 9 tools: 1 write, 8 read. whats_new, search_servers, get_server, get_install, list_categories, compare_servers, recommend_servers, search_skills and 1 more.
Does the PlugMCP directory MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the PlugMCP directory MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the PlugMCP directory MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 19, 2026. Every change is on this page and in its Atom feed.