PlugMCP directory

ai.plugmcpPublished by plugmcp.aiOfficial publisherv0.1.4Updated Nov 5, 2026

Search MCP servers and agent skills, compare them, and get install configs for your client.

VerifiedStreamable HTTPWeb executableKnowledge & MemoryDeveloper Tools

Overview

AI-generated overview

Searches a directory of 70,000+ MCP servers and agent skills, compares them, and returns install configs for the user's client.

What you can do
  • Search and browse the directory: keyword search for servers, category listings with counts, recently added servers, and plain-language recommendations
  • Inspect and compare: full details for one server (tools, auth, transport, health, packages, optional README) and side-by-side comparison of two to five servers
  • Get install instructions: exact config or command for Cursor, Claude Code, Claude Desktop, VS Code, Windsurf, ChatGPT, Codex, Gemini CLI, Grok Build, Grok Bot, or plain JSON
  • Find agent skills: search SKILL.md packs and get one skill's details, install command, and optional SKILL.md text
When to use it
Useful when the user wants to find, evaluate, or install an MCP server or agent skill and needs the right config for their specific client. Handy for discovery questions such as what is new this week or which of two servers fits better.
Requirements
Either the remote endpoint at plugmcp.ai over Streamable HTTP, or the npm package plugmcp-mcp run locally with npx (Node.js). No account needed; an optional pb_live_ key can be passed as PLUGMCP_API_KEY or as an Authorization Bearer header. Network access to plugmcp.ai.
Before you install
All tools are read-only, but the install snippets it returns point at third-party servers and skills that you should review before running. The optional API key is a secret; keep it in the environment or header rather than in shared config. Without a key, calls are rate-limited per IP address and may wait when the directory is busy.

Installation

In SourceWeft

  1. Open PlugMCP directory in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/ai.plugmcp%2Fdirectory/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "plugmcp-directory": {
      "type": "http",
      "url": "https://plugmcp.ai/mcp-server"
    }
  }
}

README

[PlugMCP]

plugmcp-mcp

One MCP server that finds the rest. Your agent searches 70,000+ MCP servers and agent skills, compares them, and gets the exact install config for your client.

[Add to Cursor] [Install in VS Code]

[npm] [MCP Registry] [MIT] [CI]

Ask your agent

Once it is connected, ask in plain words:

  • "Find an MCP server that lets Cursor query my Postgres database, and install it."
  • "Compare the GitHub and GitLab MCP servers."
  • "What MCP servers came out this week?"
  • "Give me the Claude Code command for the Linear MCP server."
  • "Find an agent skill for editing PDFs and give me the message to install it in Grok Bot."

Install

The fastest path needs no install at all. The directory is a remote MCP server at:

https://plugmcp.ai/mcp-server

Use this package when your client only runs local (stdio) servers, or when you want the server in a lockfile.

Claude Code

sh
claude mcp add --transport http plugmcp https://plugmcp.ai/mcp-server# or local:claude mcp add plugmcp -- npx -y plugmcp-mcp

Cursor, Windsurf, Claude Desktop, and any mcpServers JSON

json
{  "mcpServers": {    "plugmcp": {      "command": "npx",      "args": ["-y", "plugmcp-mcp"]    }  }}

VS Code (.vscode/mcp.json)

json
{  "servers": {    "plugmcp": { "type": "http", "url": "https://plugmcp.ai/mcp-server" }  }}

Codex CLI

sh
codex mcp add plugmcp --url https://plugmcp.ai/mcp-server

Grok Bot

Grok Bot has no config file. Send this in a Grok Bot chat and confirm the card:

Add a custom MCP server called plugmcp at https://plugmcp.ai/mcp-server

Every Bot on your account gets it; attach it to a task with @. Then ask for any server or skill with grok-bot as the client, and the reply is the message that adds that one too.

Grok Build and grok.com

  • Grok Build: grok mcp add --transport http plugmcp https://plugmcp.ai/mcp-server
  • grok.com: open Connectors, choose New Connector, then Custom, and paste https://plugmcp.ai/mcp-server.

ChatGPT

Settings, then Connectors, then Add. Name plugmcp, URL https://plugmcp.ai/mcp-server.

API key (optional)

Every tier is paced, so one busy agent cannot use the whole day at once:

Per minutePer hourPer day
No key (per IP)51020
Free account key1560400
Paid plan key300no cap20,000

When a limit is hit, the tool result says which one and when it resets. Calls without a key may also wait while the directory is busy; key holders keep working. Create a pb_live_ key at plugmcp.ai/app and pass it as PLUGMCP_API_KEY:

json
{  "mcpServers": {    "plugmcp": {      "command": "npx",      "args": ["-y", "plugmcp-mcp"],      "env": { "PLUGMCP_API_KEY": "pb_live_..." }    }  }}

For the remote URL, send it as Authorization: Bearer pb_live_.... Details are in auth.md.

Tools

Every tool is read-only.

ToolWhat it does
search_serversKeyword search with filters for remote, official, and client
recommend_serversRanked picks for a task described in plain words
get_serverOne server: tools, auth, packages, health, and optionally the README
get_installThe exact config for Cursor, Claude Code, Claude Desktop, VS Code, Windsurf, ChatGPT, Codex, Gemini CLI, Grok Build, Grok Bot, or plain JSON
compare_serversSide by side for two to five servers
whats_newServers added recently
list_categoriesCategories with counts
search_skillsSearch agent skills (SKILL.md)
get_skillOne skill with install commands for Cursor, Claude Code, Codex, and Grok Build, plus the Grok Bot message

How it works

plugmcp-mcp is a small stdio server built on the official MCP TypeScript SDK. It forwards tools/list and tools/call to https://plugmcp.ai/mcp-server over Streamable HTTP. The upstream connection opens on the first call and reconnects after a network error. Nothing is stored locally.

VariableDefaultPurpose
PLUGMCP_API_KEYnoneOptional pb_live_ key
PLUGMCP_URLhttps://plugmcp.ai/mcp-serverDirectory endpoint

Develop

sh
npm cinpm test        # build, then unit tests against an in-memory upstreamnpm run smoke   # run the built server over stdio against plugmcp.ai

Release

Push a v* tag that matches package.json. The publish workflow runs the tests, publishes to npm (NPM_TOKEN secret), then publishes server.json to the MCP Registry as ai.plugmcp/directory, signed with the plugmcp.ai domain key (MCP_REGISTRY_PRIVATE_KEY secret).

Related

License

MIT

Source: README.md at commit c3b9696

Tools

9

search_servers

Search MCP servers

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.

Parameterslimitqueryclientcursorfieldscategoryremote_onlyvoice_readyofficial_onlyverified_onlyresponse_format

get_server

Get one MCP server

Details for one server by slug: description, tools, auth, transport, health, packages, and links. include_readme adds the README (trimmed).

Parametersslugrequiredinclude_readmeresponse_format

get_install

Get install config

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.

Parametersslugrequiredclient

list_categories

List categories

Directory categories with listing counts. Use a slug as the category filter in search_servers.

Takes no parameters.

whats_new

New MCP servers

Servers added to the directory recently, best first, plus health changes. Defaults to the last 7 days.

Parameterslimitsincecursorcategoryremote_onlyresponse_format

compare_servers

Compare MCP servers

Compare two to five servers side by side by slug: trust signals, auth, hosting, transport, tools count, license.

Parametersslugsrequiredresponse_format

recommend_servers

Recommend MCP servers for a task

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.

Parameterstaskrequiredlimitclientconstraintsresponse_format

search_skills

Search agent skills

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.

Parameterslimitquerycursorcategoryresponse_format

get_skill

Get one agent skill

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).

Parametersslugrequiredinclude_bodyresponse_format

Version history

2
  1. v0.1.4LatestNov 5, 2026
  2. v0.1.1Nov 5, 2026

Score

100% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts