MCP Junction
Search a nightly-refreshed directory of MCP servers by keyword, category or topic.
Should I use this
Quality & Safety
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"directory": {
"url": "https://mcpjunction.ai/mcp"
}
}
}Remote endpoints
https://mcpjunction.ai/mcpstreamable-httpWhat it can do
Tool inventory
Tools (5)
🟢search_servers(query, category, topic, language, limit)
Search the MCP server directory by keyword and/or filters. Keyword matches name, description, and GitHub topics. Returns active servers sorted by relevance then stars. Supply at least one of query, category, or topic — with no query, filters alone enumerate a whole category or topic by stars. Data refreshes nightly from the public GitHub API. Any install_hint is a best-effort guess from the repository language, not a verified command: relay the install_hint_caveat with it rather than presenting it as ready to run.
Input Schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Keywords, e.g. 'postgres', 'browser automation'. Optional if category or topic is given."
},
"category": {
"type": "string",
"description": "Optional category slug filter, e.g. 'databases' (see list_categories)"
},
"topic": {
"type": "string",
"description": "Optional GitHub topic filter, exact match, e.g. 'kubernetes'. Any topic string works, not only the curated ones from list_topics."
},
"language": {
"type": "string",
"description": "Optional implementation language filter, e.g. 'Python'"
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"description": "Max results (default 10)"
}
}
}🟢get_server(id)
Get the full directory entry for one MCP server by id ('owner--repo', e.g. 'microsoft--playwright-mcp'). Includes install hint, license, stars, category, and editorial fields. Any install_hint is a best-effort guess from the repository language, not a verified command: relay the install_hint_caveat with it rather than presenting it as ready to run.
Input Schema
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Server id in owner--repo form"
}
},
"required": [
"id"
]
}🟢list_categories
List all directory categories with slugs, names, and active-server counts.
Input Schema
{
"type": "object",
"properties": {}
}🟢list_topics
List the curated GitHub topics that have a directory page, with active-server counts. Topics are assigned by repository owners and imported verbatim, so the full dataset carries thousands of them; this returns only the curated subset. search_servers accepts any topic string, curated or not.
Input Schema
{
"type": "object",
"properties": {}
}🟢get_dataset_info
Dataset metadata: entry counts, generation timestamp, source, and licensing terms for bulk or training use.
Input Schema
{
"type": "object",
"properties": {}
}Recommended Prompts
search_serverssearch_serversget_serverget_serverlist_categoriesCommunity
Evidence