Summary
A meta-tool for discovering and installing other MCP servers. It aggregates three major registries (Official MCP, Glama, and Smithery) into a single searchable SQLite database with FTS5. You get four tools: search_mcp_servers for keyword queries, get_server_details for specs and documentation, get_install_config to generate platform-specific JSON configs, and browse_categories for exploration. Useful when you're building workflows and need to find the right server without manually checking multiple registries. The Python API exposes the same functions if you want to build automation around server discovery. Ships as a pip package that runs as a standard stdio MCP server.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →mcp-server-find
MCP server discovery - find and install MCP servers from Official Registry, Glama, and Smithery.
mcp-name: io.github.daedalus/mcp-server-find
Install
pip install mcp-server-find
MCP Server
mcp-server-find is an MCP server that helps AI agents discover, evaluate, and install other MCP servers. It aggregates data from:
- Official MCP Registry
- Glama (glama.ai)
- Smithery (registry.smithery.ai)
Claude Desktop
{
"mcpServers": {
"mcp-server-find": {
"command": "python",
"args": ["-m", "mcp_server_find"]
}
}
}
Usage
from mcp_server_find import search_servers, get_server_details, get_install_config
# Initialize database
from mcp_server_find.db import init_database
conn = init_database()
# Search for MCP servers
results = search_servers(conn, "postgres", 10)
# Get server details
detail = get_server_details(conn, "io.modelcontextprotocol/filesystem")
# Generate install config
config = get_install_config(conn, "io.modelcontextprotocol/filesystem", "claude-desktop")
MCP Tools
search_mcp_servers: Search for MCP servers by keywordget_server_details: Get detailed server informationget_install_config: Generate install config for a platformbrowse_categories: Browse MCP server categories
API
Core Functions
init_database(db_path?: str) -> sqlite3.Connection- Initialize SQLite with FTS5search_servers(conn, query, limit?, filters?) -> list[SearchResult]- Search MCP serversget_server_details(conn, name_or_slug) -> ServerDetail | None- Get detailed server infoget_install_config(conn, name_or_slug, platform) -> InstallConfig- Generate install configlist_categories(conn) -> list[Category]- List all categoriesget_servers_by_category(conn, category, limit?) -> list[dict]- Get servers in category
Development
git clone https://github.com/daedalus/mcp-server-find.git
cd mcp-server-find
pip install -e ".[test]"
# Run tests
pytest
# Format
ruff format src/ tests/
# Lint
ruff check src/ tests/
# Type check
mypy src/
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →