MCP server by toolprint · ★ 155 · updated 11 months ago
Dynamically expose tools from proxied servers based on an Agent Persona
Choose your AI client and copy the config.
Add to claude_desktop_config.json — macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\. Then restart Claude. Setup guide
{
"mcpServers": {
"hypertool-mcp": {
"command": "npx",
"args": [
"-y",
"@toolprint/hypertool-mcp"
]
}
}
}Or add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project). Setup guide
{
"mcpServers": {
"hypertool-mcp": {
"command": "npx",
"args": [
"-y",
"@toolprint/hypertool-mcp"
]
}
}
}Or add to .vscode/mcp.json in your workspace. Setup guide
{
"servers": {
"hypertool-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@toolprint/hypertool-mcp"
]
}
}
}Cascade → Actions → Open MCP config file (often ~/.config/devin/mcp_config.json). Setup guide
{
"mcpServers": {
"hypertool-mcp": {
"command": "npx",
"args": [
"-y",
"@toolprint/hypertool-mcp"
]
}
}
}Run in your terminal: Setup guide
claude mcp add hypertool-mcp -- npx -y @toolprint/hypertool-mcpCLI or add to ~/.codex/config.toml. Setup guide
codex mcp add hypertool-mcp -- npx -y @toolprint/hypertool-mcp[mcp_servers.hypertool-mcp]
command = "npx"
args = ["-y", "@toolprint/hypertool-mcp"]Cline panel → Configure MCP Servers, or ~/.cline/data/settings/cline_mcp_settings.json. Setup guide
{
"mcpServers": {
"hypertool-mcp": {
"command": "npx",
"args": [
"-y",
"@toolprint/hypertool-mcp"
]
}
}
}Run the server directly:
npx -y @toolprint/hypertool-mcpTest/reference server that exercises every MCP feature (prompts, tools, resources, sampling). Built for MCP client developers, not for everyday use.
Fetches web pages and converts HTML to markdown so LLMs can read web content. Caution: can reach local/internal IPs.
Node.js server for filesystem operations: read/write files, create/list/delete directories, move and search files, with configurable allowed directories.
Tools to read, search and manipulate Git repositories (status, diff, log, commit, branches) via LLMs.
Basic persistent memory using a local knowledge graph of entities, relations and observations, so the assistant can remember information about you across chats.
Provides a tool for dynamic, reflective problem-solving: break problems into steps, revise thoughts, and branch into alternative reasoning paths.