Tripleshot MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Tripleshot MCP Serversearch prompts for 'next.js'"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-tripleshot-http
A clean, Streamable HTTP MCP server (no stdio) that fronts api.tripleshot.ai so Claude/Cursor can search prompts and "prompt itself." Built with the MCP SDK’s StreamableHTTPServerTransport, handling both SSE (GET) and JSON-RPC (POST).
What you get (tools)
list_communities(): Return communities from
/api/public/communities.search_prompts(q, community?, limit?, offset?): Search
/api/public/prompts/search.get_prompt(id): Get prompt by ID via
/api/public/prompts/:id.trending_prompts(community?, limit?): Trending via
/api/public/prompts/trending.featured_prompts(limit?): Featured via
/api/public/prompts/featured.render_prompt(id, variables={}): Fetches a prompt and fills
{{placeholders}}in its body.
Project setup
Requirements: Node 18+.
git clone <this repo>
cd mcp-tripleshot-http
npm cipackage.json scripts:
{
"scripts": {
"dev": "tsx src/server.ts",
"build": "tsc -p .",
"start": "node --enable-source-maps dist/server.js"
}
}Optional .env (create at repo root):
TRIPLESHOT_BASE=https://api.tripleshot.ai
HTTP_TIMEOUT_MS=15000
PORT=8787
BIND=127.0.0.1
# If you publish this, add a shared secret
MCP_TOKEN=replace-meServer (Streamable HTTP)
The HTTP endpoint is exposed at /mcp using StreamableHTTPServerTransport.
GET
/mcp: Server-Sent Events stream (keepalive)POST
/mcp: JSON-RPC 2.0 requests
There’s also a health check at GET / that returns { ok: true, mcp: "/mcp" }.
Build & run
npm run dev
# or
npm run build && npm run startSmoke tests (local)
curl http://127.0.0.1:8787/
curl -N -H "Accept:text/event-stream" http://127.0.0.1:8787/mcpIf you set MCP_TOKEN, include the header:
curl -H "Authorization: Bearer replace-me" http://127.0.0.1:8787/Connect clients
Cursor (local)
First start the server:
npm run devThen add to ~/.cursor/mcp.json:
{
"mcpServers": {
"tripleshot-http": {
"type": "streamable-http",
"url": "http://127.0.0.1:8787/mcp"
}
}
}With token:
{
"mcpServers": {
"tripleshot": {
"type": "streamable-http",
"url": "http://127.0.0.1:8787/mcp",
"headers": { "Authorization": "Bearer replace-me" }
}
}
}Claude Desktop
Claude Desktop requires using mcp-remote as a bridge to connect to HTTP-based MCP servers.
Add to your Claude Desktop configuration file:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
Basic configuration:
{
"mcpServers": {
"tripleshot-http": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"http://127.0.0.1:8787/mcp"
]
}
}
}With authentication token:
{
"mcpServers": {
"tripleshot-http": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"http://127.0.0.1:8787/mcp",
"--header",
"Authorization: Bearer ${MCP_TOKEN}"
],
"env": {
"MCP_TOKEN": "your-token-here"
}
}
}
}After updating the configuration, restart Claude Desktop to apply changes. The tools will appear automatically in the UI.
Example model flow
Discover:
{ "tool": "search_prompts", "args": { "q": "next.js auth", "limit": 5 } }Inspect:
{ "tool": "get_prompt", "args": { "id": 82 } }Render / prompt itself:
{
"tool": "render_prompt",
"args": { "id": 82, "variables": { "projectName": "Acme", "provider": "Clerk" } }
}Use the rendered text as the next system/assistant message.
Deploy notes
Any Node host works (Vercel/Render/Fly/Cloud Run). Ensure keep‑alive for SSE
GET /mcp.If public, set
MCP_TOKENand restrict inbound origins/IPs at the proxy.If you later add write ops, create a separate admin MCP server.
License
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Remote MCP server exposing SMI Aware tools, resources, and skills over Streamable HTTP.
AI Reasoning Cache & Consensus Layer with 11 MCP tools via Streamable HTTP.
Streamable HTTP MCP server exposing planner flows, tasks, and squads.
Search and compare flight offers through a cache-aware Streamable HTTP MCP server for AI agents.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables users to search, browse, and retrieve AI prompts from the Tripleshot public API. Provides access to community prompts, trending content, and template rendering capabilities through a durable MCP server interface.-
- AlicenseBqualityAmaintenanceMCP server that exposes any LynxPrompt instance to LLMs, enabling browsing, searching, and managing AI configuration blueprints and prompt hierarchies.643 npm2GPL 3.0
- AlicenseAqualityDmaintenanceEnables storage, versioning, and retrieval of prompts with rich metadata via MCP tools, supporting stdio and SSE transports.37 npm3ISC
- FlicenseNot gradedqualityCmaintenanceProvides a production-oriented MCP server exposing tools, resources, and prompts over Streamable HTTP with JWT authentication and per-tool RBAC, enabling Amazon Bedrock Claude clients to securely invoke MCP capabilities.-