Poe Algolia MCP Proxy
An OpenAI-compatible proxy that forwards chat completions to Poe API and transparently executes Algolia MCP tool calls on the server side.
README
Poe API + Algolia MCP Proxy
OpenAI-compatible proxy that forwards chat completions to Poe API, and transparently executes Algolia MCP tool calls on the server side.
Converted from Deno to Node.js for deployment on Render.
Features
- OpenAI-compatible
POST /v1/chat/completions - Simulated function calling via system prompt injection
- Auto-executes Algolia MCP tools (
algolia_*) and feeds results back to the model - Non-Algolia tools are returned as standard OpenAI
tool_callsfor the client to run - Streaming (
stream: true) and non-streaming modes - CORS enabled
Local development
npm install
npm start
# or with auto-reload:
npm run dev
Server listens on PORT (default 10000).
curl http://localhost:10000/healthz
curl http://localhost:10000/
Deploy to Render
Option A: Blueprint (render.yaml)
- Push this repo to GitHub/GitLab
- In Render Dashboard → New → Blueprint
- Connect the repo; Render reads
render.yaml
Option B: Manual Web Service
| Setting | Value |
|---|---|
| Runtime | Node |
| Build Command | npm install |
| Start Command | npm start |
| Node Version | 18+ (recommended 20) |
Render injects PORT automatically — the app already reads process.env.PORT.
Environment variables (optional)
| Key | Default |
|---|---|
PORT |
set by Render |
POE_API_BASE_URL |
https://api.poe.com/v1 |
ALGOLIA_MCP_URL |
Algolia MCP endpoint |
Poe API keys are passed per-request via
Authorization: Bearer <POE_API_KEY>. You do not need to store the Poe key as a Render env var unless you want a server-side default.
API
curl https://YOUR-SERVICE.onrender.com/v1/chat/completions \
-H "Authorization: Bearer $YOUR_POE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "Claude-Sonnet-4.6",
"messages": [{"role": "user", "content": "幫我查一下如何加入賽事"}],
"stream": false,
"tools": [
{
"type": "function",
"function": {
"name": "algolia_index_help",
"description": "Search the Algolia index help",
"parameters": {
"type": "object",
"properties": {
"query": { "type": "string", "description": "搜尋關鍵字" }
},
"required": ["query"]
}
}
}
]
}'
Also supports prefixed routes: POST /:prefix/v1/chat/completions.
Endpoints
| Method | Path | Description |
|---|---|---|
| GET | / |
Help text |
| GET | /healthz |
Health check |
| POST | /v1/chat/completions |
Chat completions |
| POST | /:prefix/v1/chat/completions |
Prefixed chat completions |
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.