Forge runs on your own machine — the client starts it, so there is no endpoint to ping. 106 installs a week from npm. Last commit 31 May 2026.
MCP server for Forge, Voxell's hosted text-embedding API. Tools: embed and list_models.
Today is the operative word: we check Forge every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add forge -- npx -y @voxell/forge-mcp
{
"mcpServers": {
"forge": {
"args": [
"-y",
"@voxell/forge-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.forge]
command = "npx"
args = ["-y", "@voxell/forge-mcp"]
{
"mcpServers": {
"forge": {
"args": [
"-y",
"@voxell/forge-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"forge": {
"args": [
"-y",
"@voxell/forge-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
FORGE_API_KEY (Your Forge API key — create one at https://dash.voxell.ai (free tokens to start, no card).).
The author declared them in the registry entry; get the values from the project itself.
MCP server for the OpenAI ChatGPT API — chat, vision, and embeddings
MCP server for the xAI Grok API — chat, vision, search, and embeddings
35 AI tools for image/video generation, TTS, transcription, OCR & embeddings via deAPI
30 GPU-powered AI services as MCP tools. LLM, image, video, audio, embeddings & more.
RAG memory for LLM agents over Garnet Vector Sets: store text as embeddings, recall by meaning.
MCP server for NVIDIA NIM - 50+ LLMs, multimodal, image gen, embeddings, reranking
MCP server for GigaChat — AI chat, embeddings, image generation (Russia)
Local-first memory for coding agents — MCP server, single SQLite file, local embeddings
Answers built from our own checks of this server.