VoxellInc/forge-mcp
by Various
[](https://glama.ai/mcp/servers/VoxellInc/forge-mcp) ๐๏ธ ๐ โ๏ธ - Official MCP server for Forge, Voxell's hosted text-embedding API. Generate vector embeddings (turbo 1024d, pro 256
MCP
VoxellInc/forge-mcp
Added 7 June 2026
Overview
An MCP server that provides access to Voxell's hosted text-embedding API, generating vector embeddings in two dimensions: turbo (1024d) and pro (256d). It integrates with MCP-compatible clients to enable semantic search, clustering, and retrieval-augmented generation workflows.
Best for
Best for
Developers building MCP-based tools that need quick, hosted text embeddings for semantic search or RAG.
Use cases
- Generate embeddings for semantic search over documents
- Encode text for clustering or similarity comparisons
- Feed embeddings into a vector database for RAG pipelines
How to use
Install
claude mcp add forge -e FORGE_API_KEY=your-key-here -- npx -y @voxell/forge-mcp Tools exposed
input_typeFORGE_API_KEYFORGE_BASE_URL
Tested with
Claude Desktop, Claude Code, Cursor, Windsurf, Cline, VS Code, ChatGPT
Notes
An MCP server that provides access to Voxellโs hosted text-embedding API, generating vector embeddings in two dimensions: turbo (1024d) and pro (256d). It integrates with MCP-compatible clients to enable semantic search, clustering, and retrieval-augmented generation workflows.
0 stars on GitHub. Last updated 2026-05-31. Licensed MIT.
Use cases
- Generate embeddings for semantic search over documents
- Encode text for clustering or similarity comparisons
- Feed embeddings into a vector database for RAG pipelines
Pros
- Simple MCP interface for embedding generation
- Two embedding dimensions to balance speed and precision
- Hosted API removes need for local model deployment
Cons
- No offline or self-hosted option
- Limited to two embedding models
- Dependent on Voxell API availability and pricing
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Simple MCP interface for embedding generation
- Two embedding dimensions to balance speed and precision
- Hosted API removes need for local model deployment
Cons
- No offline or self-hosted option
- Limited to two embedding models
- Dependent on Voxell API availability and pricing
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
Milvus
Community
Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search
Qdrant
Community
Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
Chroma
Community
Search infrastructure for AI
Get the free Developerโs Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.
