In-depth architectural comparison of the Forge MCP and Searchcraft MCP Server MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.
At a Glance & Executive Verdict
Forge MCP
Search & Data Extraction · Local stdio
Quality: 59/100 (Good) | Auth: API Key required
Searchcraft MCP Server
Search & Data Extraction · Remote HTTP/SSE
Quality: 53/100 (Good) | Auth: API Key required
Verdict Summary: Choose Forge MCP if you need specialized Search & Data Extraction tools running via a local process. Choose Searchcraft MCP Server if your workspace requires Search & Data Extraction integration with remote web transport. Both servers can be configured concurrently in your client's mcpServers manifest.
Which MCP Server Should You Choose?
Choose Forge MCP when:
You need dedicated capabilities in the Search & Data Extraction domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: API Key required (Freemium).
Official MCP server for Forge, Voxell's hosted text-embedding API. Generate vector embeddings (turbo 1024d, pro 2560d, ultra 4096d; Matryoshka truncation) for semantic search and RAG. npx -y @voxell/forge-mcp
Official MCP server for managing Searchcraft clusters, creating a search index, generating an index dynamically given a data file and for easily importing data into a search index given a feed or local json file.
Category & Scope
Tools & Capabilities Breakdown
Forge MCP Tools (2)
embed
Generate vector embeddings for one or more texts with Forge (Voxell's hosted embedding API). Use it to turn text into vectors for semantic search, RAG, clustering, or similarity. Set input_type='query' for search queries and 'document' for content you index. Choose model by quality/cost: turbo (1024d, fast, default) -> pro (2560d) -> ultra (4096d, #4 on MTEB English, top usable). Optionally set dim to truncate (Matryoshka, re-normalized).
list_models
List the available Forge embedding models and their dimensions. Call this to pick a model before embedding.
Searchcraft MCP Server Tools (48)
create_index
Create a new index with the specified schema. This will empty the index if it already exists.
delete_index
Delete an index and all its documents permanently.
Ready-to-Paste Client Configurations
Paste either (or both) of these JSON server blocks into your client config file (e.g. claude_desktop_config.json or ~/.cursor/mcp.json).
Forge MCP is categorized under Search & Data Extraction and uses a local stdio subprocess. In contrast, Searchcraft MCP Server belongs to Search & Data Extraction using remote streaming HTTP/SSE transport. Select Forge MCP when you need capabilities focused on search & data extraction and Searchcraft MCP Server when you require tools for search & data extraction.