RigBase MCP
A free, public, read-only MCP server that allows AI assistants to query a database of 187 real home AI rigs and 442 measured local LLM generation speeds. It provides tools to search builds by hardware constraints, check if specific models can run on given GPUs, find the best GPU for a model, and retrieve detailed build information with source citations.
Endpoint and access
No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.
https://getrigbase.com/mcpWhat you can do with it
- Search for measured local-LLM builds filtered by GPU, model, VRAM, or price
- Check if a specific model can run on a given GPU configuration
- Find the fastest measured GPU setup for a specific AI model
- Retrieve detailed build information including source credits and URLs
Source and maintenance
Protocol and capabilities
- Server
- rigbase 1.0.0
- MCP protocol
- 2025-03-26
- Tools
- 4 advertised
- Resources
- Not advertised
- Resource templates
- Not advertised
- Prompts
- Not advertised
{
"tools": {
"listChanged": false
}
}Server-provided instructions
Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.
Tools
4 advertised
search_builds
Search RigBase measured home AI builds. Filter by GPU name, model name, minimum VRAM (GB), and/or maximum build cost. Returns top matches with tok/s, quant, engine, source credit and canonical getrigbase.com URL. Never invents numbers.
{
"type": "object",
"properties": {
"gpu": {
"type": "string",
"description": "Substring to match in the GPUs field (e.g. \"3090\", \"DGX Spark\", \"5090\")."
},
"limit": {
"type": "integer",
"description": "Max builds to return (default 8, max 25)."
},
"model": {
"type": "string",
"description": "Substring to match a measured model name (e.g. \"Qwen3.8\", \"gpt-oss 120B\")."
},
"currency": {
"type": "string",
"description": "Optional currency filter: EUR or USD."
},
"max_price": {
"type": "number",
"description": "Maximum reported build cost (same currency as the build, usually EUR or USD)."
},
"min_vram_gb": {
"type": "number",
"description": "Minimum total VRAM / unified memory in GB."
}
}
}{
"readOnlyHint": true,
"openWorldHint": false
}can_it_run
Ask whether a given GPU setup can run a model. Returns measured RigBase results when available; otherwise a VRAM-fit estimate clearly labelled as an estimate (weights arithmetic, not a measured speed). Advises against quants below Q4. Always includes source credit and URLs for measured rows.
{
"type": "object",
"required": [
"gpu",
"model"
],
"properties": {
"gpu": {
"type": "string",
"description": "GPU or system name, e.g. \"RTX 3090\", \"RTX 5090\", \"DGX Spark\", \"Apple Silicon Mac\"."
},
"count": {
"type": "integer",
"description": "How many identical GPUs / nodes (default 1)."
},
"model": {
"type": "string",
"description": "Model name, e.g. \"Qwen3.8 27B\", \"gpt-oss 120B\", \"Gemma 4 31B\"."
},
"quant": {
"type": "string",
"description": "Optional quant for the estimate (default Q4_K_M). Avoid below Q4."
}
}
}{
"readOnlyHint": true,
"openWorldHint": false
}best_gpu_for_model
Return the fastest measured RigBase result for a model, plus tok/s per euro where a build cost or known GPU street price exists. Includes source credit and canonical URL.
{
"type": "object",
"required": [
"model"
],
"properties": {
"limit": {
"type": "integer",
"description": "How many top results to return (default 5, max 15)."
},
"model": {
"type": "string",
"description": "Model name or substring, e.g. \"Gemma 4 31B\" or \"Qwen3.8\"."
}
}
}{
"readOnlyHint": true,
"openWorldHint": false
}get_build
Fetch one RigBase build by slug (e.g. "dual-3090-ryzen-3700x"). Returns parts, measured results, source credit and canonical URL.
{
"type": "object",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string",
"description": "Build slug from a RigBase /builds/.../ URL."
}
}
}{
"readOnlyHint": true,
"openWorldHint": false
}Prompts
Not advertised
Resources
Not advertised
30-day availability
Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.
- Successful checks
- 1 of 1 (100%)
- Average latency
- 440 ms
- 95th percentile latency
- 440 ms
Maintenance history
Public check and source-refresh events. Editorial and ownership records remain private.
- · probe · passed · 440 ms · metadata changed · 4 tool(s)
Connect from your client
Each snippet registers the same endpoint; pick the client you use.
Claude Code
claude mcp add --transport http rigbase-mcp https://getrigbase.com/mcpCodex
codex mcp add rigbase-mcp --url https://getrigbase.com/mcpCursor
{
"mcpServers": {
"rigbase-mcp": {
"url": "https://getrigbase.com/mcp"
}
}
}Cline
{
"mcpServers": {
"rigbase-mcp": {
"type": "streamableHttp",
"url": "https://getrigbase.com/mcp",
"disabled": false
}
}
}VS Code
{
"servers": {
"rigbase-mcp": {
"type": "http",
"url": "https://getrigbase.com/mcp"
}
}
}Gemini CLI
gemini mcp add --transport http rigbase-mcp https://getrigbase.com/mcpClaude Desktop
{
"mcpServers": {
"rigbase-mcp": {
"url": "https://getrigbase.com/mcp"
}
}
}Windsurf
{
"mcpServers": {
"rigbase-mcp": {
"serverUrl": "https://getrigbase.com/mcp"
}
}
}Let your agent find its tools
Find servers like RigBase MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.
Other ai and machine learning servers
Do you run RigBase MCP?
Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.