RigBase MCP server
Commit Nov 6, 2026Access measured local-LLM performance benchmarks and hardware build data to compare token generation speeds across different AI rigs.
Also known as getrigbase/rigbase-data, rigbase-data
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 1.0.1
- Last commit
- Nov 6, 2026
- License
- CC-BY-4.0
What is RigBase MCP?
RigBase accesses measured local-LLM performance benchmarks and hardware build data to compare token generation speeds across different AI rigs.
Summary generated from the project's README
About RigBase MCP server
RigBase provides access to a normalized dataset of local large language model performance benchmarks. It is designed for developers and hardware enthusiasts who need to compare token generation speeds across different computer configurations. The server serves data collected from various public sources like llama.cpp discussions, GitHub repositories, and technical blogs, covering 150 builds and 51 different models.
Users interact with this data through CSV or JSON files containing specific hardware metrics such as GPU count, VRAM capacity, CPU type, and power consumption. The dataset includes measured tokens per second, prefill speeds, and time to first token metrics. Because the data is aggregated from external sources, it is intended for comparative analysis rather than serving as a primary measurement tool. Users can filter results by speculative decoding methods or specific engines to find relevant performance benchmarks for their own hardware setups.
What you can do with it
- 1Evaluate decoding methodsFilter benchmarks to see only plain decoding speeds without speculative decoding methods.
- 2Verify measurement sourcesTrace a specific performance metric back to its original public documentation or blog.
Written from the project's README. Every use case is checked against a quote from it.
How to install RigBase MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall RigBase MCP in Claude Code
$ claude mcp add --transport http rigbase-data https://getrigbase.com/mcpInstall RigBase MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"rigbase-data": {
"url": "https://getrigbase.com/mcp"
}
}
}Install RigBase MCP in VS Code
.vscode/mcp.json
{
"servers": {
"rigbase-data": {
"type": "http",
"url": "https://getrigbase.com/mcp"
}
}
}Install RigBase MCP in VS Code CLI
$ code --add-mcp '{"name":"rigbase-data","type":"http","url":"https://getrigbase.com/mcp"}'Install RigBase MCP in Codex
$ codex mcp add rigbase-data --url https://getrigbase.com/mcpInstall RigBase MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.rigbase-data] url = "https://getrigbase.com/mcp"
Install RigBase MCP in Gemini CLI
$ gemini mcp add -s user --transport http rigbase-data https://getrigbase.com/mcpInstall RigBase MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"rigbase-data": {
"url": "https://getrigbase.com/mcp",
"type": "http"
}
}
}Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablegetrigbase/rigbase-data is public and reachablegithub.com/getrigbase/rigbase-data ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)CC-BY-4.0 is not OSI-approvedspdx.org/licenses/CC-BY-4.0.html ↗Finding
- Commit or release in the last yearLast commit or release 2026-11-07github.com/getrigbase/rigbase-data ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeinitialize answered with protocol 2025-03-26 in 96 msPass
README
View on GitHubRigBase data
Measured local-LLM speeds on real home hardware.
getrigbase.com · Live download · Hugging Face · Licence: CC BY 4.0
This repository mirrors the free RigBase dataset:
| Builds | 150 |
| Measured results | 358 |
| Models | 51 |
| Snapshot generated | 2026-10-27 (from getrigbase.com/data/) |
Every number links to its original public source (llama.cpp discussions, llama-bench databases, blogs, GitHub repos, Mia's AI Lab recipes, and similar). RigBase collects and normalises these numbers; it does not re-measure them or invent estimates for the tps column.
Files
builds.csv— one row per measured result (358 rows)builds.json— one object per build with parts + nested resultsLICENSE— CC BY 4.0CITATION.cff— machine-readable citation
Quick start
# CSV
curl -LO https://getrigbase.com/data/builds.csv
# Or clone this repo
git clone https://github.com/getrigbase/rigbase-data.git
import pandas as pd
df = pd.read_csv("builds.csv")
# Plain decode only (drop speculative / MTP / draft runs):
plain = df[df["spec_decode"].fillna("none").eq("none")]
print(plain.groupby("model")["tps"].max().sort_values(ascending=False).head(10))
Columns (CSV)
| column | meaning |
|---|---|
build_slug, build_title, page_url |
Build id, name, and RigBase page |
gpus, vram_gb, cpu, ram, power |
Hardware as stated by the source |
model, quant, engine |
What was run, as stated by the source |
tps |
Generation (decode) tokens/sec reported by the source |
spec_decode |
none, or the speculative-decoding method (MTP, DFlash, …) |
prefill_tps, prefill_tokens, prefill_metric |
Prefill speed only where the source reports one; never estimated |
est_ttft_8k_s_calculated |
Calculated (not measured): 8192 / prefill_tps when prefill_tokens ≥ 512 |
ttft_s_measured, ttft_prompt_tokens |
TTFT as measured by the source |
source |
Original public measurement URL |
source_checked_by_rigbase |
yes = RigBase re-read the number at the source |
Full column notes: https://getrigbase.com/data/
Caveats
- Numbers come from different people, engines, quants and settings. Compare rows from the same source when you compute ratios.
- Filter on
spec_decode == "none"for plain decode speed. - Calculator pages on the site (VRAM, KV cache) are arithmetic, not measurements. They are not in this dataset.
Related
- Browse builds: https://getrigbase.com/
- Can I run it? (VRAM + KV cache calculator): https://getrigbase.com/can-it-run/
- DGX Spark recipes: https://getrigbase.com/dgx-spark/
- Submit a correction or build: https://getrigbase.com/submit/
Attribution
Required by CC BY 4.0:
RigBase (getrigbase.com), CC BY 4.0. Each row keeps its original source URL.
Please also keep or cite the per-row source URL when you reuse an individual number.
Updates
The live files at https://getrigbase.com/data/ are the source of truth. This GitHub mirror is refreshed when the site dataset changes. Issues and PRs that fix a sourced number (with a link) are welcome.
RigBase MCP questions
How do I add RigBase MCP to Claude Code?
Run claude mcp add --transport http rigbase-data https://getrigbase.com/mcp in your terminal. Add --scope user to make it available in every project.
How do I add RigBase MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
Does RigBase perform its own LLM measurements?
No, RigBase collects and normalizes numbers from original public sources like llama.cpp discussions and blogs rather than re-measuring them.
How can I find plain decode speeds without speculative decoding?
You can filter the dataset for rows where the spec_decode column is set to 'none'.