MCP serverio.github.Flotapponnier/openchainbench

Live, neutral benchmarks for public RPC latency, oracles, bridges, perp DEX, and prediction markets.

UNRATEDActivestreamable-httpopenchainbench.com

Overview

Score?

UNRATED 0.724

of what a free look can see, on 32 looks

Looks

last 11 min ago

Tools

changed 2 days ago

More info

URL

openchainbench.com/api/mcp/mcp

streamable-http

Says it is

mcp-typescript server on vercel 0.1.0

protocol 2025-06-18

In the record since

32 days ago

Among servers18,413 with a card

0median 0.606 · this server 0.724 · highest on record 0.8561

Toolsfrom sha256:614bd0a1df…d037f3 · +3 −1 2 days ago

The tools this server lists, read out of the definition it returned
Tool	Schema
compare_providers added Puts two or more named providers side by side on one benchmark, with each one's rank, measured value and success rate. Use when the user names the candidates themselves: "Alchemy	input · no output
get_benchmark Returns full detail for one benchmark, ready to cite verbatim: • rankings (every provider sorted by p50) • sparkline (24h trend, 72 points) • headline sentence + paste-ready	input · no output
list_answers Returns every published answer page: one plain question, the sentence that answers it from live data, and the benchmark the number comes from. Call this when the user asks a quest	input · no output
list_benchmarks A compact index of what OpenChainBench measures. One short row per benchmark: slug, title, category, the metric, the current value and who leads it. Use when the user asks what is	input · no output
recommend_provider added Answers "which should I use for X" by picking the benchmarks that measure X and reporting who currently leads them. Pass the user's goal in their own words: "a Solana trading bot"	input · no output
search_benchmarks added Ranks the benchmark catalogue against a question in the user's own words and returns the best few matches. Use this when somebody asks which provider, chain or service is fastest,	input · no output
~~query_prom~~ removed Direct PromQL passthrough for advanced questions that don't map cleanly to `list_benchmarks` / `get_benchmark`, e.g. "what was Mobula's p50 head-lag yesterday at 14:00 UTC" or "plo	—

Verify it yourselfnpx teppi-check https://openchainbench.com/api/mcp/mcpcurl -s https://api.teppi.xyz/v1/trust/mcp/mcs_01M1FZ2CH7Z2E6CKMG65X08V6H