# OpenChainBench

Lets your agent pull live benchmarks for crypto infrastructure: RPC latency, oracles, bridges, perp DEXes and prediction markets.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 8
- Author: ChainBench
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/ChainBench/OpenChainBench
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/mcp/openchainbench

## What it does

OpenChainBench measures crypto infrastructure and publishes the numbers: RPCs, oracles, bridges, aggregators, price feeds, cross-chain messaging, perp DEXes, prediction markets. Every provider is scored on the same metric under the same conditions. Data ships under CC-BY-4.0, the harnesses under MIT.

The MCP server exposes that data to your agent through three tools — `list_benchmarks`, `get_benchmark` and `query_prom` — plus the `openchainbench://benchmark/{slug}` resource. It runs over HTTP at `https://openchainbench.com/api/mcp/mcp`, so there is no local process to start. In Claude the whole setup is `claude mcp add --transport http openchainbench https://openchainbench.com/api/mcp/mcp`.

Benchmarks get refreshed, and each one carries a freshness value, so check the as-of date before you quote a figure. Providers that appear in a ranking can also submit pull requests, which is a reason to read the methodology rather than just the top row.

## Requirements
- Remote server: `https://openchainbench.com/api/mcp/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http openchainbench https://openchainbench.com/api/mcp/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add openchainbench --url https://openchainbench.com/api/mcp/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "openchainbench": {
            "url": "https://openchainbench.com/api/mcp/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "openchainbench": {
            "type": "http",
            "url": "https://openchainbench.com/api/mcp/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http openchainbench https://openchainbench.com/api/mcp/mcp
```

## When to use it
- compare RPC provider latency on one shared metric
- pick a bridge or oracle for a specific chain
- pull a live benchmark figure into an agent answer
- read the methodology before citing a number
- find every benchmark a given product appears in

## Example prompts
- List the OpenChainBench benchmarks for RPCs
- Which provider leads head lag in the aggregator-head-lag benchmark?
- Fetch the methodology for the bridges benchmark and tell me when it was last updated

## Similar
- [World Monitor](https://affpapa.org/en/nevibecode/mcp/world-monitor.md) — MCP server · ★ 89408
- [Scrapling MCP Server](https://affpapa.org/en/nevibecode/mcp/scrapling-mcp-server.md) — MCP server · ★ 89433
- [MCP Toolbox for Databases](https://affpapa.org/en/nevibecode/mcp/googleapis-mcp-toolbox-for-databases.md) — MCP server · ★ 16717
- [PostHog MCP Server](https://affpapa.org/en/nevibecode/mcp/posthog-mcp-server.md) — MCP server · ★ 40409
- [dbx](https://affpapa.org/en/nevibecode/mcp/dbx.md) — MCP server · ★ 27669
- [Metabase](https://affpapa.org/en/nevibecode/mcp/metabase.md) — MCP server · ★ 49845

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md