Routescore
@Routescore
关于 Routescore
Routescore
基本信息
配置
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"mcp": {
"command": "node",
"args": [
"dist/index.js"
],
"env": {
"ROUTESCORE_API_KEY": "rs_live_...",
"ROUTESCORE_API_URL": "http://localhost:3000"
}
}
}
}工具
8Modeled premium estimate for MEV-sandwich exposure on a swap (modeled premium, expected/CVaR loss).
Modeled premium estimate for cross-chain bridge execution failure vs a modeled SLA expectation.
Modeled premium estimate for slashing risk on an LRT position given AVS exposure.
What-if Monte Carlo: modeled expected premium vs refund/loss over a horizon.
Pre-trade check an agent runs before it signs: modeled route quality, price-impact / slippage band, modeled MEV/execution exposure where observable, and a token registry read (recognized vs unverified), as a `clear / caution / unsupported` verdict. Supports Ethereum (1) and Robinhood Chain (4663). Recognition is not safety, sellability, rights, redemption, liquidity, or investment-quality verification. Decision support, not execution. Every keyed call also attempts to persist a hash-verifiable evidence record and returns its `record_id`, `evidence_bundle_id`, and `record_output_hash` — null, with a `record_persistence_failed` caveat, if the record store is unavailable.
Fetch one persisted preflight evidence record by `record_id` (owner-scoped to the configured key's account). The record embeds the original check response verbatim plus a canonical-JSON SHA-256 integrity hash so the evidence can be re-verified offline. Read-only evidence: record creation rejects known execution-material keys (calldata, transaction payloads, signing material) and drops identity-shaped labels from the actor context.
Latest public MEV-detector run manifest (version hash + universe).
Confirm the key works and report its plan tier.
概览
What is Mcp?
An MCP server that exposes the Routescore public API as tools for Claude, Codex, Cursor, and any MCP-capable agent. It is a thin, stateless wrapper around the keyed REST gateway — no data is stored locally.
How to use Mcp?
The README includes setup instructions such as "command": "npx",.
Key features of Mcp
- ROUTESCORE_API_URL — override the API base (default https://www.routescore.io)
- Scenario and quote outputs are modeled decision-support, not investment advice
- MCP does not custody assets, execute transactions, route funds, or guarantee
- Rate limits apply per key; responses carry X-RateLimit-* headers
Use cases of Mcp
- Connect an MCP-compatible client to this repository's service.
- Review the README-backed setup before enabling it in production.
FAQ from Mcp
Where is the source code for Mcp?
The source code is linked from the repository URL on this page.
Does Mcp include a standard MCP config?
If the README contains a parseable MCP configuration block, it is shown in the Config tab.
AI 与智能体 分类下的更多 MCP 服务器
Shell and Coding agent for Claude and other mcp clients
rusiaamanShell and coding agent on mcp clients
Open Multi-Agent Canvas
CopilotKitThe open-source multi-agent chat interface that lets you manage multiple agents in one dynamic conversation and add MCP servers for deep research
Hass-MCP
voskaControl and query Home Assistant from Claude and other LLMs — a Model Context Protocol (MCP) server.
MCP Manager for Claude Desktop
zueaisimple web ui to manage mcp (model context protocol) servers in the claude app
Just Prompt - A lightweight MCP server for LLM providers
dislerjust-prompt is an MCP server that provides a unified interface to top LLM providers (OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama)
评论