Security & Testing

routescore.io

Provides tools for checking on-chain swaps, retrieving preflight records, and assessing MEV exposure for secure transaction execution.

1 endpoint8 known toolsFirst detected July 25, 2026Last detected July 25, 2026

ENDPOINT 1

https://www.routescore.io/api/mcp

No auth detected

MCP server metadata

Name: routescore
Version: 0.3.5

Capabilities

tools

Server instructions

Routescore is a read-only pre-sign evidence layer for onchain agents — one element of the agentic execution stack, not the executor and not a guarantee. Primary tool: check_swap. Call it AFTER you have constructed a proposed swap and BEFORE you sign it or hand it to an executor. Given the notional, chain, and (optionally) the route and token, it returns a clear / caution / unsupported verdict with machine-readable reasons and caveats, and persists a hash-verifiable record of exactly what was known before signing. check_swap never signs, executes, routes funds, or custodies assets — the calling agent still decides whether to proceed. Relay the verdict, reasons, and caveats to the user or downstream executor verbatim: do not paraphrase away a caution or drop a caveat. Treat a verdict of "unsupported" as first-class evidence ("not evaluated"), not an error to retry around. Every check_swap call returns a record_id; use get_preflight_record to fetch that durable, offline-re-verifiable evidence later. Use whoami to confirm the configured key and its tier. check_swap is free on any tier (a free key runs 100 pre-sign checks/day). The quote_* and simulate_scenario tools return MODELED premium estimates — decision support only, never a live cover, insurance, or offer — and require the Power tier.

Known tools 8

check_swap

CALL THIS BEFORE SIGNING AN ONCHAIN SWAP.

Inferred read-only

get_preflight_record

Retrieve the durable evidence record a prior check_swap call persisted — the "record" leg of plan → preflight → execute → record.

Potential side effects

whoami

Confirm the configured API key works and report which plan tier it carries.

Inferred read-only

get_detector_manifest

Fetch the latest public MEV-detector run manifest: the detector version hash and the eligible pool/token universe it was committed to.

Inferred read-only

quote_mev_cover

Modeled premium estimate for MEV-sandwich exposure on a swap.

Inferred read-only

quote_bridge_refund

Modeled premium estimate for cross-chain bridge execution failure against a modeled SLA expectation.

Inferred read-only

quote_lrt_slashing

Modeled premium estimate for slashing risk on a liquid-restaking-token (LRT) position given its AVS exposure.

Inferred read-only

simulate_scenario

Run a what-if Monte Carlo: model expected premium vs expected refund/loss over a horizon, given assumptions about sandwich frequency, average loss, and deductible.

Potential side effects

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.routescore]
url = "https://www.routescore.io/api/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "routescore": {
      "type": "http",
      "url": "https://www.routescore.io/api/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: routescore
Remote MCP URL: https://www.routescore.io/api/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "routescore": {
      "url": "https://www.routescore.io/api/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "routescore": {
      "type": "http",
      "url": "https://www.routescore.io/api/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "routescore",
  "transport": "streamable-http",
  "url": "https://www.routescore.io/api/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.