MCP.Market

Routescore MCP server

online · 100% uptime
by routescore.io·io.routescore/mcp·v0.3.5
No reviews yet

Read-only pre-sign evidence for onchain agents: route quality, MEV exposure, clear/caution verdict.

A89/100grade A
Write a reviewRun it
What users say
No reviews yet
Be the first
Safety scan
A89/100

full report

Adoption
Growing

0 stars30 downloads/wk

Reviews

Write one

Nobody has reviewed Routescore yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Routescore tools (11, 2 write)

write = sends, deletes, buys or posts
  • check_swapFree

    CALL THIS BEFORE SIGNING AN ONCHAIN SWAP. Read-only pre-sign evidence check: given notional, chain, and an optional route and token, it returns a modeled route-quality grade, price-impact / slippage band, modeled MEV/execution exposure where observable, and a token registry read (recognized vs unverified), composed into a clear / caution / unsupported verdict with machine-readable reasons and caveats. Point-in-time decision support: it does not execute, route funds, sign, or promise an outcome — the agent still decides. Recognition is not safety, sellability, redemption, rights, liquidity, or investment-quality verification; unverified tokens, unknown order flow, and uncalibrated sequencer ordering downgrade the verdict rather than reading as safe. Relay the verdict, reasons, and caveats verbatim.

  • get_detector_manifestFree

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

  • get_preflight_recordFree

    Retrieve the durable evidence record a prior check_swap call persisted — the "record" leg of plan → preflight → execute → record. Fetch one record by the record_id that check_swap returned. Owner-scoped: the configured key only ever sees records belonging to its own account. The record embeds the evaluated check_swap response payload (including its evidence_bundle_id, before the additive record_id / record_output_hash linkage fields) plus a canonical-JSON SHA-256 integrity hash (record_id and recorded_at excluded) so the evidence can be re-verified offline, and includes the stored evidence bundle. Read-only evidence: record creation rejects known execution-material keys (calldata, transaction payloads, signing material) and drops identity-shaped labels from the actor context.

  • quote_bridge_refundwrite actionFree

    Modeled premium estimate for cross-chain bridge execution failure against a modeled SLA expectation. Returns a modeled premium and conditions — not a live cover, refund, or premium-acceptance offer.

  • quote_lrt_slashingFree

    Modeled premium estimate for slashing risk on a liquid-restaking-token (LRT) position given its AVS exposure. Returns a modeled premium and slashing bounds — not a live cover offer.

  • quote_mev_coverFree

    Modeled premium estimate for MEV-sandwich exposure on a swap. Returns a modeled premium (bps + USD), expected/CVaR loss, and conditions. Point-in-time decision support before routing a trade — not a live cover, insurance, or premium-acceptance offer.

  • record_executionFree

    Persist 1-100 already-built execution_record.v1 documents as immutable, personal-account post-trade evidence. Requires a stable idempotency_key; an exact replay returns the original result and reuse with different content fails closed. Pro tier, owner-scoped, and bounded by the MCP transport byte limit. This tool never accepts calldata, signing material, routes funds, executes a transaction, applies reviewer overrides, or exposes another tenant. Invalid rows are recorded only as redacted rejection reasons and are never echoed.

  • review_executionFree

    Review one stored execution_record.v1 by record_id. Authenticated and personal-account owner-scoped: another account’s id is indistinguishable from a missing id. Returns the deterministic review_execution.v1 evidence coverage, exceptions, unavailable-evidence register, caveats, and canonical hash. Read-only retrospective decision support only: it does not query arbitrary public transactions, accept reviewer overrides, certify best execution or compliance, give advice, or expose admin actions.

  • review_public_transactionFree

    DEV-ONLY CONTRACT DISCOVERY; DISABLED AGAINST PRODUCTION. On an explicitly enabled non-production server, review one arbitrary public Ethereum transaction by transaction hash. This is separate from review_execution: it does not read an owner-scoped stored execution_record.v1 and never exposes tenant, reviewer, override, or administrative fields. Returns the deterministic tenant-free public_transaction_review.v1 coverage register, conclusions, explicit gap register, source provenance, caveats, and canonical hash. Receipt, block, index, and gas facts are measured; gas cost and point-in-time confirmation depth are calculated. Venue is unavailable in this endpoint until a server-owned verified registry adapter exists. Route, amounts, protocol fee, arrival price, feasible-route benchmark, dropped status, and historical reorg remain unavailable unless the public contract can support them. Read-only retrospective decision support only; it does not certify best execution or compliance and does not give advice.

  • simulate_scenariowrite actionFree

    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. Returns a narrative + distribution.

  • whoamiFree

    Confirm the configured API key works and report which plan tier it carries. Returns the owning account email and tier.

Public scan report

scanner v0.1.9 · 2026-09-25 · same rubric, same numbers if you re-run it

no findings
  • Code scan10 source files scanned25/25
  • Live reliabilityremote reachable in 1238ms20/20
  • Tool poisoning11 tool descriptions checked15/15
  • Auth qualityAPI key sent as a header8/15
  • Maintenancelast push 73 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; website matches verified namespace9/10
Overall 89/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Routescore compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
89/100
higher than 80% of 48,255 servers
Tools
11
the typical server has 7
Tools that change things
18%
typical: 0%. Fewer write tools means less an agent can break
Uptime
100%
of our recent checks; the typical remote server answers 100%
Response time
349 ms
faster than 42% of 30,031 servers
Downloads a week
30
more than 18% of 12,191 servers with a package

What its tools let an agent do: 9 read · 2 change

Install Routescore in Claude Code, Cursor or VS Code

claude mcp add --transport http mcp https://www.routescore.io/api/mcp
Add to Cursor

What the publisher says

From the Routescore repository's README, as published. We do not edit it. Read it on GitHub

@routescore/mcp

The read-only pre-sign evidence layer — a "pre-sign journal" — for onchain agents.

Before an agent (or you) signs a swap onchain, check_swap returns a modeled read of route quality, MEV/execution exposure, and token-registry recognition as a clear / caution / unsupported verdict with its caveats — and persists a hash-verifiable record of exactly what was known before signing, re-verifiable offline. That record is the pre-sign journal. It is read-only: it never signs, executes, routes funds, or custodies assets.

An MCP server (and a keyed REST API) for Claude, Codex, Cursor, and any MCP-capable agent — a thin, stateless wrapper around the Routescore public API, storing no request or response data locally.

checkswap is free. A free API key runs 100 pre-sign checks/day (Pro 1,000/day, Power 10,000/day); the modeled premium-estimate tools, simulatescenario, and persisted-record retrieval are Power-tier. Generate a key at Account → Developer → API & MCP access (/account) — free to mint on any plan. Keys look like rslive… and are shown once.

See how these modeled reads have tracked measured on-chain outcomes on the public calibration surface — Routescore publishes its own accuracy (Brier score, ECE, coverage), re-derivable from a bound source manifest.

Setup

Add the server to your MCP client config and set your key in the env block.

Claude Desktop (claudedesktopconfig.json) / Cursor (.cursor/mcp.json):

{
  "mcpServers": {
    "routescore": {
      "command": "npx",
      "args": ["-y", "@routescore/mcp"],
      "env": {
        "ROUTESCORE_API_KEY": "rs_live_your_key_here"
      }
    }
  }
}

Claude Code (CLI):

claude mcp add routescore --env ROUTESCORE_API_KEY=rs_live_... -- npx -y @routescore/mcp

Optional env:

Useful for local development: http://localhost:3000.

  • ROUTESCOREAPIURL — override the API base (default https://www.routescore.io).

The server checks the key at startup: if ROUTESCOREAPIKEY is missing or does not match the minted key shape (rslive followed by 64 lowercase hex characters), it exits immediately with an actionable error instead of failing on the first tool call. The configured value is never echoed. This is a shape check only — real key verification stays server-side (run the whoami tool).

Tools

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Routescore: common questions

Is Routescore MCP server safe?
Yes, by our scan: it is graded A (89/100). Read the Routescore safety report
How do I install Routescore?
It runs remotely at www.routescore.io. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Routescore need an API key?
Yes. The registry entry asks for ROUTESCORE_API_KEY, Authorization.
Is Routescore maintained?
The last commit was 113 days ago (2026-07-14). The latest release is v0.3.5.
Is Routescore up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
How does Routescore compare with other MCP servers?
safety score 89/100 (higher than 80% of 48,255 servers); tools 11 (the typical server has 7); tools that change things 18% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.