Routescore is an MCP server with 11 tools an agent can call, among them check_swap, get_detector_manifest, get_preflight_record. It answers at https://www.routescore.io/api/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 24 October 2026, succeeded.
Read-only pre-sign evidence for onchain agents: route quality, MEV exposure, clear/caution verdict.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
check_swap | 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 wher Inputs: notional_usd, chain_id, route, token_out, token_in, slippage_allowance_bps |
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. Use to verify what the detector covers. |
get_preflight_record | 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 re Inputs: record_id |
quote_bridge_refund | 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. Inputs: notional_usd, bridge, source_chain_id, dest_chain_id, sla_seconds, bridge_risk_score |
quote_lrt_slashing | 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. Inputs: covered_eth_amount, lrt_token, underlying_avs_exposure, correlation_max_overlap, cover_duration_weeks |
quote_mev_cover | 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-accepta Inputs: notional_usd, asset_pair, route, chain_id, slippage_allowance_bps, refund_threshold_bps |
record_execution | 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 Inputs: idempotency_key, records |
review_execution | 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, u Inputs: record_id |
review_public_transaction | 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 owne Inputs: chain_id, tx_hash |
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. Returns a narrative + distribution. Inputs: notional_usd, sandwich_freq_pct, avg_loss_bps, horizon_days, deductible_bps |
whoami | Confirm the configured API key works and report which plan tier it carries. Returns the owning account email and tier. |
Every block below points at https://www.routescore.io/api/mcp. Pick your client and copy.
claude mcp add --transport http routescore https://www.routescore.io/api/mcp
{
"mcpServers": {
"routescore": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://www.routescore.io/api/mcp"]
}
}
}{
"mcpServers": {
"routescore": {
"url": "https://www.routescore.io/api/mcp"
}
}
}{
"servers": {
"routescore": {
"type": "http",
"url": "https://www.routescore.io/api/mcp"
}
}
}{
"context_servers": {
"routescore": {
"url": "https://www.routescore.io/api/mcp"
}
}
}{
"mcpServers": {
"routescore": {
"serverUrl": "https://www.routescore.io/api/mcp"
}
}
}{
"mcpServers": {
"routescore": {
"url": "https://www.routescore.io/api/mcp"
}
}
}name: Routescore
version: 0.0.1
schema: v1
mcpServers:
- name: Routescore
type: streamable-http
url: https://www.routescore.io/api/mcp{
"mcpServers": {
"routescore": {
"httpUrl": "https://www.routescore.io/api/mcp"
}
}
}{
"mcpServers": {
"routescore": {
"type": "http",
"url": "https://www.routescore.io/api/mcp"
}
}
}{
"mcpServers": {
"routescore": {
"url": "https://www.routescore.io/api/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fwww.routescore.io%2Fapi%2Fmcp&type=streamable_http&id=routescore&name=Routescore
It answered our last check on 24 October 2026 in 509 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by routescore.io and served from www.routescore.io, the vendor's own domain: https://www.routescore.io/api/mcp.
11, as returned by the server's own tools/list on 22 September 2026: check_swap, get_detector_manifest, get_preflight_record, quote_bridge_refund, quote_lrt_slashing, quote_mev_cover, record_execution, review_execution, and 3 more.
It answered our last check on 24 October 2026 in 509 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://www.routescore.io/api/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.routescore. Endpoint host: www.routescore.io. ARD identifier: urn:air:io.routescore:mcp:mcp.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.