Routescore
REMOTE · WWW.ROUTESCORE.IO · 2 COMPONENTS
Read-only pre-sign evidence for onchain agents: route quality, MEV exposure, clear/caution verdict.
Available components
Last scanned (58 minutes ago)
Scores higher than 91% of remote servers
Reachable. Last reached 5 Nov 2026.
Category Crypto and Web3
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security80
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one. See how to fix → View diagnostics → Partial
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability68
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 2297 tokens (~208/item across 11 items; 11 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "quote_bridge_refund" implies "refund" and declares readOnlyHint instead, contradicting what its own name says it does. See how to fix → Fail
- An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 28 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 25 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 26 Aug 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 25 Aug 26 0
- Stability: 0.97 → pass security
- 11 Aug 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 3 Aug 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Schema quality: 1590 → 2297 ▼ functional
- Server version: 0.3.5 → 0.4.0 functional
- New tool “review_execution” functional
- New tool “review_public_transaction” functional
- New tool “record_execution” functional
- 31 Jul 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 27 Jul 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Probed https://www.routescore.io/api/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=routescore.io | CN=WE1,O=Google Trust Services,C=US | 18 Oct 2026 | 16 Jan 2027 | ECDSA 256 | ECDSA-SHA256 | 912b126326da9f390e4b636106e4ca2d |
| SANs: routescore.io, *.routescore.io | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of www.routescore.io. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| io. | present | 38690 | 8 | Verified |
| routescore.io. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=63072000; includeSubDomains; preload |
| x-content-type-options | nosniff |
| x-frame-options | DENY |
| referrer-policy | strict-origin-when-cross-origin |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://www.routescore.io/api/mcp | Verified | 200 | |
| http (plaintext) | http://www.routescore.io/api/mcp | HTTPS enforced | 308 | https://www.routescore.io/api/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
check_swap Check swap before signing (pre-sign evidence) ~380
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.
| Name | Type | Req | Description |
|---|---|---|---|
| chain_id | integer | – | Chain ID. 1 = Ethereum (default), 4663 = Robinhood Chain. |
| notional_usd | number | yes | Trade size in USD. |
| route | string | – | Route id to score, e.g. 'uniswap-v3-rho'. Omit to score the chain's default public route. |
| slippage_allowance_bps | number | – | Slippage allowance in bps. Default 50. |
| token_in | string | – | Token being sold (address or symbol). |
| token_out | string | – | Token being received (address or symbol) — checked against Routescore's recognized-token registry (recognized vs unverified). RHC tokenized stock/ETF address-level recognition uses the Routescore reg… |
| Name | Type | Req | Description |
|---|---|---|---|
| caveats | array | – | Caveat sentences to relay verbatim. |
| chain | object|null | – | Resolved chain (chainId, name, supportLevel), or null. |
| commercial_disclosure | object | – | No-pay-to-rank disclosure (paid_placement, score_influenced_by_partner, message). |
| confidence_band | object | – | Confidence band (low, high, unit, label); low/high are null when not calibrated. |
| evidence_bundle_id | string|null | – | Id of the evidence bundle; null when not persisted. |
| market_regime | object | – | Reference-market open/closed regime evidence (additive). |
| methodology_version | string | – | Methodology-version string, e.g. routescore.public_api.v1. |
| reasons | array | – | Stable reason codes; open vocabulary — tolerate unknown codes. |
| record_id | string|null | – | Id of the persisted evidence record; null if persistence failed. |
| record_output_hash | string|null | – | sha256:<hex> content hash of the record; null if persistence failed. |
| reference_price | object | – | Basis-regime gap-state evidence for tokenized assets (additive). |
| route | object|null | – | Scored route with modeled grade / quality / leak / slippage fields, or null. |
| score_state | string | – | Overall state of the response. |
| source_freshness | object | – | Per-source freshness reading (state, checked_at, max_age_seconds, sources[]). |
| token_safety | object | – | Registry recognition read: recognized vs unverified, with flags and caveats. Recognition only. |
| trust | object | – | The full nested trust envelope; additionally carries generated_at and decision_support_only. |
| verdict | string | – | Advisory pre-sign verdict. |
No examples provided.
get_detector_manifest Get MEV-detector manifest ~43
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.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| caveats | array | – | Caveat sentences to relay verbatim. |
| commercial_disclosure | object | – | No-pay-to-rank disclosure (paid_placement, score_influenced_by_partner, message). |
| confidence_band | object | – | Confidence band (low, high, unit, label); low/high are null when not calibrated. |
| detector_version_hash | string | – | SHA-256 of the detector + pricing source. |
| eligible_universe | object | – | The pinned pool / token universe scanned. |
| generated_at | string | – | ISO-8601 generation timestamp. |
| methodology_version | string | – | Methodology-version string, e.g. routescore.public_api.v1. |
| score_state | string | – | Overall state of the response. |
| source_freshness | object | – | Per-source freshness reading (state, checked_at, max_age_seconds, sources[]). |
| trust | object | – | The full nested trust envelope; additionally carries generated_at and decision_support_only. |
No examples provided.
get_preflight_record Retrieve pre-sign evidence record ~181
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.
| Name | Type | Req | Description |
|---|---|---|---|
| record_id | string | yes | The record id returned by check_swap (its record_id field). |
| Name | Type | Req | Description |
|---|---|---|---|
| caveats | array | – | Caveat sentences to relay verbatim. |
| commercial_disclosure | object | – | No-pay-to-rank disclosure (paid_placement, score_influenced_by_partner, message). |
| confidence_band | object | – | Confidence band (low, high, unit, label); low/high are null when not calibrated. |
| evidence_bundle | object|null | – | The stored evidence bundle, or null when none was captured. |
| methodology_version | string | – | Methodology-version string, e.g. routescore.public_api.v1. |
| record | object | – | The full routescore.preflight_record.v0 document (schema, record_id, recorded_at, request, actor, policy_ref, response, integrity). |
| score_state | string | – | Overall state of the response. |
| source_freshness | object | – | Per-source freshness reading (state, checked_at, max_age_seconds, sources[]). |
| trust | object | – | The full nested trust envelope; additionally carries generated_at and decision_support_only. |
No examples provided.
quote_bridge_refund Quote: bridge-failure premium (modeled) ~153
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.
| Name | Type | Req | Description |
|---|---|---|---|
| bridge | string | – | Bridge name, e.g. 'across'. |
| bridge_risk_score | number | – | Bridge risk score 0–1. Default 0.05. |
| dest_chain_id | integer | – | Destination chain ID. Default 8453 (Base). |
| notional_usd | number | yes | Amount bridged in USD. |
| sla_seconds | integer | – | Expected delivery SLA in seconds. Default 60. |
| source_chain_id | integer | – | Source chain ID. Default 1. |
| Name | Type | Req | Description |
|---|---|---|---|
| allowed | boolean | – | Whether the engine produced a modeled quote. |
| bond_id | string | – | – |
| caveats | array | – | Caveat sentences to relay verbatim. |
| commercial_disclosure | object | – | No-pay-to-rank disclosure (paid_placement, score_influenced_by_partner, message). |
| conditions | object | – | Engine-defined conditions. |
| confidence_band | object | – | Confidence band (low, high, unit, label); low/high are null when not calibrated. |
| cvar95_loss_bps | number | – | Modeled CVaR-95 loss in bps. |
| expected_loss_bps | number | – | Modeled expected loss in bps. |
| expected_outcome | object | – | Engine-defined expected-outcome payload. |
| expires_at | string|null | – | ISO-8601 expiry timestamp, or null. |
| issued_at | string | – | ISO-8601 issue timestamp. |
| margin_bps | number | – | Modeled margin component in bps. |
| methodology_version | string | – | Methodology-version string, e.g. routescore.public_api.v1. |
| no_quote_reason | string|null | – | Reason a modeled quote was withheld, or null. |
| premium_amount_usd | number | – | Modeled premium in USD. |
| premium_bps | number | – | Modeled premium in bps. |
| product | string | – | – |
| reason_codes | array | – | Stable reason codes. |
| score_state | string | – | Overall state of the response. |
| source_freshness | object | – | Per-source freshness reading (state, checked_at, max_age_seconds, sources[]). |
| trust | object | – | The full nested trust envelope; additionally carries generated_at and decision_support_only. |
No examples provided.
quote_lrt_slashing Quote: LRT-slashing premium (modeled) ~158
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.
| Name | Type | Req | Description |
|---|---|---|---|
| correlation_max_overlap | number | – | Max correlation overlap 0–1. Default 0.5. |
| cover_duration_weeks | integer | – | Modeled cover duration in weeks. Default 12. |
| covered_eth_amount | number | yes | ETH amount used as the modeled position size. |
| lrt_token | string | – | LRT token, e.g. 'weETH'. |
| underlying_avs_exposure | object | – | AVS exposure weights, e.g. { "EigenDA": 1.0 }. |
| Name | Type | Req | Description |
|---|---|---|---|
| allowed | boolean | – | Whether the engine produced a modeled quote. |
| bond_id | string | – | – |
| caveats | array | – | Caveat sentences to relay verbatim. |
| commercial_disclosure | object | – | No-pay-to-rank disclosure (paid_placement, score_influenced_by_partner, message). |
| conditions | object | – | Engine-defined conditions. |
| confidence_band | object | – | Confidence band (low, high, unit, label); low/high are null when not calibrated. |
| cvar95_loss_bps | number | – | Modeled CVaR-95 loss in bps. |
| expected_loss_bps | number | – | Modeled expected loss in bps. |
| expected_outcome | object | – | Engine-defined expected-outcome payload. |
| expires_at | string|null | – | ISO-8601 expiry timestamp, or null. |
| issued_at | string | – | ISO-8601 issue timestamp. |
| margin_bps | number | – | Modeled margin component in bps. |
| methodology_version | string | – | Methodology-version string, e.g. routescore.public_api.v1. |
| no_quote_reason | string|null | – | Reason a modeled quote was withheld, or null. |
| premium_amount_usd | number | – | Modeled premium in USD. |
| premium_bps | number | – | Modeled premium in bps. |
| product | string | – | – |
| reason_codes | array | – | Stable reason codes. |
| score_state | string | – | Overall state of the response. |
| source_freshness | object | – | Per-source freshness reading (state, checked_at, max_age_seconds, sources[]). |
| trust | object | – | The full nested trust envelope; additionally carries generated_at and decision_support_only. |
No examples provided.
quote_mev_cover Quote: MEV-sandwich premium (modeled) ~212
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.
| Name | Type | Req | Description |
|---|---|---|---|
| asset_pair | string | – | Asset pair, e.g. 'USDC/ETH'. Default USDC/ETH. |
| chain_id | integer | – | Chain ID (1 = Ethereum). Default 1. |
| historical_sandwich_freq | number | – | Historical sandwich frequency as a 0–1 fraction. Default 0.012. |
| notional_usd | number | yes | Trade size in USD. |
| refund_threshold_bps | number | – | Modeled refund threshold in bps. Default 50. |
| route | string | – | Execution route, e.g. 'uniswap-v3'. |
| slippage_allowance_bps | number | – | Slippage allowance in bps. Default 50. |
| Name | Type | Req | Description |
|---|---|---|---|
| allowed | boolean | – | Whether the engine produced a modeled quote. |
| bond_id | string | – | – |
| caveats | array | – | Caveat sentences to relay verbatim. |
| commercial_disclosure | object | – | No-pay-to-rank disclosure (paid_placement, score_influenced_by_partner, message). |
| conditions | object | – | Engine-defined conditions. |
| confidence_band | object | – | Confidence band (low, high, unit, label); low/high are null when not calibrated. |
| cvar95_loss_bps | number | – | Modeled CVaR-95 loss in bps. |
| expected_loss_bps | number | – | Modeled expected loss in bps. |
| expected_outcome | object | – | Engine-defined expected-outcome payload. |
| expires_at | string|null | – | ISO-8601 expiry timestamp, or null. |
| issued_at | string | – | ISO-8601 issue timestamp. |
| margin_bps | number | – | Modeled margin component in bps. |
| methodology_version | string | – | Methodology-version string, e.g. routescore.public_api.v1. |
| no_quote_reason | string|null | – | Reason a modeled quote was withheld, or null. |
| premium_amount_usd | number | – | Modeled premium in USD. |
| premium_bps | number | – | Modeled premium in bps. |
| product | string | – | – |
| reason_codes | array | – | Stable reason codes. |
| score_state | string | – | Overall state of the response. |
| source_freshness | object | – | Per-source freshness reading (state, checked_at, max_age_seconds, sources[]). |
| trust | object | – | The full nested trust envelope; additionally carries generated_at and decision_support_only. |
No examples provided.
record_execution Record immutable execution evidence ~168
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.
| Name | Type | Req | Description |
|---|---|---|---|
| idempotency_key | string | yes | Stable caller key for this exact records array. Reuse it only for an exact retry. |
| records | array | yes | One to 100 complete routescore.execution_record.v1 documents. The MCP argument envelope is additionally capped at 32 KiB. |
| Name | Type | Req | Description |
|---|---|---|---|
| caveats | array | – | Caveat sentences to relay verbatim. |
| commercial_disclosure | object | – | No-pay-to-rank disclosure (paid_placement, score_influenced_by_partner, message). |
| confidence_band | object | – | Confidence band (low, high, unit, label); low/high are null when not calibrated. |
| intake_id | string | yes | – |
| methodology_version | string | – | Methodology-version string, e.g. routescore.public_api.v1. |
| records | array | yes | – |
| rejected | array | yes | – |
| schema | string | yes | – |
| score_state | string | – | Overall state of the response. |
| source_freshness | object | – | Per-source freshness reading (state, checked_at, max_age_seconds, sources[]). |
| summary | object | yes | – |
| trust | object | – | The full nested trust envelope; additionally carries generated_at and decision_support_only. |
No examples provided.
review_execution Review stored execution evidence ~122
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.
| Name | Type | Req | Description |
|---|---|---|---|
| record_id | string | yes | UUID of an execution_record.v1 already stored under the configured key’s personal account. |
| Name | Type | Req | Description |
|---|---|---|---|
| caveats | array | – | Caveat sentences to relay verbatim. |
| commercial_disclosure | object | – | No-pay-to-rank disclosure (paid_placement, score_influenced_by_partner, message). |
| confidence_band | object | – | Confidence band (low, high, unit, label); low/high are null when not calibrated. |
| methodology_version | string | – | Methodology-version string, e.g. routescore.public_api.v1. |
| review | object | yes | Deterministic routescore.review_execution.v1 result. It is retrospective decision support, not advice or a best-execution certification. |
| score_state | string | – | Overall state of the response. |
| source_freshness | object | – | Per-source freshness reading (state, checked_at, max_age_seconds, sources[]). |
| trust | object | – | The full nested trust envelope; additionally carries generated_at and decision_support_only. |
No examples provided.
review_public_transaction Review public Ethereum transaction ~231
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.
| Name | Type | Req | Description |
|---|---|---|---|
| chain_id | integer | yes | Ethereum mainnet chain id. Public transaction review currently accepts only 1. |
| tx_hash | string | yes | One public Ethereum 32-byte transaction hash. |
| Name | Type | Req | Description |
|---|---|---|---|
| caveats | array | – | Caveat sentences to relay verbatim. |
| commercial_disclosure | object | – | No-pay-to-rank disclosure (paid_placement, score_influenced_by_partner, message). |
| confidence_band | object | – | Confidence band (low, high, unit, label); low/high are null when not calibrated. |
| methodology_version | string | – | Methodology-version string, e.g. routescore.public_api.v1. |
| review | object | yes | Tenant-free deterministic routescore.public_transaction_review.v1 result from normalized public Ethereum evidence. |
| score_state | string | – | Overall state of the response. |
| source_freshness | object | – | Per-source freshness reading (state, checked_at, max_age_seconds, sources[]). |
| trust | object | – | The full nested trust envelope; additionally carries generated_at and decision_support_only. |
No examples provided.
simulate_scenario Simulate premium-vs-loss scenario (modeled) ~144
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.
| Name | Type | Req | Description |
|---|---|---|---|
| avg_loss_bps | number | – | Average sandwich loss in bps. Default 40. |
| deductible_bps | number | – | Deductible in bps. Default 100. |
| horizon_days | integer | – | Horizon in days (≈ swaps). Default 30. |
| notional_usd | number | yes | Per-swap notional in USD. |
| sandwich_freq_pct | number | – | Sandwich frequency as a percentage 0–100. Default 1.2. |
| Name | Type | Req | Description |
|---|---|---|---|
| caveats | array | – | Caveat sentences to relay verbatim. |
| commercial_disclosure | object | – | No-pay-to-rank disclosure (paid_placement, score_influenced_by_partner, message). |
| confidence_band | object | – | Confidence band (low, high, unit, label); low/high are null when not calibrated. |
| distribution | array | – | Loss-distribution histogram bins for charting. |
| expected_loss_usd | number | – | Modeled expected loss in USD over the horizon. |
| expected_premium_usd | number | – | Modeled expected premium in USD over the horizon. |
| expected_refund_usd | number | – | Modeled expected refund in USD over the horizon. |
| loss_ratio_pct | number | – | Modeled loss ratio as a percentage. |
| methodology_version | string | – | Methodology-version string, e.g. routescore.public_api.v1. |
| narrative | string | – | Plain-language summary of the modeled scenario. |
| score_state | string | – | Overall state of the response. |
| source_freshness | object | – | Per-source freshness reading (state, checked_at, max_age_seconds, sources[]). |
| trust | object | – | The full nested trust envelope; additionally carries generated_at and decision_support_only. |
No examples provided.
whoami Verify API key & tier ~30
Confirm the configured API key works and report which plan tier it carries. Returns the owning account email and tier.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| authenticated | boolean | – | True when the key is valid. |
| caveats | array | – | Caveat sentences to relay verbatim. |
| check_swap_enabled | boolean | – | Whether the pre-sign check_swap endpoint is available (every tier). |
| commercial_disclosure | object | – | No-pay-to-rank disclosure (paid_placement, score_influenced_by_partner, message). |
| confidence_band | object | – | Confidence band (low, high, unit, label); low/high are null when not calibrated. |
| string | – | The owning account email. | |
| methodology_version | string | – | Methodology-version string, e.g. routescore.public_api.v1. |
| plan_includes_api | boolean | – | Back-compat alias for quote_api_enabled. |
| quote_api_enabled | boolean | – | Whether the modeled-quote / scenario tools are available (Power only). |
| score_state | string | – | Overall state of the response. |
| source_freshness | object | – | Per-source freshness reading (state, checked_at, max_age_seconds, sources[]). |
| tier | string | – | The owning account tier. |
| trust | object | – | The full nested trust envelope; additionally carries generated_at and decision_support_only. |
No examples provided.
How do I install the Routescore MCP server?
Routescore is a hosted endpoint at https://www.routescore.io/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · www.routescore.io
claude mcp add --transport http io-routescore-mcp 'https://www.routescore.io/api/mcp'
What is the Routescore MCP server?
Routescore is an MCP server listed in the public MCP registry as io.routescore/mcp. Read-only pre-sign evidence for onchain agents: route quality, MEV exposure, clear/caution verdict. This page covers its hosted endpoint (https://www.routescore.io/api/mcp).
Is the Routescore MCP server safe to use?
Routescore scores 85 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Routescore MCP server expose?
Routescore exposes 11 tools: check_swap, get_preflight_record, record_execution, review_execution, review_public_transaction, and 6 more. Their descriptions and schemas cost roughly 1,822 tokens of context every time the server is loaded.
Does the Routescore MCP server require authentication?
No. We connected to Routescore without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Routescore MCP server still maintained?
Routescore is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.