# Routescore

> Routescore, an MCP server by routescore.io, listed from the official MCP registry. Indexed, not reviewed: facts and our own checks, no score or ranking. Read-only pre-sign evidence for onchain agents: route quality, MEV exposure, clear/caution verdict.

- Canonical: https://www.anchorterminal.com/tools/routescore-mcp
- Markdown: https://www.anchorterminal.com/tools/routescore-mcp.md (~1,150 tokens)
- Slim: https://www.anchorterminal.com/tools/routescore-mcp.min.md (~1,080 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/tools/routescore-mcp.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-05

# Routescore

> Indexed, not reviewed: facts from the official MCP registry and our own checks. No score, grade or rank, and not in the rankings until the panel reviews it. How the index works: https://www.anchorterminal.com/indexed/

- Kind: MCP server, by routescore.io (https://www.routescore.io/developers)
- Listed because: It's published in the registry under routescore.io, a namespace the registry only gives to whoever proves they control that domain.
- What the official MCP registry says: Read-only pre-sign evidence for onchain agents: route quality, MEV exposure, clear/caution verdict.

## Facts

- MCP registry: `io.routescore/mcp` 0.3.5
- Endpoint: https://www.routescore.io/api/mcp (streamable HTTP)
- Package: npm `@routescore/mcp` (stdio)
- Source: https://github.com/routescore/mcp
- Website: https://www.routescore.io/developers
- npm downloads a week: 47
- GitHub stars: 0
- Registry entry updated: 2026-07-19

## Tools

- Tools it lists (11, about 9,962 tokens of context, `tools/list` without credentials, checked 2026-10-04 22:25 UTC):
  - `check_swap` (writes): 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…
  - `get_preflight_record` (read-only): 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_execution` (writes): Persist 1-100 already-built execution_record.v1 documents as immutable, personal-account post-trade evidence. Requires a stable idempotency_key; an exact…
  - `review_execution` (read-only): Review one stored execution_record.v1 by record_id. Authenticated and personal-account owner-scoped: another account’s id is indistinguishable from a missing…
  - `review_public_transaction` (read-only): DEV-ONLY CONTRACT DISCOVERY; DISABLED AGAINST PRODUCTION. On an explicitly enabled non-production server, review one arbitrary public Ethereum transaction by…
  - `whoami` (read-only): Confirm the configured API key works and report which plan tier it carries. Returns the owning account email and tier.
  - `get_detector_manifest` (read-only): 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…
  - `quote_mev_cover` (read-only): 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…
  - `quote_bridge_refund` (read-only): Modeled premium estimate for cross-chain bridge execution failure against a modeled SLA expectation. Returns a modeled premium and conditions — not a live…
  - `quote_lrt_slashing` (read-only): Modeled premium estimate for slashing risk on a liquid-restaking-token (LRT) position given its AVS exposure. Returns a modeled premium and slashing bounds —…
  - `simulate_scenario` (read-only): Run a what-if Monte Carlo: model expected premium vs expected refund/loss over a horizon, given assumptions about sandwich frequency, average loss, and…
- How its tools read to an agent (0 errors, 4 warnings, 0 notes, about 9,962 tokens; rules at https://www.anchorterminal.com/check.md; not part of the score):
  - warn TC13 quote_lrt_slashing: underlying_avs_exposure (object with no properties)
  - warn TC13 record_execution: records[] (object with no properties)
  - warn TC18 quote_bridge_refund: readOnlyHint is true but the name says "refund"
  - warn TC22 review_public_transaction: the definition is about 1,629 tokens

- JSON: https://www.anchorterminal.com/api/v1/tools/routescore-mcp.json
- Being indexed says nothing about quality, and nobody can pay for it. Ask for a review: https://www.anchorterminal.com/builders/#claiming