Skip to content

SafeRoute MCP server

io.github.crystalsignal/saferoutecrystalsignalstreamable-httpv0.18.1Scanned

Noncustodial Base x402 payment control and seller settlement recovery

13 tools: 7 do something that can't be undone, 2 change things and 4 only read.

Tools: 0 delete, 7 irreversible, 2 write, 4 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 5
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

7 tools here do something that can't be undone. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the SafeRoute MCP server can do

The SafeRoute MCP server is published by the GitHub account crystalsignal. It has 13 tools. It can do things that cannot be undone, such as sending, paying or publishing (protect_payment, check_base_swap, prove_safe_action, preflight_transaction and 3 more) and create or change data (2 tools: check_token_risk and verify_swap_execution), but cannot delete data. 4 tools only read.

5 tools can send data out of your system (check_base_swap, prove_safe_action, preflight_transaction and 2 more).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 16, 2026, version 0.18.1.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

13 tools

Can't be undone 7Claude Code: ask
  • check_base_swapWallet-free approved-token Base swap safety preflight.Can send data outNo findings

    Why it is in this group

    • The input addresses people (input.to): what it sends cannot be taken back.

    What it can reach

    • outboundThe input takes a destination (input.to): what the tool writes goes there.
    Description, as the server wrote it
    Wallet-free approved-token Base swap safety preflight. Costs $0.001 USDC.
  • guard_base_tradeComplete pre-sign trade guard with route and simulation evidence.Can send data outNo findings

    Why it is in this group

    • The input addresses people (input.to): what it sends cannot be taken back.

    What it can reach

    • outboundThe input takes a destination (input.to): what the tool writes goes there.
    Description, as the server wrote it
    Complete pre-sign trade guard with route and simulation evidence. Costs $0.12 USDC.
  • preflight_transactionDecode and simulate approved Base ERC-20 calldata or SafeRoute's exact official ERC-8004 registration.Can send data outNo findings

    Why it is in this group

    • The input addresses people (input.transaction.to): what it sends cannot be taken back.

    What it can reach

    • outboundThe input takes a destination (input.transaction.to): what the tool writes goes there.
    Description, as the server wrote it
    Decode and simulate approved Base ERC-20 calldata or SafeRoute's exact official ERC-8004 registration. Costs $0.05 USDC.
  • prepare_token_transferPrepare a bounded, simulated unsigned Base token transfer.Can send data outNo findings

    Why it is in this group

    • The name "prepare_token_transfer" says "transfer": a word for a change that another call does not undo.
    • The input addresses people (input.recipient): what it sends cannot be taken back.

    What it can reach

    • outboundThe input takes a destination (input.recipient): what the tool writes goes there.
    Description, as the server wrote it
    Prepare a bounded, simulated unsigned Base token transfer. Costs $0.10 USDC.
  • protect_paymentOne automatic x402 payment-safety front door: pre-payment ALLOW/BLOCK, duplicate-safe ID binding, policy risk reasons, and optional mined-settlement verification.No findings

    Why it is in this group

    • The name "protect_payment" says "payment": a word that usually means money moves, which cannot be taken back.
    Description, as the server wrote it
    One automatic x402 payment-safety front door: pre-payment ALLOW/BLOCK, duplicate-safe ID binding, policy risk reasons, and optional mined-settlement verification. Free and rate-limited; the buyer signs and pays.
  • prove_safe_actionCreate a signed pre-sign ALLOW, BLOCK, or REVIEW receipt.Can send data outNo findings

    Why it is in this group

    • The description's first verb is "create": a word for a change.
    • The input addresses people (input.to): what it sends cannot be taken back.

    What it can reach

    • outboundThe input takes a destination (input.to): what the tool writes goes there.
    Description, as the server wrote it
    Create a signed pre-sign ALLOW, BLOCK, or REVIEW receipt. Costs $0.05 USDC.
  • route_agent_paymentPrepare a bounded, simulated exact-buy route to a payer-owned Base USDC target covering the x402 payment and optional buffer.No findings

    Why it is in this group

    • The name "route_agent_payment" says "payment": a word that usually means money moves, which cannot be taken back.
    Description, as the server wrote it
    Prepare a bounded, simulated exact-buy route to a payer-owned Base USDC target covering the x402 payment and optional buffer. Costs $0.05 USDC; buyer confirms funding, then retries standard x402 once.
Changes things 2Claude Code: ask
  • check_token_riskApproved Base token risk and liquidity check.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Approved Base token risk and liquidity check. Costs $0.03 USDC.
  • verify_swap_executionVerify a standard-mode SafeRoute Base execution against its signed receipt.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Verify a standard-mode SafeRoute Base execution against its signed receipt. Free; referral payouts remain disabled.
Only reads 4Show 4 read-only tools
  • check_wallet_riskRead-only Base wallet account-posture check.No findings

    Why it is in this group

    • The description's first verb is "read": a word for reading.
    Description, as the server wrote it
    Read-only Base wallet account-posture check. Costs $0.01 USDC.
  • get_safe_swap_quoteSafety-checked noncustodial Base swap quote.No findings

    Why it is in this group

    • The name "get_safe_swap_quote" says "get": a word for reading.
    Description, as the server wrote it
    Safety-checked noncustodial Base swap quote. Costs $0.01 USDC; the buyer signs and broadcasts.
  • list_supported_assetsList SafeRoute's seven approved Base assets, limits, fees, and execution modes.No findings

    Why it is in this group

    • The name "list_supported_assets" says "list": a word for reading.
    Description, as the server wrote it
    List SafeRoute's seven approved Base assets, limits, fees, and execution modes. Free.
  • verify_transaction_intentCompare a mined Base transaction with buyer intent.No findings

    Why it is in this group

    • The description's first verb is "compare": a word for reading.
    Description, as the server wrote it
    Compare a mined Base transaction with buyer intent. Costs $0.05 USDC.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out5
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:03 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
9
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 9 tools that change things (7 irreversible, 2 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://api.usesaferoute.com/mcp: tools/list returned 13 tools to an anonymous client, including protect_payment (irreversible), check_base_swap (irreversible), prove_safe_action (irreversible), preflight_transaction (irreversible), prepare_token_transfer (irreversible) and 4 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools2 changed.~2 changedView diff

Install

Pinned to version 0.18.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http saferoute https://api.usesaferoute.com/mcp
claude mcp add --transport http saferoute https://api.usesaferoute.com/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__saferoute__get_safe_swap_quote",
      "mcp__saferoute__check_wallet_risk",
      "mcp__saferoute__verify_transaction_intent",
      "mcp__saferoute__list_supported_assets"
    ],
    "ask": [
      "mcp__saferoute__protect_payment",
      "mcp__saferoute__check_base_swap",
      "mcp__saferoute__prove_safe_action",
      "mcp__saferoute__check_token_risk",
      "mcp__saferoute__preflight_transaction",
      "mcp__saferoute__prepare_token_transfer",
      "mcp__saferoute__guard_base_trade",
      "mcp__saferoute__verify_swap_execution",
      "mcp__saferoute__route_agent_payment"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as saferoute. Review it before you use it.

Capability tags behind 5 rules
  • mcp__saferoute__check_base_swap outbound
  • mcp__saferoute__prove_safe_action outbound
  • mcp__saferoute__preflight_transaction outbound
  • mcp__saferoute__prepare_token_transfer outbound
  • mcp__saferoute__guard_base_trade outbound

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.github.crystalsignal/saferoute/verify?hash=880d7b7aac3078d3b50aed0f146724af5f13d9883de9a42db5972074134b2951" | jq -e '.changed == false'

Pinned hash 880d7b7aac30, from Nov 16, 2026, 15:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.crystalsignal/saferoute/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.crystalsignal/saferoute
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.crystalsignal/saferoute.svg)](https://radar.anlyon.com/servers/io.github.crystalsignal/saferoute)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:28 UTC.

SafeRoute MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the SafeRoute MCP server safe?

No scan can promise that. What its definitions show: 13 tools, 9 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the SafeRoute MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the SafeRoute MCP server do things that cannot be undone?

Yes. 7 tools can send, pay, publish or merge: protect_payment, check_base_swap, prove_safe_action, preflight_transaction, prepare_token_transfer, guard_base_trade and 1 more.

What tools does the SafeRoute MCP server have?

13 tools: 7 irreversible, 2 write, 4 read. protect_payment, check_base_swap, prove_safe_action, preflight_transaction, prepare_token_transfer, guard_base_trade, route_agent_payment, check_token_risk and 5 more.

Does the SafeRoute MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the SafeRoute MCP server send data to outside services?

5 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): check_base_swap, prove_safe_action, preflight_transaction, prepare_token_transfer and guard_base_trade.

Has the SafeRoute MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 3, 2026. Every change is on this page and in its Atom feed.