Skip to content

Flow — Base quotes & contract safety for agents MCP server

io.github.flow-executor/flowflow-executorstreamable-httpv0.1.0Scanned

Best-execution quotes and contract safety checks on Base for AI agents, paid per call via x402.

4 tools: 2 change things and 2 only read.

Tools: 0 delete, 0 irreversible, 2 write, 2 read.
  • Reads private data · 0
  • Reads text others write · 1
  • Can send data out · 0
  • 1 finding

Tools listed without sign-in. Remote posture

With Anlyon

2 tools here change things. 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 Flow — Base quotes & contract safety for agents MCP server can do

The Flow — Base quotes & contract safety for agents MCP server is published by the GitHub account flow-executor. It has 4 tools. It can create or change data (2 tools: flow_paycheck and flow_health), but cannot delete data. 2 tools only read.

1 tool brings in text other people can write (flow_search).

The fixed checks matched 1 finding (base64-blob). Each one comes with the text it matched.

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

Last scanned Nov 19, 2026, version 0.1.0.

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.

4 tools

Changes things 2Claude Code: ask
  • flow_healthCheck the Flow quote API health: status, chain, and latest synced block number.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
    Check the Flow quote API health: status, chain, and latest synced block number.
  • flow_paycheckBefore you pay this agent, 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
    Before you pay this agent, check. PayCheck ($0.50 USDC via x402 on Base) runs Flow's whole checker stack on a payee in ONE call — the payee verdict (kind, on-chain activity, the full contract-safety engine when the payee is a contract), the wallet approval-exposure audit, contract safety, and the payee's recent USDC settlement history — and returns one finished grade (ALLOW / REVIEW / BLOCK with a 0-100 score), a verify_status (verified / failed / unverified_verifier_down), every check, the evidence under it, and a receipt. The guarantee: the report is produced before settlement; if it cannot be produced, the payment is never settled — no report, no charge. This hosted endpoint does not hold a wallet: an unpaid call returns the endpoint's x402 payment challenge itself, never an invented result. Pay it with any x402 client, or use the @flowexecutor/flow-mcp stdio package with an Early Builder Key.
Only reads 2Show 2 read-only tools
  • flow_quoteGet a best-execution swap quote on Base.1 finding

    Why it is in this group

    • The description's first verb is "get": a word for reading.

    Findings

    • Warn

      The input schema at properties.tokenIn.description contains a 42-character base64 string.

      Matched text

      inputSchema.properties.tokenIn.description: "...on Base (e.g. USDC 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA4E46E)"

      What this check looks for
    Description, as the server wrote it
    Get a best-execution swap quote on Base. Compares Uniswap V3, PancakeSwap V3 and Aerodrome (plus two-hop routes via WETH), returns the winning venue, expected output, edge in bps vs the baseline, a liquidity flag (deep/watch/thin), the exact block number and timestamp, and build latency. Read-only: no funds move.

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 outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write1
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
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, 19:04 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
2
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
  • WarnThe whole server

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

    Matched text

    https://flow-kg4x.vercel.app/api/mcp: tools/list returned 4 tools to an anonymous client, including flow_paycheck (write), flow_health (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • The input schema at properties.tokenIn.description contains a 42-character base64 string.

    Matched text

    inputSchema.properties.tokenIn.description: "...on Base (e.g. USDC 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA4E46E)"

    What this check looks for

History

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

  1. Tools1 changed.~1 changedView diff

Install

Pinned to version 0.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http flow https://flow-kg4x.vercel.app/api/mcp
claude mcp add --transport http flow https://flow-kg4x.vercel.app/api/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__flow__flow_quote",
      "mcp__flow__flow_search"
    ],
    "ask": [
      "mcp__flow__flow_paycheck",
      "mcp__flow__flow_health"
    ],
    "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 flow. Review it before you use it.

Capability tags behind 1 rule
  • mcp__flow__flow_search untrusted-input

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.flow-executor/flow/verify?hash=cd5322413d3b809c3823c4cf20c06dce9d6f5afe1eb22c3f9b055d1c3b17fd9b" | jq -e '.changed == false'

Pinned hash cd5322413d3b, from Nov 19, 2026, 17:18 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.flow-executor/flow/changes.xml

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

Badge

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

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:34 UTC.

Flow — Base quotes & contract safety for agents MCP server: questions and answers

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

Is the Flow — Base quotes & contract safety for agents MCP server safe?

No scan can promise that. What its definitions show: 4 tools, 2 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Flow — Base quotes & contract safety for agents MCP server delete data?

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

Can the Flow — Base quotes & contract safety for agents MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the Flow — Base quotes & contract safety for agents MCP server have?

4 tools: 2 write, 2 read. flow_paycheck, flow_health, flow_quote and flow_search.

Does the Flow — Base quotes & contract safety for agents MCP server need sign-in or OAuth?

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

Does the Flow — Base quotes & contract safety for agents MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the Flow — Base quotes & contract safety for agents MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 5, 2026. Every change is on this page and in its Atom feed.