Skip to content

CantorFi lending vaults and agent door MCP server

io.github.cantorfi/cantorfi-mcpcantorfistreamable-httpv0.3.0Scanned

CantorFi on Base: vaults, positions, unsigned transactions, x402 paid services, apps built on it.

10 tools: 8 change things and 2 only read.

Tools: 0 delete, 0 irreversible, 8 write, 2 read.
  • Reads private data · 2
  • Reads text others write · 10
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

8 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 CantorFi lending vaults and agent door MCP server can do

The CantorFi lending vaults and agent door MCP server is published by the GitHub account cantorfi. It has 10 tools. It can create or change data (8 tools: cantorfi_vaults, cantorfi_vault, cantorfi_contracts, cantorfi_liquidation_bot and 4 more), but cannot delete data. 2 tools only read.

2 tools read private data (search and fetch); 10 tools bring in text other people can write (cantorfi_vaults, cantorfi_vault, cantorfi_contracts and 7 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 2 times since Anlyon Radar first saw them.

Last scanned Nov 21, 2026, version 0.3.0.

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.

10 tools

Changes things 8Claude Code: ask
  • cantorfi_appsApplications registered in the CantorFi integrator registry, read from the chain: name, site and the endpoint where an agent reads and acts in each application.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Applications registered in the CantorFi integrator registry, read from the chain: name, site and the endpoint where an agent reads and acts in each application. One connection to CantorFi finds them all.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • cantorfi_contractsNetwork, chain id, deployment block and addresses of the CantorFi contracts: protocol registry, vault factory, reader, price oracle and every vault with its token, receipt token an…Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Network, chain id, deployment block and addresses of the CantorFi contracts: protocol registry, vault factory, reader, price oracle and every vault with its token, receipt token and staking contract.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • cantorfi_liquidation_botHow to run the open-source CantorFi liquidation bot: read-only without a key, or liquidating with the user's own wallet.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    How to run the open-source CantorFi liquidation bot: read-only without a key, or liquidating with the user's own wallet. Returns the repository and the commands filled with the network values.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • cantorfi_paid_servicesServices an agent pays per call in USDC with x402: resource, price, input and how to pay.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Services an agent pays per call in USDC with x402: resource, price, input and how to pay. No account and no key on the server: the agent's own wallet signs a USDC authorization, without gas.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • cantorfi_positionWhat one wallet has supplied and owes in each CantorFi vault: supply, debt with interest, what it can still borrow, what it can withdraw and its health factor.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    What one wallet has supplied and owes in each CantorFi vault: supply, debt with interest, what it can still borrow, what it can withdraw and its health factor.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • cantorfi_prepareUnsigned transactions for one vault action (supply, borrow, repay or withdraw) and one amount, ready to be signed and sent in order by the user's or the agent's own wallet.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Unsigned transactions for one vault action (supply, borrow, repay or withdraw) and one amount, ready to be signed and sent in order by the user's or the agent's own wallet. Nothing is signed or sent by this server.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • cantorfi_vaultLive state of one CantorFi vault, chosen by token symbol (USDC, WETH), vault id or vault address.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Live state of one CantorFi vault, chosen by token symbol (USDC, WETH), vault id or vault address.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • cantorfi_vaultsLive state of every CantorFi isolated lending vault: token, supplied, borrowed, available liquidity, utilization, borrow and supply APR, borrow limit, liquidation threshold and liq…Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Live state of every CantorFi isolated lending vault: token, supplied, borrowed, available liquidity, utilization, borrow and supply APR, borrow limit, liquidation threshold and liquidation bonus.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
Only reads 2Show 2 read-only tools
  • fetchFull record of one CantorFi vault or full text of one guide, by id (from search).Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "fetch" says "fetch": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "vault": it reads secrets.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Full record of one CantorFi vault or full text of one guide, by id (from search).

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true

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 outbound.

Reads private data2
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write10
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, 18:19 UTC, unchanged since Nov 20, 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
4
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 4 tools that change things (4 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://www.cantorfi.xyz/api/mcp: tools/list returned 6 tools to an anonymous client, including cantorfi_vaults (write), cantorfi_vault (write), cantorfi_contracts (write), cantorfi_liquidation_bot (write)

    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. Tools1 added.+1 addedView diff
  2. Tools3 added.+3 addedView diff

Install

Pinned to version 0.3.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http cantorfi https://www.cantorfi.xyz/api/mcp
claude mcp add --transport http cantorfi https://www.cantorfi.xyz/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__cantorfi__search",
      "mcp__cantorfi__fetch"
    ],
    "ask": [
      "mcp__cantorfi__cantorfi_vaults",
      "mcp__cantorfi__cantorfi_vault",
      "mcp__cantorfi__cantorfi_contracts",
      "mcp__cantorfi__cantorfi_liquidation_bot",
      "mcp__cantorfi__cantorfi_apps",
      "mcp__cantorfi__cantorfi_position",
      "mcp__cantorfi__cantorfi_prepare",
      "mcp__cantorfi__cantorfi_paid_services"
    ],
    "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 cantorfi. Review it before you use it.

Capability tags behind 10 rules
  • mcp__cantorfi__cantorfi_vaults untrusted-input
  • mcp__cantorfi__cantorfi_vault untrusted-input
  • mcp__cantorfi__cantorfi_contracts untrusted-input
  • mcp__cantorfi__cantorfi_liquidation_bot untrusted-input
  • mcp__cantorfi__cantorfi_apps untrusted-input
  • mcp__cantorfi__cantorfi_position untrusted-input
  • mcp__cantorfi__cantorfi_prepare untrusted-input
  • mcp__cantorfi__cantorfi_paid_services untrusted-input
  • mcp__cantorfi__search private-data, untrusted-input
  • mcp__cantorfi__fetch private-data, 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.cantorfi/cantorfi-mcp/verify?hash=1e49aae4e28ba13f5f1746ad67634cf1425036c0f14402e32dd14991b41a5030" | jq -e '.changed == false'

Pinned hash 1e49aae4e28b, from Nov 21, 2026, 14:18 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.cantorfi/cantorfi-mcp/changes.xml

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

Badge

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

Source: MCP Registry · repository. Synced Nov 21, 2026, 14:18 UTC.

CantorFi lending vaults and agent door MCP server: questions and answers

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

Is the CantorFi lending vaults and agent door MCP server safe?

No scan can promise that. What its definitions show: 10 tools, 8 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 CantorFi lending vaults and agent door MCP server delete data?

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

Can the CantorFi lending vaults and agent door 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 CantorFi lending vaults and agent door MCP server have?

10 tools: 8 write, 2 read. cantorfi_vaults, cantorfi_vault, cantorfi_contracts, cantorfi_liquidation_bot, cantorfi_apps, cantorfi_position, cantorfi_prepare, cantorfi_paid_services and 2 more.

Does the CantorFi lending vaults and agent door MCP server need sign-in or OAuth?

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

Does the CantorFi lending vaults and agent door MCP server send data to outside services?

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

Has the CantorFi lending vaults and agent door MCP server changed its tools?

Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 21, 2026. Every change is on this page and in its Atom feed.