Skip to content

Courio (sendcourio.com) MCP server

si.courio/couriocourio.sistreamable-httpv1.0.1Scanned

Courio (sendcourio.com): mail real paper letters (standard, registered) worldwide. No account.

5 tools: 3 do something that can't be undone and 2 only read.

Tools: 0 delete, 3 irreversible, 0 write, 2 read.
  • Reads private data · 1
  • Reads text others write · 2
  • Can send data out · 3
  • 2 findings

Tools listed without sign-in. Remote posture

With Anlyon

3 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 Courio (sendcourio.com) MCP server can do

The Courio (sendcourio.com) MCP server is published by courio.si, a domain the MCP Registry verified. It has 5 tools. It can do things that cannot be undone, such as sending, paying or publishing (quote_letter, send_letter and send_feedback), but cannot delete data. 2 tools only read.

1 tool reads private data (get_coverage); 2 tools bring in text other people can write (get_coverage and send_letter); 3 tools can send data out of your system (quote_letter, send_letter and send_feedback). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

The fixed checks matched 2 findings (credentials-mention). 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 9, 2026, version 1.0.1.

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.

5 tools

Can't be undone 3Claude Code: ask
  • quote_letterPrices a physical letter (printed, enveloped and posted by Courio) and returns a quote_id.Can send data outNo findings

    Why it is in this group

    • 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
    Prices a physical letter (printed, enveloped and posted by Courio) and returns a quote_id. Free and commits to nothing: no account, no payment, nothing is mailed. Give the service level, sender and recipient postal addresses, and the document (pdf_base64, pdf_url, or plain/markdown text). The price is in EUR including VAT (set currency to "USD" to also see a USD price), fixed for 24 hours. The document is checked and content-moderated; a problem comes back as an error with a hint. Quotes are capped per day (limit_exceeded with retry_after): reuse a quote_id rather than re-quoting. Service levels: "standard" (ordinary mail, no proof), "tracked" (tracking only), "registered" (registered mail: proof of deposit), "registered_ar" (registered with acknowledgement of receipt: proof of delivery, the one to use for legal notices). The quote gives the estimated delivery time (estimated_delivery_days). Next step: show the price, the legal product and the terms of sale (terms_url) to the human, then call send_letter if they agree.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • send_feedbackSend feedback to the developers of this server: a feature request, or something the user asked for that these tools can't do.Can send data out1 finding

    Why it is in this group

    • The name "send_feedback" says "send": a word for sending, and what is sent cannot be taken back.

    What it can reach

    • outboundThe name "send_feedback" says "send": it sends or publishes something to other people.

    Findings

    • Info

      The input schema at properties.capability.description mentions "credentials".

      Matched text

      inputSchema.properties.capability.description: "...s and roles. Omit names, contacts, IDs, credentials and all tool argument values."

      What this check looks for
    Description, as the server wrote it
    Send feedback to the developers of this server: a feature request, or something the user asked for that these tools can't do. The user can also ask you to send feedback directly.

    Annotations the server declares

    • title: Send feedback
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • send_letterCreates the letter for a quote and returns a payment link (Stripe Checkout).Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "send_letter" says "send": a word for sending, and what is sent cannot be taken back.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe name "send_letter" says "send": it sends or publishes something to other people.
    • outboundThe input takes a URL (input.webhook_url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Creates the letter for a quote and returns a payment link (Stripe Checkout). No account is needed. YOU CANNOT PAY: show the price and the payment link to the human and ask them to open it and pay. The letter is mailed right after payment and cannot be cancelled or recalled once paid, so paying is the point of no return: make sure the human has seen the price, the recipient and the document first. Calling it again with the same quote_id returns the same letter and link (or its current status once it has been paid). The link expires after about 24 hours. Optionally pass webhook_url (public https) to be notified of status changes. Poll get_letter_status to follow the letter. Autonomous agents whose owner gave them a card through a Stripe Shared Payment Token (e.g. Link) can pay by card themselves with MPP through the REST API (POST /v1/letters with payment_method "mpp", which may be disabled: 422 payment_method_unavailable). Agents that can sign crypto payments can instead pay with x402 through the REST API (POST /v1/letters with payment_method "x402", which may be disabled on this deployment: 422 payment_method_unavailable); official x402 clients cap a payment at $1 by default, so raise the spend limit to cover the quoted price first.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
Only reads 2Show 2 read-only tools
  • get_coverageLists which destination countries and service levels Courio can mail a physical paper letter to, with an indicative "from" price (EUR including VAT, 1 black-and-white page), typica…Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "get_coverage" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "list" and "mail": it reads mail.
    • untrusted-inputThe description's first sentence says "list" and "mail": it reads inbound email, which other people can write.
    Description, as the server wrote it
    Lists which destination countries and service levels Courio can mail a physical paper letter to, with an indicative "from" price (EUR including VAT, 1 black-and-white page), typical delivery time and the legal product name. No account or API key is needed. Call it before quote_letter to check a destination is served; pass a country (ISO 3166-1 alpha-2, e.g. "DE") to narrow the answer. Service levels: "standard" (ordinary mail, no proof), "tracked" (tracking only), "registered" (registered mail: proof of deposit), "registered_ar" (registered with acknowledgement of receipt: proof of delivery, the one to use for legal notices).

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_letter_statusReturns the current status of a letter (awaiting_payment, paid, submitted, in_transit, delivered, failed, expired, ...), its timeline and, once available, proof links (proof of dep…1 finding

    Why it is in this group

    • The name "get_letter_status" says "get": a word for reading.

    Findings

    • Info

      The description mentions "credential".

      Matched text

      description: "...account is needed; the letter_id is the credential. Recipient details are partially redact..."

      What this check looks for
    Description, as the server wrote it
    Returns the current status of a letter (awaiting_payment, paid, submitted, in_transit, delivered, failed, expired, ...), its timeline and, once available, proof links (proof of deposit for "registered", proof of delivery for "registered_ar"). No account is needed; the letter_id is the credential. Recipient details are partially redacted unless the request carries the API key that created the letter.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false

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.

6 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 private-data tool breaks every one.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write2
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out3
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__courio__get_coverage"
    ]
  }
}

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 18, 2026, 16:23 UTC, unchanged since Nov 11, 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
3
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 3 tools that change things (3 irreversible). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://api.sendcourio.com/mcp: tools/list returned 5 tools to an anonymous client, including quote_letter (irreversible), send_letter (irreversible), send_feedback (irreversible)

    What this check looks for

Posture changes

  1. Nov 11, 2026
    • Tools that change things, listed without credentials: 2 to 3

Findings

Matches of fixed checks, with the text they matched.

2 info
  • The description mentions "credential".

    Matched text

    description: "...account is needed; the letter_id is the credential. Recipient details are partially redact..."

    What this check looks for
  • The input schema at properties.capability.description mentions "credentials".

    Matched text

    inputSchema.properties.capability.description: "...s and roles. Omit names, contacts, IDs, credentials and all tool argument values."

    What this check looks for

History

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

  1. PostureRemote posture changed. Tools that change things, listed without credentials: 2 -> 3.View diff
    • Tools that change things, listed without credentials: 2 to 3
  2. Tools1 added, 4 changed.+1 added~4 changedView diff

Install

Pinned to version 1.0.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http courio https://api.sendcourio.com/mcp
claude mcp add --transport http courio https://api.sendcourio.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__courio__get_coverage",
      "mcp__courio__get_letter_status"
    ],
    "ask": [
      "mcp__courio__quote_letter",
      "mcp__courio__send_letter",
      "mcp__courio__send_feedback"
    ],
    "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 courio. Review it before you use it.

Capability tags behind 4 rules
  • mcp__courio__get_coverage private-data, untrusted-input
  • mcp__courio__quote_letter outbound
  • mcp__courio__send_letter untrusted-input, outbound
  • mcp__courio__send_feedback 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/si.courio/courio/verify?hash=6663be54febd83860b29ea54b3b63f6ceafbef563916cd21b0ff72a94231ea6c" | jq -e '.changed == false'

Pinned hash 6663be54febd, from Nov 9, 2026, 21:18 UTC.

Watch

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

https://radar.anlyon.com/servers/si.courio/courio/changes.xml

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

Badge

Anlyon Radar badge for si.courio/courio
[![Anlyon Radar](https://radar.anlyon.com/badge/si.courio/courio.svg)](https://radar.anlyon.com/servers/si.courio/courio)

Source: MCP Registry. Synced Nov 9, 2026, 21:18 UTC.

Courio (sendcourio.com) MCP server: questions and answers

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

Is the Courio (sendcourio.com) MCP server safe?

No scan can promise that. What its definitions show: 5 tools, 3 of which can change, send or delete something, and 2 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 Courio (sendcourio.com) MCP server delete data?

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

Can the Courio (sendcourio.com) MCP server do things that cannot be undone?

Yes. 3 tools can send, pay, publish or merge: quote_letter, send_letter and send_feedback.

What tools does the Courio (sendcourio.com) MCP server have?

5 tools: 3 irreversible, 2 read. quote_letter, send_letter, send_feedback, get_coverage and get_letter_status.

Does the Courio (sendcourio.com) MCP server need sign-in or OAuth?

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

Does the Courio (sendcourio.com) MCP server send data to outside services?

3 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): quote_letter, send_letter and send_feedback.

Has the Courio (sendcourio.com) MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 9, 2026. Every change is on this page and in its Atom feed.