Skip to content

Delivery Planner by Spoke MCP server

com.deliveryplanner/delivery-plannerdeliveryplanner.comstreamable-httpv1.0.0Scanned

Plan and optimize a multi-stop delivery route, then share it with your driver.

6 tools: 3 change things and 3 only read.

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

Tools listed without sign-in. Remote posture

With Anlyon

3 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 Delivery Planner by Spoke MCP server can do

The Delivery Planner by Spoke MCP server is published by deliveryplanner.com, a domain the MCP Registry verified. It has 6 tools. It can create or change data (3 tools: create_route, confirm_route and select_addresses), but cannot delete data. 3 tools only read.

3 tools bring in text other people can write (search_places, create_route and resolve_current_location).

The fixed checks matched 1 finding (annotation-conflict). 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 18, 2026, version 1.0.0.

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.

6 tools

Changes things 3Claude Code: ask
  • confirm_routeCalled by the address panel when the user clicks Optimize.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
    Called by the address panel when the user clicks Optimize. Records the chosen addresses and route settings and returns the single-use confirmationToken that create_route takes. Not for direct model use.

    Annotations the server declares

    • title: Confirm reviewed route
    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: false
  • create_routeOptimizes and saves one driving route for one driver with 1–20 delivery stops, from the addresses and settings the user confirmed in the address panel.Reads text others writeNo findings

    Why it is in this group

    • The name "create_route" says "create": a word for a change.

    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
    Optimizes and saves one driving route for one driver with 1–20 delivery stops, from the addresses and settings the user confirmed in the address panel. Use this when a user asks what order to visit delivery addresses, wants an efficient driving route between multiple stops, or wants a route they can open and share. Takes the single-use token the panel issues when the user clicks Optimize route. Returns the stops in optimized order, estimated duration and distance, the route geometry, and route links. Every call creates a new route, and anyone with the returned link can view its addresses. Does not enforce delivery time windows, and not for package tracking, public transit, multiple drivers, or live-traffic estimates.

    Annotations the server declares

    • title: Plan a delivery route with Spoke
    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: true
    • idempotentHint: false
  • select_addressesShows a panel where the user picks a match for each address and sets the start, finish, time at each stop and distance unit.1 finding

    Why it is in this group

    • The name "select_addresses" says "select": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "select_addresses" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "select_addresses" says "select": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Shows a panel where the user picks a match for each address and sets the start, finish, time at each stop and distance unit. Takes each original address with its suggested matches; addresses without suggestions let the user search again in the panel. Missing start and finish appear as empty fields, and fields in routeSettings.ignoredFields are listed as not applied. Read-only: when the user clicks Optimize, the panel issues a single-use confirmation token for route creation.

    Annotations the server declares

    • title: Choose addresses and route settings
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
    • idempotentHint: true
Only reads 3Show 3 read-only tools
  • resolve_current_locationReturns the nearest address for coordinates from the Use current location button in the panel, to fill the start.Reads text others writeNo findings

    Why it is in this group

    • The name "resolve_current_location" says "resolve": a word for reading.

    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
    Returns the nearest address for coordinates from the Use current location button in the panel, to fill the start.

    Annotations the server declares

    • title: Find starting address from current location
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • search_placesFinds Google address suggestions, with place IDs, for one address or place name.Reads text others writeNo findings

    Why it is in this group

    • The name "search_places" says "search": a word for reading.

    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
    Finds Google address suggestions, with place IDs, for one address or place name. Use this when a user wants to plan deliveries, order driving stops, or optimize a multi-stop driving route and provides addresses or place names, including pasted spreadsheets, tables, CSV, or numbered lists. Suggestions come from autocomplete and are not validated addresses. Not for general place recommendations, package tracking, or public-transit directions.

    Annotations the server declares

    • title: Find delivery addresses
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • show_dispatch_optionsShows a link to Spoke Dispatch, our route planner for teams, for needs this free planner does not cover: multiple drivers, enforced delivery time windows, or more than 20 delivery …No findings

    Why it is in this group

    • The name "show_dispatch_options" says "show": a word for reading.
    Description, as the server wrote it
    Shows a link to Spoke Dispatch, our route planner for teams, for needs this free planner does not cover: multiple drivers, enforced delivery time windows, or more than 20 delivery stops. Use this only when the user explicitly asks for one of those. It only displays the link; it does not transfer addresses or create a Dispatch account.

    Annotations the server declares

    • title: More delivery planning options
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
    • idempotentHint: 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 private-data or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write3
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 19, 2026, 17:22 UTC, unchanged since Nov 5, 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
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://deliveryplanner.com/api/free-route-planner/mcp: tools/list returned 6 tools to an anonymous client, including create_route (write), confirm_route (write), select_addresses (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • The server marks "select_addresses" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "select_addresses" says "select": a word for a change.

    What this check looks for

History

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

  1. Tools6 changed.~6 changedView diff

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http delivery-planner https://deliveryplanner.com/api/free-route-planner/mcp
claude mcp add --transport http delivery-planner https://deliveryplanner.com/api/free-route-planner/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__delivery-planner__search_places",
      "mcp__delivery-planner__show_dispatch_options",
      "mcp__delivery-planner__resolve_current_location"
    ],
    "ask": [
      "mcp__delivery-planner__create_route",
      "mcp__delivery-planner__confirm_route",
      "mcp__delivery-planner__select_addresses"
    ],
    "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 delivery-planner. Review it before you use it.

Capability tags behind 3 rules
  • mcp__delivery-planner__search_places untrusted-input
  • mcp__delivery-planner__create_route untrusted-input
  • mcp__delivery-planner__resolve_current_location 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/com.deliveryplanner/delivery-planner/verify?hash=0fb19c976dd792b908762af500dd1ab1dbb8d91bf3fd65c5e2aff735b4b699ab" | jq -e '.changed == false'

Pinned hash 0fb19c976dd7, from Nov 18, 2026, 15:18 UTC.

Watch

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

https://radar.anlyon.com/servers/com.deliveryplanner/delivery-planner/changes.xml

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

Badge

Anlyon Radar badge for com.deliveryplanner/delivery-planner
[![Anlyon Radar](https://radar.anlyon.com/badge/com.deliveryplanner/delivery-planner.svg)](https://radar.anlyon.com/servers/com.deliveryplanner/delivery-planner)

Source: MCP Registry. Synced Nov 4, 2026, 22:17 UTC.

Delivery Planner by Spoke MCP server: questions and answers

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

Is the Delivery Planner by Spoke MCP server safe?

No scan can promise that. What its definitions show: 6 tools, 3 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 Delivery Planner by Spoke MCP server delete data?

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

Can the Delivery Planner by Spoke 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 Delivery Planner by Spoke MCP server have?

6 tools: 3 write, 3 read. create_route, confirm_route, select_addresses, search_places, show_dispatch_options and resolve_current_location.

Does the Delivery Planner by Spoke MCP server need sign-in or OAuth?

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

Does the Delivery Planner by Spoke MCP server send data to outside services?

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

Has the Delivery Planner by Spoke MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 18, 2026. Every change is on this page and in its Atom feed.