Skip to content

PlanLimits MCP server

app.vercel.planlimits-rpatel021/planlimitsplanlimits-rpatel021.vercel.appstreamable-httpv1.3.0Scanned

AI coding plan limits (Claude Code, Codex, Cursor, Copilot): router, picker, status, budget check

8 tools: 4 change things and 4 only read.

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

Tools listed without sign-in. Remote posture

With Anlyon

4 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 PlanLimits MCP server can do

The PlanLimits MCP server is published by planlimits-rpatel021.vercel.app, a domain the MCP Registry verified. It has 8 tools. It can create or change data (4 tools: recommend_plan, route_task, can_afford_task and pick_plan), but cannot delete data. 4 tools only read.

2 tools bring in text other people can write (list_plans and get_service_status).

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 12, 2026, version 1.3.0.

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.

8 tools

Changes things 4Claude Code: ask
  • can_afford_taskFor agents deciding whether to start a task: given the plans you own, how much of each is used, optionally the plan you are on now, and the task size, returns verdict go | wait | s…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.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    For agents deciding whether to start a task: given the plans you own, how much of each is used, optionally the plan you are on now, and the task size, returns verdict go | wait | switch, which plan to use, reasons and reset windows. Reuses the route_task logic. Task size is a labeled heuristic (vendors don't publish per-task usage). size: small = One file or a quick question; medium = A feature across a few files (tens of minutes); large = A long refactor or multi-hour agent run. Plan ids: claude-pro, claude-max, claude-ultra, codex-free, codex-go, codex-plus, codex-pro, cursor-free, cursor-plus, cursor-premium, cursor-super, cursor-ultra, copilot-free, copilot-pro, copilot-pro-plus, copilot-max, antigravity-individual-free, antigravity-google-ai-pro, antigravity-google-ai-ultra, windsurf-free, windsurf-pro, windsurf-max.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • pick_planAnswers 4 questions and returns the cheapest fitting plan with reasons, up to 3 alternatives and source links (same logic as https://planlimits.app/picker/).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.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Answers 4 questions and returns the cheapest fitting plan with reasons, up to 3 alternatives and source links (same logic as https://planlimits.app/picker/). interface: terminal | ide | any; budget_usd: monthly USD; usage: light | daily | heavy (usage rule is a labeled rule of thumb); who: individual | team.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • recommend_planPlans priced at or under a monthly USD budget, highest price first (same logic as the PlanLimits budget picker).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.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Plans priced at or under a monthly USD budget, highest price first (same logic as the PlanLimits budget picker).

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • route_taskGiven the plans you own, how much of each is used, and the task type, returns which plan to use now, a fallback, when each limit resets (from vendor-stated windows), a rationale, a…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.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Given the plans you own, how much of each is used, and the task type, returns which plan to use now, a fallback, when each limit resets (from vendor-stated windows), a rationale, a suggested weekly rotation, and source links. Same logic as https://planlimits.app/router/. Unknowns are labeled estimate / not published. Plan ids: claude-pro, claude-max, claude-ultra, codex-free, codex-go, codex-plus, codex-pro, cursor-free, cursor-plus, cursor-premium, cursor-super, cursor-ultra, copilot-free, copilot-pro, copilot-pro-plus, copilot-max, antigravity-individual-free, antigravity-google-ai-pro, antigravity-google-ai-ultra, windsurf-free, windsurf-pro, windsurf-max.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
Only reads 4Show 4 read-only tools
  • get_recent_changesDated change log of AI coding plan and usage-limit changes, newest first, each with a vendor source.No findings

    Why it is in this group

    • The name "get_recent_changes" says "get": a word for reading.
    Description, as the server wrote it
    Dated change log of AI coding plan and usage-limit changes, newest first, each with a vendor source.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • get_service_statusLive operational status and open incidents from official vendor status pages (Claude/Anthropic, OpenAI/Codex, Cursor, GitHub Copilot, Google Cloud Gemini/Vertex AI, Windsurf).Reads text others writeNo findings

    Why it is in this group

    • The name "get_service_status" says "get": 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
    Live operational status and open incidents from official vendor status pages (Claude/Anthropic, OpenAI/Codex, Cursor, GitHub Copilot, Google Cloud Gemini/Vertex AI, Windsurf). Outages only: it does not detect throttling or per-account limits. provider one of: anthropic, openai, cursor, github, google, windsurf (or a tool id); omit for all.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • get_tool_plansPlans and limits for one tool.No findings

    Why it is in this group

    • The name "get_tool_plans" says "get": a word for reading.
    Description, as the server wrote it
    Plans and limits for one tool. tool_id one of: claude-code, openai-codex, cursor, github-copilot, gemini-cli, antigravity, windsurf.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • list_plansAll tracked AI coding tools (Claude Code, Codex, Cursor, Copilot, Gemini Code Assist, Antigravity, Windsurf) with every plan: price, stated usage limits, window, models, source URL…Reads text others writeNo findings

    Why it is in this group

    • The name "list_plans" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
    Description, as the server wrote it
    All tracked AI coding tools (Claude Code, Codex, Cursor, Copilot, Gemini Code Assist, Antigravity, Windsurf) with every plan: price, stated usage limits, window, models, source URL and checked date. Undisclosed values say "not disclosed".

    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.

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 write2
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, 18:30 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
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://planlimits.app/mcp: tools/list returned 8 tools to an anonymous client, including recommend_plan (write), route_task (write), can_afford_task (write), pick_plan (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. Tools2 changed.~2 changedView diff

Install

Pinned to version 1.3.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http planlimits https://planlimits.app/mcp
claude mcp add --transport http planlimits https://planlimits.app/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__planlimits__list_plans",
      "mcp__planlimits__get_tool_plans",
      "mcp__planlimits__get_recent_changes",
      "mcp__planlimits__get_service_status"
    ],
    "ask": [
      "mcp__planlimits__recommend_plan",
      "mcp__planlimits__route_task",
      "mcp__planlimits__can_afford_task",
      "mcp__planlimits__pick_plan"
    ],
    "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 planlimits. Review it before you use it.

Capability tags behind 2 rules
  • mcp__planlimits__list_plans untrusted-input
  • mcp__planlimits__get_service_status 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/app.vercel.planlimits-rpatel021/planlimits/verify?hash=43d9785147b4cd3a96baa550defc6cdce8c82f8ae32d5e0cf77af5b691e4e60d" | jq -e '.changed == false'

Pinned hash 43d9785147b4, from Nov 12, 2026, 04:17 UTC.

Watch

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

https://radar.anlyon.com/servers/app.vercel.planlimits-rpatel021/planlimits/changes.xml

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

Badge

Anlyon Radar badge for app.vercel.planlimits-rpatel021/planlimits
[![Anlyon Radar](https://radar.anlyon.com/badge/app.vercel.planlimits-rpatel021/planlimits.svg)](https://radar.anlyon.com/servers/app.vercel.planlimits-rpatel021/planlimits)

Source: MCP Registry. Synced Oct 21, 2026, 17:45 UTC.

PlanLimits MCP server: questions and answers

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

Is the PlanLimits MCP server safe?

No scan can promise that. What its definitions show: 8 tools, 4 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 PlanLimits MCP server delete data?

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

Can the PlanLimits 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 PlanLimits MCP server have?

8 tools: 4 write, 4 read. recommend_plan, route_task, can_afford_task, pick_plan, list_plans, get_tool_plans, get_recent_changes and get_service_status.

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

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

Does the PlanLimits MCP server send data to outside services?

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

Has the PlanLimits MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 12, 2026. Every change is on this page and in its Atom feed.