PlanLimits

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

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

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "PlanLimits": {
      "url": "https://planlimits.app/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (8)

• list_plans read-only

  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".

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• get_tool_plans read-only

  Plans and limits for one tool. tool_id one of: claude-code, openai-codex, cursor, github-copilot, gemini-cli, antigravity, windsurf.

  Parameters:

  • tool_id (required) — string

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• get_recent_changes read-only

  Dated change log of AI coding plan and usage-limit changes, newest first, each with a vendor source.

  Parameters:

  • since — string — YYYY-MM-DD

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• recommend_plan read-only

  Plans priced at or under a monthly USD budget, highest price first (same logic as the PlanLimits budget picker).

  Parameters:

  • budget_usd (required) — number
  • use — string

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• route_task read-only

  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-5x, claude-max-20x, 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.

  Parameters:

  • plans (required) — array
  • task — string — refactor = Big refactor / long agent run; everyday = Everyday edits; quick = Quick questions

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• can_afford_task read-only

  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-5x, claude-max-20x, 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.

  Parameters:

  • plans (required) — array
  • size — string — small | medium (default) | large
  • task — string
  • current — string — plan id you are using now

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• pick_plan read-only

  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.

  Parameters:

  • who — string
  • usage — string
  • interface — string
  • budget_usd — number

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• get_service_status read-only

  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.

  Parameters:

  • provider — string

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

Publisher website

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.