AI coding plan limits (Claude Code, Codex, Cursor, Copilot): router, picker, status, budget check
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh 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-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.
small | medium (default) | large
plan id you are using now
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.
| Argument | Type | Description |
|---|---|---|
| size | string | small | medium (default) | large |
| task | string | |
| plans* | array | |
| current | string | plan id you are using now |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"plans"
],
"properties": {
"size": {
"type": "string",
"maxLength": 20,
"description": "small | medium (default) | large"
},
"task": {
"type": "string",
"maxLength": 40
},
"plans": {
"type": "array",
"items": {
"type": "object",
"required": [
"plan"
],
"properties": {
"plan": {
"type": "string"
},
"state": {
"type": "string",
"maxLength": 40,
"description": "fine | low | session_hit | exhausted (weekly_hit / monthly_hit = exhausted)"
}
},
"additionalProperties": false
},
"maxItems": 12,
"minItems": 1
},
"current": {
"type": "string",
"maxLength": 40,
"description": "plan id you are using now"
}
},
"additionalProperties": false
}Dated change log of AI coding plan and usage-limit changes, newest first, each with a vendor source.
| Argument | Type | Description |
|---|---|---|
| since | string | YYYY-MM-DD |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"since": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "YYYY-MM-DD"
}
},
"additionalProperties": false
}Live operational status and open incidents from official vendor status pages (Claude/Anthropic, OpenAI/Codex, Cursor, GitHub Copilot, Google Cloud Gemini/Vertex AI, Windsurf). Outages only: it does not detect throttling or per-account limits. provider one of: anthropic, openai, cursor, github, google, windsurf (or a tool id); omit for all.
| Argument | Type | Description |
|---|---|---|
| provider | string |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"provider": {
"type": "string",
"maxLength": 40
}
},
"additionalProperties": false
}Plans and limits for one tool. tool_id one of: claude-code, openai-codex, cursor, github-copilot, gemini-cli, antigravity, windsurf.
| Argument | Type | Description |
|---|---|---|
| tool_id* | string |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"tool_id"
],
"properties": {
"tool_id": {
"type": "string"
}
},
"additionalProperties": false
}All tracked AI coding tools (Claude Code, Codex, Cursor, Copilot, Gemini Code Assist, Antigravity, Windsurf) with every plan: price, stated usage limits, window, models, source URL and checked date. Undisclosed values say "not disclosed".
No arguments.
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {}
}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.
| Argument | Type | Description |
|---|---|---|
| who | string | |
| usage | string | |
| interface | string | |
| budget_usd | number |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"who": {
"type": "string",
"maxLength": 20
},
"usage": {
"type": "string",
"maxLength": 20
},
"interface": {
"type": "string",
"maxLength": 20
},
"budget_usd": {
"type": "number",
"minimum": 0
}
},
"additionalProperties": false
}Plans priced at or under a monthly USD budget, highest price first (same logic as the PlanLimits budget picker).
| Argument | Type | Description |
|---|---|---|
| use | string | |
| budget_usd* | number |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"budget_usd"
],
"properties": {
"use": {
"enum": [
"individual",
"team",
"any"
],
"type": "string"
},
"budget_usd": {
"type": "number",
"minimum": 0
}
},
"additionalProperties": false
}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.
| Argument | Type | Description |
|---|---|---|
| task | string | refactor = Big refactor / long agent run; everyday = Everyday edits; quick = Quick questions |
| plans* | array |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"plans"
],
"properties": {
"task": {
"type": "string",
"maxLength": 40,
"description": "refactor = Big refactor / long agent run; everyday = Everyday edits; quick = Quick questions"
},
"plans": {
"type": "array",
"items": {
"type": "object",
"required": [
"plan"
],
"properties": {
"plan": {
"type": "string",
"description": "plan id, e.g. claude-pro"
},
"state": {
"type": "string",
"maxLength": 40,
"description": "fine = Fine / plenty left; low = Running low (~80% of the main limit used); session_hit = Hit the short (session/daily) limit; exhausted = Hit the main (weekly/monthly) limit; weekly_hit / monthly_hit = aliases of exhausted. Unknown values are rejected."
}
},
"additionalProperties": false
},
"maxItems": 12,
"minItems": 1
}
},
"additionalProperties": false
}