Which integrations are available for this server?

Provides tools to check GitHub Copilot quota and rate-limit status, including monthly usage, session and weekly rate limit windows, and reset times.

How do I use copilot-status-mcp?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@copilot-status-mcp Show me my Copilot quota and rate limit status" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

copilot-status-mcp

by DrSmile444

Overview Schema Related Servers Score Discussions

TypeScript

Local

copilot-status-mcp

Check your GitHub Copilot quota and rate-limit status from Claude Code, Copilot, or any MCP client.

copilot-status-mcp solves a visibility problem: when Copilot blocks your request with "You've hit your rate limit", you know you're blocked — but not for how long, how close you were before it happened, or what your monthly quota looks like. This package exposes all of that as a CLI command and MCP tool.

claude mcp add --scope user copilot-status-mcp -- npx -y copilot-status-mcp --mcp

Features

Detects active rate limits and shows the exact reset time (5-hour session and weekly windows).
Shows window usage percentage when available (server sends it above 50% used).
Reports monthly quota for chat, completions, and premium model interactions.
Works for free and paid Copilot plans.
--pretty flag for a readable terminal summary.
Exposes a single MCP tool: get_copilot_status.
Does not read, store, log, or print your Copilot access token.

Related MCP server: copilot-usage-mcp

Quick Start

Print your current Copilot status in the terminal:

npx copilot-status-mcp

Pretty-print for humans:

npx copilot-status-mcp --pretty

Add to Claude Code:

claude mcp add --scope user copilot-status-mcp -- npx -y copilot-status-mcp --mcp

Then ask:

What is my current Copilot quota?
Am I rate limited on Copilot right now?

Programmatic Usage

Install the package and import directly:

npm install copilot-status-mcp

import { getCopilotStatus } from "copilot-status-mcp";

const result = await getCopilotStatus();
console.log(result.shortTermRateLimit.rateLimited); // true or false
console.log(result.shortTermRateLimit.sessionResetsAt); // ISO date if rate limited

With options:

import { getCopilotStatus } from "copilot-status-mcp";

const result = await getCopilotStatus({
  timeoutMs: 30000,
  includeLogin: true,
});

The package exports:

getCopilotStatus(options?) — fetch current Copilot quota; returns CopilotStatusResult
CopilotStatusError — thrown when the CAPI probe or token exchange fails
DEFAULT_TIMEOUT_MS — default timeout (15 000 ms)
getCopilotOAuthToken() — resolve Copilot OAuth token only
getGhToken() — resolve a general GitHub token
CredentialError — thrown when no token can be found

Requirements

Node.js 18 or newer.
One of the following for full support (session + weekly rate limits):
- JetBrains Copilot plugin installed and authenticated
- GitHub Copilot CLI: npm install -g @github/copilot && copilot auth login
- GITHUB_COPILOT_TOKEN env var set to a Copilot-issued OAuth token
For monthly quota only: gh CLI authenticated, or GITHUB_TOKEN env var set.

CLI Usage

Default — JSON output

npx copilot-status-mcp

Example output:

{
  "source": "copilot-status-mcp",
  "tokenSource": "apps.json",
  "account": {
    "plan": "individual",
    "sku": "yearly_subscriber_quota"
  },
  "shortTermRateLimit": {
    "rateLimited": false,
    "session": {
      "percentUsed": 64.7,
      "percentRemaining": 35.3,
      "entitlement": 0,
      "resetsAt": "2026-06-01T16:29:39.000Z"
    },
    "weekly": {
      "percentUsed": 55.1,
      "percentRemaining": 44.9,
      "entitlement": 0,
      "resetsAt": "2026-06-08T00:00:00.000Z"
    },
    "probeAvailable": true
  },
  "monthlyQuota": {
    "resetsAt": "2026-07-01T00:00:00.000Z",
    "chat": { "unlimited": true, "percentRemaining": 100 },
    "completions": { "unlimited": true, "percentRemaining": 100 },
    "premiumInteractions": { "remaining": 299, "entitlement": 300, "percentRemaining": 99.6 }
  }
}

When rate limited:

{
  "shortTermRateLimit": {
    "rateLimited": true,
    "sessionResetsAt": "2026-06-08T00:00:00.000Z",
    "sessionRetryAfterSecs": 310852,
    "limitKey": "global-usage-weekly-key",
    "probeAvailable": true
  }
}

Pretty output

npx copilot-status-mcp --pretty

━━━ Account ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
  Plan:         individual
  SKU:          yearly_subscriber_quota
  Token source: apps.json

━━━ Short-Term Rate Limit ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
  ✅  Not rate limited
  5h session:        64.7% used  [█████████████░░░░░░░]  35.3% remaining
  Session resets at: 2026-06-01T16:29:39.000Z (in 2h 40m)
  Weekly:            55.1% used  [███████████░░░░░░░░░]  44.9% remaining
  Weekly resets at:  2026-06-08T00:00:00.000Z (in 154h 11m)

━━━ Monthly Quota ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
  Chat:               unlimited  (100.0% remaining)
  Completions:        unlimited  (100.0% remaining)
  Premium models:     299 / 300  (99.6% remaining)
  Monthly resets at:  2026-07-01T00:00:00.000Z
  Monthly resets in:  706h 11m

All flags

npx copilot-status-mcp [options]

Options:
  --pretty               Human-readable summary instead of JSON.
  --include-login        Include GitHub login in output.
  --timeout-ms <ms>      Timeout for API requests (default: 15000).
  --mcp                  Run as an MCP stdio server.
  --help, -h             Show help.

MCP Setup

The MCP server exposes one tool: get_copilot_status.

It returns the same JSON as the CLI. Optional arguments:

{
  "timeoutMs": 15000,
  "includeLogin": false
}

Claude Code

claude mcp add --scope user copilot-status-mcp -- npx -y copilot-status-mcp --mcp

Verify:

claude mcp list
claude mcp get copilot-status-mcp

Equivalent MCP JSON:

{
  "mcpServers": {
    "copilot-status-mcp": {
      "command": "npx",
      "args": ["-y", "copilot-status-mcp", "--mcp"]
    }
  }
}

Other MCP Clients

{
  "mcpServers": {
    "copilot-status-mcp": {
      "command": "npx",
      "args": ["-y", "copilot-status-mcp", "--mcp"]
    }
  }
}

How It Works

Token resolution

Short-term rate limit probe requires a Copilot-specific OAuth token:

GITHUB_COPILOT_TOKEN env var
  └─ ~/.config/github-copilot/apps.json  (written by JetBrains / Copilot CLI)

Monthly quota works with any GitHub token:

GITHUB_COPILOT_TOKEN env var
  └─ ~/.config/github-copilot/apps.json
       └─ GITHUB_TOKEN env var
            └─ `gh auth token`

What gets called

GET https://api.github.com/copilot_internal/v2/token
  → exchange OAuth token for a short-lived CAPI session token

POST https://api.individual.githubcopilot.com/chat/completions
  max_tokens=1, model=gpt-5-mini
  → 200: not rate limited; response headers carry window usage %
  → 429: rate limited; retry-after header carries seconds until reset

GET https://api.github.com/copilot_internal/user
  → monthly quota snapshots and reset date

Rate limit windows

GitHub Copilot enforces two rolling windows on top of the monthly quota:

Window	Key	Resets
Session	`global-usage-5-hour-key`	Rolling 5 hours
Weekly	`global-usage-weekly-key`	Every Monday 00:00 UTC

Window usage percentage is only returned by the server above the 50% threshold. Below 50%, the response only confirms you are not rate limited.

Local Checkout Setup

npm install
npm run build
node dist/cli.js
node dist/cli.js --pretty
node dist/cli.js --mcp

From TypeScript directly:

npx tsx src/cli.ts
npx tsx src/cli.ts --pretty

Claude Code from local checkout

claude mcp add --scope user copilot-status-mcp -- node /absolute/path/to/copilot-status-mcp/dist/cli.js --mcp

Development

npm install          # install dependencies
npm run status       # print status from TypeScript
npm run status:pretty  # pretty output from TypeScript
npm run dev          # run MCP server from TypeScript
npm run build        # compile to dist/
npm run typecheck    # type-check without emitting
npm pack --dry-run   # preview npm package contents

Troubleshooting

No short-term rate limit data

The tool falls back to monthly-quota-only mode when no Copilot OAuth token is found. Install one of:

JetBrains Copilot plugin (authenticates automatically)
Copilot CLI: npm install -g @github/copilot && copilot auth login
Set GITHUB_COPILOT_TOKEN manually

`probeAvailable: false` in output

Same as above — no Copilot session token was available for the CAPI probe.

MCP tool does not show up

Restart Claude Code or your MCP client after adding the server.

Timeout errors

Increase the timeout:

{ "timeoutMs": 30000 }

Security Notes

OAuth tokens are read from environment variables or local config files and are never printed, logged, or stored beyond the lifetime of the request.
The CAPI probe uses a single minimal chat request (max_tokens: 1) solely to read response headers. The response content is discarded.
GitHub login is omitted from output by default; use --include-login only when needed.

These packages are part of the same family of AI provider status tools:

claude-status-mcp — Claude OAuth usage and rate-limit windows
codex-status-mcp — Codex / ChatGPT rate-limit windows and credits
provider-status-mcp — Aggregates Claude, Codex, and Copilot status into a single view

License

MIT

Made with ❤️ by Dmytro Vakulenko, 2026

Available Tools

1 tool

get_copilot_statusA

Retrieve GitHub Copilot quota and rate-limit status: whether the 5-hour session window is exhausted and when it resets, weekly window usage, and monthly quota for chat, completions, and premium models.

ParametersJSON Schema

Name	Required	Description	Default
`timeoutMs`	No	Timeout in milliseconds for API requests. Defaults to 15000.
`includeLogin`	No	Include the GitHub login in the response. Defaults to false.

TDQS

A3.8/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are present, so the description must carry the transparency burden. It discloses that the tool reads quota and rate-limit status without side effects, but does not mention auth requirements, error behavior, or external API interactions. Adequate but not comprehensive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence that front-loads the core purpose and efficiently enumerates the returned metrics. Every phrase adds value with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a status-checking tool with no output schema, the description sufficiently explains what the agent will receive and the main parameters are documented in the schema. It could note the response format or potential errors, but the core context is complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema provides full descriptions for both parameters (timeoutMs and includeLogin), achieving 100% coverage. The tool description adds no parameter-specific meaning, so the baseline score of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the specific verb 'Retrieve' and clearly identifies the resource as GitHub Copilot quota and rate-limit status. It lists concrete data points returned, making the tool's purpose unmistakable even without sibling comparison.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit when-to-use or alternative guidance is provided, but the description implies the tool is for checking Copilot limits before or during usage. Since there are no sibling tools, the lack of alternatives is acceptable, but clearer use-case framing would strengthen this dimension.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4/5.0

Disambiguation5/5

With only one tool, there is no possibility of confusion. The tool's purpose is clearly and uniquely defined.

Naming Consistency5/5

The tool name follows a standard verb_noun pattern, is descriptive, and is internally consistent despite being the only tool.

Tool Count3/5

A single tool feels thin for a server, but it could be justified if the entire purpose is status retrieval. However, it falls at the borderline of the typical 3-15 tool range.

Completeness5/5

The tool comprehensively covers the domain of Copilot status, including session window, weekly usage, monthly quota, and premium models. No obvious gaps exist for its stated purpose.

Maintenance

ActivityStale

ResponsivenessSyncing

Resources

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

docs
dev.continue
An MCP server for docs.continue.dev
Documentation Access Developer Tools Search
2
gread A
io.github.NitroRCr
An MCP server that gives your AI access to the source code and docs of all public github repos
Version Control Code Analysis Documentation Access
5361
mcp AOAuth
com.mux
The official MCP Server for the Mux API
Multimedia Processing Entertainment & Media API Testing
22168
mcp-aichat
io.github.AceDataCloud
MCP server for AI dialogue using various LLM models via AceDataCloud
AI & Machine Learning
2

Related MCP Servers

GitHub Copilot Usage MCP
Developer Tools Monitoring
lucasliet
A
license
A
quality
F
maintenance
An MCP server that retrieves current GitHub Copilot usage data, including quotas, limits, and usage statistics. It allows AI agents to monitor premium interaction status and detailed account usage via raw or formatted summaries.
Updated 9 months ago (2025-12-09 18:39 UTC)
3
16
MIT
copilot-usage-mcp
Monitoring Developer Tools Version Control
tatsuyamiyazaki
A
license
A
quality
C
maintenance
An MCP server that retrieves GitHub Copilot usage metrics and seat assignment data across Enterprise, Organization, and Team levels. It allows users to monitor code completions, chat activity, and active user counts through integrated tools.
Updated a month ago (2026-07-31 02:16 UTC)
5
2
MIT
mcp-github-server
Version Control Developer Tools
Mervecaliskann
F
license
Not graded
quality
D
maintenance
A simple MCP server that provides repository information (list repos, get repo details) using GitHub's public REST API, without needing any API keys or tokens.
Updated 3 months ago (2026-06-13 17:16 UTC)
mcp-github-copilot
AI & Machine Learning Developer Tools
kud
A
license
A
quality
B
maintenance
MCP server for GitHub Copilot that allows querying any Copilot model programmatically using existing Copilot CLI credentials, with support for file attachments and model discovery.
Updated a month ago (2026-08-03 16:31 UTC)
2
19
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/DrSmile444/copilot-status-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

copilot-status-mcp

Features

Quick Start

Programmatic Usage

Requirements

CLI Usage

Default — JSON output

Pretty output

All flags

MCP Setup

Claude Code

Other MCP Clients

How It Works

Token resolution

What gets called

Rate limit windows

Local Checkout Setup

Claude Code from local checkout

Development

Troubleshooting

No short-term rate limit data

probeAvailable: false in output

MCP tool does not show up

Timeout errors

Security Notes

Related Packages

License

Available Tools

TDQS

TDQS

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

GitHub Copilot Usage MCP

copilot-usage-mcp

mcp-github-server

mcp-github-copilot

Latest Blog Posts

MCP directory API

`probeAvailable: false` in output