Warning - This is a public repository, please be mindful of sharing sensitive data

Why are you seeing this issue?

This is a support escalation! You can find out more about expectations on communications and response times in the on-call docs. Thank you for doing your part to keep GitHub customers happy!

Severity

Note, for Sev1 issues always page the team first, using the PagerDuty information in the service catalog and the command .pager trigger <rotation> <reason>. Opening an issue for a Sev2 incident can come later (and can be done by the available Escalation Engineer).

• sev1 - Engineering must respond, when paged, within their on-call SLO
• sev2 - Engineering must respond to this issue within one business day
• sev3 - Engineering must respond to this issue within one week

Service

github-mcp-server

Context

⚠️ Kindly provide all the requested information to ensure a prompt and efficient response. ⚠️

GitHub Support Plan

• Top 20
• Premium Plus
• Premium
• Enterprise
• Free/Pro/Team

GitHub Product(s) Impacted (check appropriate boxes and provide GHES version if applicable)

• GitHub.com (including GHEC)
• GitHub Enterprise Server.
  • Running version: x.y.z
  • Recently upgraded from version: x.y.z (upgrade date: yyyy-mm-dd)
• Proxima (ghe.com)
  • Customer tenant: -

Customer Impact

If applicable, list the impacted entities:

• Enterprise: -
• Organization: -
• Repository: -
• User: -https://admin.github.com/stafftools/users/Lysander086/copilot_settings

Zendesk Ticket(s), support bundles, and other relevant Issues and links

• ZD_3600473_

Issue

We have a client:

https://admin.github.com/stafftools/users/Lysander086/copilot_settings

who was getting api rate limits broken constantly and after working with them they see that the MCP extension for VSCode was consuming a lot of tokens for this user.

The errors they received:

Running gh api second to second for this user produced:

lysander@MPro ~ % gh api rate_limit
{
  "resources": {
    "core": {
      "limit": 5000,
      "used": 2995,
      "remaining": 2005,
      "reset": 1755497482
    },

lysander@MPro ~ % gh api rate_limit
{
  "resources": {
    "core": {
      "limit": 5000,
      "used": 3050,
      "remaining": 1950,
      "reset": 1755497482
    },

lysander@MPro ~ % gh api rate_limit
{
  "resources": {
    "core": {
      "limit": 5000,
      "used": 4192,
      "remaining": 808,
      "reset": 1755497482
    },

The client wanted to know why the MCP server was draining all of the resources for his api rate limits, i have asked them to provide me more info on this end, but i wanted to see if there was an issue with over-consumptive api resources.

To Reproduce

Steps to reproduce the behavior:

1. Go to '...'
2. Click on '....'
3. Scroll down to '....'
4. See error

Expected behavior

A clear and concise description of what you expected to happen.

Screenshots

If applicable, add screenshots to help explain your problem.

Additional context

Add any other context about the problem here.

cc:
@github/copilot-agentservices-team-eng
@toby

Support Squad(s): @github/support-squad-worktent