mcpField
S
standupbot

standupbot

Local
github.com/rimysoreVersion Control0Updated 18w ago

About standupbot

standupbot is an MCP server connecting GitHub activity to Claude. It summarizes commits, PRs, reviews, and issues for individuals or teams, and reports recent repository activity.

Key features

  1. 01Summarizes recent commits, PRs, reviews, and issues
  2. 02Generates team standup summaries
  3. 03Checks public or private repository activity
  4. 04Accepts a GitHub token through an environment variable

Use cases

  1. 01Prepare a personal daily standup
  2. 02Summarize recent work across a team
  3. 03Review recent activity in a repository

MCP support

The MCP server exposes tools for personal and team standups and repository activity, retrieving data directly from the GitHub API.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"rimysore-standupbot": {
"command": "npx",
"args": [
"-y",
"standupbot-mcp"
],
"env": {
"GITHUB_TOKEN": "<GITHUB_TOKEN>"
}
}
}
}
Run commandnpx -y standupbot-mcp
Environment variables to set
GITHUB_TOKENSecretGitHub personal access token with read:user and repo scopes. Generate at https://github.com/settings/tokens

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmstandupbot-mcp1.0.1

Tools

3

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
usernamestringYesYour GitHub username, e.g. 'torvalds'
hours_backintegerNoHow many hours back to look. Default 24.
github_tokenstringNoGitHub personal access token. If omitted, uses the GITHUB_TOKEN env var set in MCP config.

Details

From the project README

StandupBot MCP

"What did I even do yesterday?" — solved.

StandupBot is a free Model Context Protocol server that connects Claude to your GitHub activity. Ask Claude for your standup and it pulls the last 24h of commits, PRs, reviews, and issues — formatted and ready to paste into Slack.


Tools

ToolWhat it does
get_standupYour personal standup — commits, PRs, reviews, issues in the last N hours
get_standup_multiTeam standup — same thing for a list of GitHub usernames
get_repo_pulseRecent activity on any public or private repo

Quick Start

1. Get a GitHub token

Go to GitHub → Settings → Developer settings → Personal access tokens → Tokens (classic).

Create a token with these scopes:

  • repo (to see private repos)
  • read:user
2. Add to Claude Code

Add this to your Claude Code config (~/.claude/claude_desktop_config.json for Claude Desktop, or .claude/settings.json for Claude Code CLI):

{
  "mcpServers": {
    "standupbot": {
      "command": "npx",
      "args": ["-y", "standupbot-mcp"],
      "env": {
        "GITHUB_TOKEN": "ghp_your_token_here"
      }
    }
  }
}
3. Ask Claude
Give me my standup for the last 24 hours. My GitHub username is alice.
Generate a team standup for usernames: alice, bob, carol
What's been happening in the facebook/react repo today?

Example Output

## Daily Standup — @alice
_Last 24h of GitHub activity_

### Commits
- **alice/my-app** (a3f9c12) — fix: resolve race condition in auth middleware
  https://github.com/alice/my-app/commit/a3f9c12

### PRs Opened
- **alice/my-app** (#42) — feat: add OAuth2 support
  https://github.com/alice/my-app/pull/42

### PRs Reviewed
- **team-org/backend** (#99) — refactor: extract payment service
  https://github.com/team-org/backend/pull/99

Environment Variables

You can set GITHUB_TOKEN as an env var in your MCP config and omit it from tool calls:

"env": { "GITHUB_TOKEN": "ghp_..." }

The tool will fall back to the env var automatically if no token is passed.


Privacy

  • Your token is stored only in your local config file.
  • StandupBot makes direct HTTPS calls to api.github.com — no proxy, no telemetry, no servers.
  • 100% open source. MIT license.

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.