Email sending
Skill Eng-Muhammad-Affan/digital-fte/.qwen/skills/email-sending
Personal AI agent that handles social media as well as any social media
npx -y skills add Eng-Muhammad-Affan/digital-fte --skill email-sendingAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Send emails via Gmail using the Email MCP server. Supports sending, drafting, searching emails, and marking as read. Use when tasks require email communication, sending invoices, replying to clients, or managing Gmail inbox.
SKILL.md
3.7 KB, as published. Nobody here has run it
Email Sending Skill
Send and manage emails via Gmail MCP server built with FastMCP.
MCP Server Setup
Start Email MCP Server
# Start with stdio transport (for Claude Code integration)
uv run python mcp-servers/email/server.py
# Or start with HTTP transport
uv run python mcp-servers/email/server.py --transport http --port 8801
Configure Claude Code MCP
Add to your Claude Code MCP configuration:
{
"mcpServers": {
"email": {
"command": "uv",
"args": ["run", "python", "mcp-servers/email/server.py"]
}
}
}
Gmail API Setup
- Go to Google Cloud Console
- Create a new project
- Enable Gmail API
- Create OAuth 2.0 credentials
- Download
credentials.json - Place in
~/.gmail_watcher/credentials.json - First run will auto-generate token
Tools
send_email
Send an email via Gmail.
uv run python scripts/mcp-client.py call -t send_email -p '{
"to": "[email protected]",
"subject": "Invoice #123",
"body": "Please find attached your invoice...",
"html": false
}'
Parameters:
to(required): Recipient email addresssubject(required): Email subjectbody(required): Email body contentfrom_email(optional): Sender emailcc(optional): CC recipients (comma-separated)bcc(optional): BCC recipients (comma-separated)html(optional): Whether body is HTML (default: false)
draft_email
Create a draft email in Gmail (does not send).
uv run python scripts/mcp-client.py call -t draft_email -p '{
"to": "[email protected]",
"subject": "Proposal for Project",
"body": "Dear Client, Here is the proposal..."
}'
search_emails
Search emails in Gmail.
# Find unread emails
uv run python scripts/mcp-client.py call -t search_emails -p '{
"query": "is:unread",
"max_results": 10
}'
# Find emails from specific sender
uv run python scripts/mcp-client.py call -t search_emails -p '{
"query": "from:[email protected]",
"max_results": 5
}'
Parameters:
query(required): Gmail search querymax_results(optional): Maximum results (default: 10)
get_email_content
Get full content of a specific email.
uv run python scripts/mcp-client.py call -t get_email_content -p '{
"message_id": "123abc"
}'
mark_as_read
Mark an email as read.
uv run python scripts/mcp-client.py call -t mark_as_read -p '{
"message_id": "123abc"
}'
Workflow: Reply to Client Email
- Search for unread emails
- Get email content
- Draft reply (requires approval)
- On approval, send email
Workflow: Send Invoice
- Create invoice PDF
- Draft email with attachment
- Create approval file in
/Pending_Approval/ - On approval (file moved to
/Approved/), send email
Environment Variables
# Gmail credentials
GMAIL_CREDENTIALS_PATH=~/.gmail_watcher/credentials.json
GMAIL_TOKEN_PATH=~/.gmail_watcher/token.json
# Dry run mode
DRY_RUN=true # Set to 'false' for production
Troubleshooting
| Issue | Solution |
|---|---|
| Authentication failed | Re-run server to trigger OAuth flow |
| Credentials not found | Download from Google Cloud Console |
| Email not sending | Check DRY_RUN environment variable |
| API quota exceeded | Wait and retry, or increase quota |
Related Skills
- linkedin-posting - Social media posting
- whatsapp-monitoring - WhatsApp message monitoring
Gives 0 of the 12 instructions most mcp tooling skills give
Counted across 638 of the 750 authors here whose files we hold, read 2026-08-06
- create ten complex read-only evaluation questionsin 71 of 638, across 17 files
- test servers using MCP Inspectorin 60 of 638, across 18 files
- provide actionable error messagesin 56 of 638, across 14 files
- prioritize comprehensive API coverage over specific workflowsin 54 of 638, across 12 files
- use TypeScript and Streamable HTTP for remote serversin 53 of 638, across 7 files
- define structured output schemas where possiblein 51 of 638, across 9 files
- use Zod or Pydantic for input schemasin 48 of 638, across 6 files
- fetch MCP specification pages with markdown suffixin 46 of 638, across 4 files
- load framework documentation using WebFetchin 45 of 638, across 3 files
- verify each evaluation answer independentlyin 45 of 638, across 3 files
- implement API client with authentication and paginationin 45 of 638, across 3 files
- Define input schemas with validationin 28 of 638, across 10 files
Said here and by no other author read
- search unread emails first
- get full email content
- draft a reply requiring approval
- send email upon approval
- create invoice pdf
- draft email with attachment
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.