Postfleet MCP
Gives AI agents their own email address with inbound parsing, classification, extraction, and prompt injection screening, plus tools to manage mailboxes, send/receive emails, and handle draft approval workflows.
README
Postfleet MCP
Give an AI agent its own email address. Postfleet is email infrastructure for agents — inbound is parsed, classified, extracted to your schema, and screened for prompt injection before your agent reads a word.
This repo holds the server source and its plugin manifests. It is a mirror — the code is
developed in the Postfleet application repo and published to npm as
@postfleet/mcp; open issues here, send patches
here, and they land upstream. The server ships two ways:
| Hosted (no install) | https://api.postfleet.ai/api/mcp, streamable HTTP, Authorization: Bearer pf_... |
| Local (stdio) | @postfleet/mcp via npx |
Get a pf_ API key at postfleet.ai.
Tools
list_mailboxes, create_mailbox, list_domains, send_email, reply_email, list_inbox,
read_email, wait_for_email — plus the draft lifecycle (create_draft, list_drafts,
get_draft, update_draft, send_draft, delete_draft) for flows where a human approves
before mail goes out. A send that lands in that gate returns 202 pending_approval, which is
not a failure.
Every tool is thin-over-REST — it calls the same /api/v1/ endpoints your key already reaches
(OpenAPI), so auth, scoping, and quotas are enforced once.
Install
Cursor
The manifest in this repo declares both transports. To wire it up by hand, add your key:
{
"mcpServers": {
"postfleet": {
"url": "https://api.postfleet.ai/api/mcp",
"headers": { "Authorization": "Bearer pf_your_key_here" }
}
}
}
Claude Code
claude mcp add postfleet --env POSTFLEET_API_KEY=pf_your_key_here -- npx -y @postfleet/mcp
Any stdio client
{
"mcpServers": {
"postfleet": {
"command": "npx",
"args": ["-y", "@postfleet/mcp"],
"env": { "POSTFLEET_API_KEY": "pf_your_key_here" }
}
}
}
POSTFLEET_API_URL (default https://api.postfleet.ai) overrides the API origin for staging or
self-hosted deployments.
Keys
Keys are scoped — bootstrap can only create mailboxes, api covers mail operations, mcp is the
one to hand a client. Use a separate key per workload so you can revoke one without breaking the
rest. Never commit a key; the manifests in this repo deliberately contain none.
Links
- Registry listing:
ai.postfleet/postfleeton the MCP Registry - npm:
@postfleet/mcp - Docs: postfleet.ai/docs/mcp
Build from source
npm install && npm run build # tsup → dist/
MIT licensed.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.