Productivity · Local MCP server
dead-letter
Convert.eml and.mbox email to clean Markdown for RAG, LLM pipelines, and local knowledge bases.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.BigCactusLabs/dead-letter- Version
- 0.4.5
- Status
- Active
- Category
- productivity
- Transport
- stdio (local process)
- Package
- PyPI, MCP Bundle (.mcpb), OCI image (Docker)
- Published
- 2026-09-28
- Updated
- 2026-09-28
- Publisher
- BigCactusLabs (GitHub)
- Repository
- github.com/BigCactusLabs/dead-letter
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| PyPIruntime: uvx | dead-letter | 0.4.5 | stdio |
| MCP Bundle (.mcpb) | https://github.com/BigCactusLabs/dead-letter/releases/download/v0.4.5/dead-letter-mcp-0.4.5.mcpbSHA-256 checksum stated | 0.4.5 | stdio |
| OCI image (Docker)runtime: docker | ghcr.io/bigcactuslabs/dead-letter@sha256:18ff617fb594196e12e3574809caf8ff5b79bea8a831f801b8fc2ac6418a82a1 | — | stdio |
How to connect dead-letter
dead-letter runs locally from a Python package published to PyPI: dead-letter version 0.4.5. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install — the usual command is uvx dead-letter.
dead-letter runs locally from an MCP Bundle: a single downloadable archive holding a local server and a manifest that describes it: https://github.com/BigCactusLabs/dead-letter/releases/download/v0.4.5/dead-letter-mcp-0.4.5.mcpb version 0.4.5. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs a client that installs MCP Bundles; the file is opened in, or added to, that client.
dead-letter runs locally from a container image in an OCI registry such as Docker Hub or GitHub Container Registry: ghcr.io/bigcactuslabs/dead-letter@sha256:18ff617fb594196e12e3574809caf8ff5b79bea8a831f801b8fc2ac6418a82a1. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Docker or another OCI container runtime; started with docker run — the usual command is docker run -i --rm ghcr.io/bigcactuslabs/dead-letter@sha256:18ff617fb594196e12e3574809caf8ff5b79bea8a831f801b8fc2ac6418a82a1.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"dead-letter": {
"command": "uvx",
"args": [
"dead-letter"
]
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More productivity servers
| Server | Runs |
|---|---|
| DayOneLeadFind newly registered businesses, manage prospects, and run approval-gated email outreach. | Remote · HTTP |
| DaystructFind source-package workflows, inspect live prices and evidence, and connect with a scoped key. | Remote · HTTP |
| DazbenchTask management your AI agents can actually run. One line becomes a context-ready task over MCP. | Remote · HTTP |
| Dead Simple EmailGive an agent its own inbox: send, receive, and pull signup codes from real email. | Remote & Local · HTTP, stdio |
| DealboardSimple deal tracker with pipeline cards, notes, goals, reports, and AI-powered deal updates. | Remote · HTTP |
| DealwizeAnalyse B2B sales deals, uncover risks, stakeholders, next steps, and winning actions. | Remote · HTTP, SSE |
| DecernMCP server for Decern CRM — contacts, deals, pipelines, tasks, and approvals. | Local · stdio |
| dechonet.com20 domain recon tools for AI agents: DNS, SSL, headers, email, subdomains, lookalikes, changes. | Remote & Local · HTTP, stdio |