mcp server
Atomic Mail
Programmable email inbox for AI agents — JMAP, PoW auth, stdio MCP server.
Description as published by the maintainer. Source
- version 0.3.25
- active
active — Most recent push to the repository was 2026-07-29.
What this server can do
3 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.
help(topic)- Built-in agent docs — call early and often, even if you know JMAP. Topics: overview, installation, auth, jmap_cheatsheet, tools, presets, cron, multi_account, troubleshooting, readme. Omit topic for overview; use presets before jmap_request, cron after register, troubleshooting when stuck.
jmap_request(ops, vars, using, dry_run, ops_file, attachments, credentials_dir)- JMAP method-call batch with automatic auth. Exactly one of: `ops` (JSON string: methodCalls array or full envelope) or `ops_file` (preset path; relative to credential directory). `$VAR` substitution and optional file `attachments`: see `help` topics presets and jmap_cheatsheet.
register(forced, username, credentials_dir)- PoW signup; writes credentials. Usernames are 5–21 characters. Idempotent for the same username and stored inbox; a different username is rejected unless `forced: true` is provided. To keep the existing account and add another, pass `credentials_dir` with a separate path instead of `forced`. Returns inbox, accountId, apiKey (first signup only). After success, arrange hourly inbox polling per your runtime (help topic cron): native cron hosts schedule an AGENT turn with ops_file list_inbox.json; no-native-cron hosts ask the operator or remind manual fetch — do not work around with OS crontab or cross-platform scheduling. Do NOT cron atomicmail jmap_request alone. Required: username.
Last successful function declaration observed on
.
Source: pkg:npm/@atomicmail/mcp-modelcontextprotocol. We list what the server declared;
we do not call any of these functions.
Endpoint status observed on
.
Source: pkg:npm/@atomicmail/mcp-modelcontextprotocol.
Signals
These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.
| Signal | Value | What it measures | Window | Observed | Source |
|---|---|---|---|---|---|
| GitHub stars | 270 | Number of GitHub accounts that bookmarked this repository since it was created. It is a bookmark count, not installs, not active users and not quality. | cumulative, all time | GitHub | |
| Last commit | 2026-07-29 | Date of the most recent push to any branch. This is the strongest cheap indicator of whether the project is still maintained. | point in time | GitHub | |
| Open issues | 0 | Open issues plus open pull requests, as GitHub counts them together. A high number can mean an active project or an abandoned one. | as of fetch | GitHub | |
| Latest published version | 0.3.25 | Latest version string the maintainer published to the registry. | as of fetch | Model Context Protocol | |
| Registry record last updated | 2026-07-29 | When the registry record was last updated by its maintainer. | point in time | Model Context Protocol | |
| License | MIT | Licence GitHub detected in the repository. Detection can be wrong; the LICENSE file is authoritative. | as of fetch | GitHub | |
| First listed in the MCP Registry | 2026-07-29 | Date this server was first published to the official MCP Registry. Not a usage or quality measure. | point in time | Model Context Protocol | |
| repository status | active | The repository exists on GitHub and is not archived. This says nothing about how recently it was worked on. | as of fetch | GitHub | |
| mcp tools declared | 3 tools | Number of functions the server declared when started and asked to list them. It says what the server offers an agent, not how well any of it works. | as of probe | npm |
|
| mcp endpoint status | ok | The server listed 3 functions when asked. | as of probe | npm |
|
| package install scripts | none | This package declares no install-time scripts, so installing it does not execute any of its code. | as of probe | npm |
Where to get it
Related, by what their authors tagged them
-
MINT Protocol — Universal Work Attestation
— last commit 2026-07-19, shares proof-of-work
Trust stack for AI agents: identity, attest, verify, rate, recommend, discover — on Solana.
-
Canvora
— last commit 2026-07-19, shares hermes, openclaw
Turn any idea, URL, doc, or PDF into on-brand visuals: 100+ formats, native in 150+ languages
-
Elasticflow
— last commit 2026-05-01, shares hermes, openclaw
AI-native team workspace — tables, documents, workflow automation, live dashboards & analytics
-
Kenwea Marketplace
— last commit 2026-07-28, shares hermes, openclaw
Agents sell, humans buy. Self-register in one call, publish keyless, get a real sandbox verdict.
-
ClawLink
— last commit 2026-08-06, shares hermes, openclaw
MCP server connecting AI agents to 100+ apps (Gmail, Slack, Notion, GitHub) via one-click OAuth.
-
DocDeploy
— last commit 2026-04-16, shares hermes, openclaw
Document hosting and encrypted agent memory with multi-tenant persistence.
-
Codex Control Plane MCP
— last commit 2026-07-15, shares hermes, openclaw
Durable MCP control plane for long-running Codex Desktop tasks.
-
io.github.davidmosiah/delx-living-body
— last commit 2026-08-06, shares hermes
Meta-MCP that auto-detects installed wellness connectors and composes them into one body data layer.
-
ai.sentvia/mcp
— last commit 2026-07-27, shares email, openclaw
Email for AI agents: inboxes, send/reply/forward, search, threads, webhooks — 21 SentVia tools.
-
io.github.agenticmail/mcp
— last commit 2026-08-06, shares email, openclaw
Real email and SMS for AI agents — send mail, receive verification codes, drive a real inbox.
These share tags the maintainers applied themselves, such as proof-of-work, hermes, openclaw, email. Common tags like "mcp" or "ai" are ignored for this: agreeing with six hundred other projects is not a similarity.
This is not a recommendation and not a test result. It is a map of what the authors said their work is about.
How the author describes it
Topics the maintainer set on GitHub: ai, ai-agents, claude, email, hermes, jmap, openclaw, proof-of-work.
This record as data
Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.
GET /api/v1/entries/mcp_server.json