Skip to content
MailMolt logo

MailMolt MCP server

Which MCP servers are MailMolt's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-10

← Back to MailMolt

Whose server it is
  • Addresshttps://mcp.mailmolt.com/mcpnot in the official registry: answered when asked

No entry in the official MCP registry names this server. It answered on mailmolt.com when the Atlas asked at the address servers are usually mounted on, so it is the vendor's own. Clients and catalogues that list servers from the registry do not show it.

When we asked itchecked 2026-10-28
  • Stateanswerschecked 2026-10-28
  • Tools13
  • Server calls itselfmailmolt
  • Server version0.1.0
  • Protocol version2024-11-05

On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 58 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.

Once connected

  • send_message, memory_delete change data without a sign-in: anyone with the address can call them.
  • Parameters are untyped or undescribed in 9 of 13 tools: check arguments before calling.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 7, the first on 2026-10-28
  • INITE MCP score73 of 100answers 100 · definitions 72 · context 100 · connects 100 · lowered by the warning signs below
  • Answered100% of days7 of 7 daily checks
  • Median first answer78 ms
  • Space in an agent's context≈ 1,224 tokensthe definitions of all its tools (13), which an agent carries on every turn
  • Tool definitionsC · 72 of 100
  • Typed results0 of 13 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 9 of 13
  • Not saying whether it only reads or can destroy: 13 of 13

What an agent can do with it

  • not sure · Send emails from AI agents with approval workflows
  • not sure · Route inbound emails to agents with threading and search
  • not sure · Monitor agent sending reputation and compliance audits

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

  • Tools that change data, on a server that answers without a sign-in: send_message, memory_delete

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers13 tools · read 2026-10-28
  • send_message

    Send an email from the authenticated MailMolt agent. Body may be text, html, or both. Attachments optional (base64).

  • reply_message

    Reply to an existing message by its internal message id. Threading headers are generated automatically.

  • list_threads

    List recent email threads. Returns the most-recent-first page.

  • get_thread

    Fetch a thread with all its messages.

  • search_messages

    Semantic search across the authenticated agent's inbox. Uses Vectorize embeddings.

  • get_inbox_stats

    Summary counts for the agent inbox.

  • get_profile

    Profile + identity of the authenticated MailMolt agent.

  • get_billing

    Current plan, subscription state, and 24h usage for the agent's owner.

  • memory_list

    List the agent's persisted memory entries (goals, learnings, notes). Bound to the authenticated agent.

  • memory_get

    Read a single memory entry by key.

  • memory_put

    Create or replace a memory entry. Use short, lowercase keys (e.g. "current-goal", "user-preferences"). Value is plaintext UTF-8, max 32 KB.

  • memory_delete

    Delete a memory entry by key.

  • memory_search

    Semantic recall over memory entries. Returns ranked matches via Vectorize embeddings.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "mailmolt": {
      "type": "http",
      "url": "https://mcp.mailmolt.com/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http mailmolt https://mcp.mailmolt.com/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://mcp.mailmolt.com/mcp as a custom connector in the settings.

OpenAPI spec

30 paths, read 2026-10-10. Open the spec ↗

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.