This server provides a FastMCP interface to the Jelly team inbox API, enabling management of conversations, messages, labels, contacts, drafts, autoresponder, and comments.
Conversations: List, search, get (with comments & timeline), archive/unarchive, trash/restore, spam/unspam, snooze/unsnooze, ignore, set mailboxes, assign/unassign, add/remove labels.
Messages & Drafts: List messages, get message, create new draft conversation/draft reply, update draft, resolve attachment URLs.
Comments: List internal comments, add comment.
Labels: List, create (with optional color), update (rename/recolor), delete.
Members & Mailboxes: List active team members, list mailboxes and their members.
Contacts: Find by email, upsert (create/update).
Team Settings: Get/update autoresponder, list saved replies.
Resources: Access a markdown-rendered conversation view via jelly://conversations/{id}/markdown.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Jelly-FastMCP List all conversations in the Support mailbox"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A FastMCP-based Model Context Protocol (MCP) server for the Jelly API. It exposes the API as MCP tools for creating, reading, updating, and managing conversations, labels, contacts, drafts, autoresponder settings, comments, and more.
Python 3.12+
uv (recommended)
Related MCP server: FastMail MCP Server
Configure the following environment variables to authenticate and set defaults:
Environment Variable | Description |
| Jelly API token from Settings → API Tokens |
| Optional override for the API base URL. Defaults to |
uv run server.pyuv pip install -e .This registers the jelly-mcp command.
To use this with Claude Desktop (or other MCP hosts), add the following configuration.
Using sh -c allows the use of $HOME (or other environment variables) dynamically across different user machines/setups, since most MCP hosts do not perform shell expansion on paths:
{
"mcpServers": {
"LetsJelly": {
"command": "sh",
"args": [
"-c",
"uv --directory \"$HOME/.agents/Jelly-FastMCP\" run server.py"
],
"env": {
"JELLY_API_TOKEN": "your-api-token-here"
}
}
}
}Note: If you prefer not to use sh -c, replace "command" with "uv" and use the absolute path in the "--directory" argument.
list_conversations
search_conversations
get_conversation
list_conversation_messages
list_conversation_comments
add_comment
archive_conversation / unarchive_conversation
trash_conversation / restore_conversation_from_trash
spam_conversation / unspam_conversation
snooze_conversation / unsnooze_conversation
ignore_conversation
set_conversation_mailboxes
assign_conversation / unassign_conversation
add_conversation_label / remove_conversation_label
get_message
create_draft_conversation
create_draft_reply
update_draft
resolve_attachment_download_url
list_labels
create_label
update_label
delete_label
list_members
list_mailboxes
list_mailbox_members
find_contact_by_email
upsert_contact
get_autoresponder
update_autoresponder
list_saved_replies
jelly://conversations/{conversation_id}/markdown — LLM-friendly markdown view of a conversation
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
MCP server for generating rough-draft project plans from natural-language prompts.
MCP server for Nylas — read email, calendars, events and contacts, and send email or create events.
An MCP server that provides an API to LLMs to manage their JumpCloud resources.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/js-cohn/Jelly-FastMCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
