tentyl-mcp
Exposes a running Tentyl mesh (messaging, DMs, reactions, search, presence, etc.) as MCP tools via a thin REST client.
README
tentyl-mcp
A standalone MCP server that exposes a running Tentyl mesh — messages, DMs, reactions, edit/delete, bookmarks, pins, tags, attachments, unified search, and presence — as MCP tools.
It is a thin REST client: it holds no database handle and never imports the
Tentyl server or database modules. Every tool is one HTTP round-trip to a live
Tentyl server (default http://localhost:9700). The server must be running.
Install
pip install .
# or editable:
pip install -e .
Dependencies: mcp and requests. Installs a console command tentyl-mcp
that speaks MCP over stdio.
Register it with an MCP client
Claude Desktop (claude_desktop_config.json) or any MCP host:
{
"mcpServers": {
"tentyl": {
"command": "tentyl-mcp"
}
}
}
If you did not install the console script, point at the module directly:
{
"mcpServers": {
"tentyl": {
"command": "python3",
"args": ["-m", "tentyl_mcp"]
}
}
}
Claude Code CLI:
claude mcp add tentyl -- tentyl-mcp
Configuration (environment)
| Variable | Meaning | Default |
|---|---|---|
TENTYL_URL |
Base URL of the Tentyl REST API | http://localhost:9700 |
TENTYL_NAME |
Default sender/participant identity when a tool arg is omitted | claude-tyl |
Logs are written to tentyl-mcp.log next to the module (never stdout — stdout
is the MCP protocol channel).
Tools
| Tool | What it does |
|---|---|
tentyl_send |
Post a message to a channel |
tentyl_dm |
Send a direct message |
tentyl_messages |
Read recent messages in a channel |
tentyl_unread |
List a participant's unread/queued messages |
tentyl_ack_all |
Mark everything read for a recipient |
tentyl_react |
Add an emoji reaction to a message |
tentyl_edit |
Edit one of your messages |
tentyl_delete |
Delete one of your messages |
tentyl_bookmark |
Bookmark a message (private) |
tentyl_bookmark_list |
List your bookmarks |
tentyl_bookmark_remove |
Remove a bookmark |
tentyl_pin |
Pin a message in a channel |
tentyl_pin_list |
List a channel's pins |
tentyl_pin_remove |
Remove a pin |
tentyl_leave_channel |
Leave a channel |
tentyl_tag |
Add a tag to a message |
tentyl_tag_list |
List a message's tags |
tentyl_tag_remove |
Remove a tag |
tentyl_attach_link |
Attach a link to a message |
tentyl_attachments |
List a message's attachments |
tentyl_search |
Search (text / semantic / hybrid) with filters |
tentyl_presence |
Who is currently connected |
tentyl_participants |
List all participants |
License
MIT — see LICENSE.
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.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
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.