Keila MCP Server

Keila MCP Server

Secure multi-tenant proxy exposing 34 MCP tools to manage Keila contacts, campaigns, forms, segments, templates, and transactional messaging through the Keila REST API.

Category
Visit Server

README

Keila MCP Server

This repository contains a Model Context Protocol (MCP) server that acts as a secure, multi-tenant proxy between an AI Assistant and the Keila backend API. It exposes 34 MCP tools covering 6 resource domains with full CRUD, transactional messaging, and system operations.

โœจ Features

  • ๐Ÿ”‘ Identity Passthrough โ€” Extracts the Authorization: Bearer <token> header from incoming HTTP requests and forwards it to the Keila API without server-side authentication.
  • ๐Ÿ‘ฅ Multi-Tenancy โ€” Uses Python contextvars to maintain thread-safe user identity isolation, ensuring all AI-driven actions are scoped to the authenticated user's permissions.
  • ๐Ÿ“Š Full Keila Coverage โ€” 34 tools mapped to Keila REST API endpoints across 6 resource domains.
  • โšก TOON Optimization โ€” Bulk list responses are automatically compressed using TOON (Token-Optimized Object Notation) to reduce token consumption and maximize context window efficiency.
  • ๐Ÿš€ Efficient Gets โ€” GET responses return only commonly used fields by default. Full objects are available via an include_all_fields flag.
  • ๐Ÿงช Comprehensive Testing โ€” 75 automated tests covering all tool domains, run via the test runner pipeline.

๐Ÿ”ง Environment Variables

Variable Required Description
KEILA_BASE_URL Yes Docker-internal URL of the Keila API (e.g. http://keila-app:4000).
MCP_SERVER_PORT Yes Port number the MCP server listens on
ALLOW_ALL_AGGREGATE No When true, aggregate listing tools honor the include_all_fields parameter. When false (default), the parameter is silently forced to False for aggregate list operations.
IS_STATEFUL No When true, uses stateful Streamable HTTP with session tracking. When false (default), uses stateless mode.

๐Ÿ“ฆ Installation & Local Development

  1. Ensure you have Python 3.12+ installed.
  2. Install dependencies:
    pip install fastmcp httpx pydantic uvicorn toon-mcp-server
    
  3. Run the server:
    export KEILA_BASE_URL=http://keila-app:4000
    export MCP_SERVER_PORT=80
    python -m src.main
    

๐Ÿณ Docker Deployment

Build and run the server using Docker:

docker build -t keila-mcp:latest .
docker run -d --name keila-mcp \
    -e KEILA_BASE_URL="http://keila-app:4000" \
    -e MCP_SERVER_PORT=80 \
    -e ALLOW_ALL_AGGREGATE=false \
    keila-mcp:latest

The MCP server serves at http://keila-mcp:80/mcp (Streamable HTTP).

โš ๏ธ Important Notes

  • ๐Ÿ“‹ include_all_fields โ€” The include_all_fields parameter (available on all get_* and list_* tools) controls whether all available fields are included in responses. Defaults to False for performance; set to True only when additional fields are needed.
  • ๐Ÿ”’ ALLOW_ALL_AGGREGATE โ€” Controls whether aggregate listing tools respect the include_all_fields parameter. When set to false (default), all aggregate list operations silently return only default fields regardless of the caller's request.
  • โšก TOON Compression โ€” All bulk list responses are automatically compressed using TOON to reduce token consumption by 30โ€“60%.
  • ๐Ÿ“ Required Fields & Defaults โ€” Each create_* tool requires specific key fields. All other fields default to empty strings or reasonable values.

๐Ÿ› ๏ธ API Tool Mapping

The server implements 34 MCP tools organized into the following categories:

๐Ÿ“ง Campaigns (7 tools)

  • list_all_campaigns โ€” List all campaign records
  • get_campaign_by_id โ€” Get a single campaign by ID
  • create_campaign โ€” Create a new campaign
  • update_campaign โ€” Update an existing campaign
  • delete_campaign_by_id โ€” Delete a campaign by ID
  • send_campaign โ€” Queue a campaign for immediate delivery
  • schedule_campaign โ€” Schedule a campaign for future delivery

๐ŸŽฏ Segments (5 tools)

  • list_all_segments โ€” List all segment records
  • get_segment_by_id โ€” Get a single segment by ID
  • create_segment โ€” Create a new segment
  • update_segment โ€” Update an existing segment
  • delete_segment_by_id โ€” Delete a segment by ID

๐Ÿ‘ฅ Contacts (7 tools)

  • list_all_contacts โ€” List all contact records
  • get_contact_by_id โ€” Get a single contact by ID, email, or external ID
  • create_contact โ€” Create a new contact
  • update_contact โ€” Update an existing contact
  • delete_contact_by_id โ€” Delete a contact by ID, email, or external ID
  • update_contact_data โ€” Shallow-merge custom data fields on a contact
  • replace_contact_data โ€” Replace all custom data fields on a contact

๐Ÿ“ Forms (6 tools)

  • list_all_forms โ€” List all form records
  • get_form_by_id โ€” Get a single form by ID
  • create_form โ€” Create a new form
  • update_form โ€” Update an existing form
  • delete_form_by_id โ€” Delete a form by ID
  • submit_form โ€” Submit a form to create or update a contact

๐Ÿ“„ Templates (5 tools)

  • list_all_templates โ€” List all template records
  • get_template_by_id โ€” Get a single template by ID
  • create_template โ€” Create a new template
  • update_template โ€” Update an existing template
  • delete_template_by_id โ€” Delete a template by ID

๐Ÿ› ๏ธ Senders, Transactional Messages & System Tools (4 tools)

  • list_all_senders โ€” List all sender records
  • send_transactional_message โ€” Send a transactional message
  • render_transactional_message โ€” Render a transactional message without sending it
  • check_server_status โ€” Check connectivity to the Keila backend

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured