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.
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.
โจ Features
- ๐ Identity Passthrough โ Extracts the
Authorization: Bearer <token>header from incoming HTTP requests and forwards it to the Keila API without server-side authentication. - ๐ฅ Multi-Tenancy โ Uses Python
contextvarsto maintain thread-safe user identity isolation, ensuring all AI-driven actions are scoped to the authenticated user's permissions. - ๐ Full Keila Coverage โ 34 tools mapped to Keila REST API endpoints across 6 resource domains.
- โก TOON Optimization โ Bulk list responses are automatically compressed using TOON (Token-Optimized Object Notation) to reduce token consumption and maximize context window efficiency.
- ๐ Efficient Gets โ GET responses return only commonly used fields by
default. Full objects are available via an
include_all_fieldsflag. - ๐งช Comprehensive Testing โ 75 automated tests covering all tool domains, run via the test runner pipeline.
๐ง 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. |
๐ฆ Installation & Local Development
- Ensure you have Python 3.12+ installed.
- Install dependencies:
pip install fastmcp httpx pydantic uvicorn toon-mcp-server - Run the server:
export KEILA_BASE_URL=http://keila-app:4000 export MCP_SERVER_PORT=80 python -m src.main
๐ณ 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).
โ ๏ธ Important Notes
- ๐
include_all_fieldsโ Theinclude_all_fieldsparameter (available on allget_*andlist_*tools) controls whether all available fields are included in responses. Defaults toFalsefor performance; set toTrueonly when additional fields are needed. - ๐
ALLOW_ALL_AGGREGATEโ Controls whether aggregate listing tools respect theinclude_all_fieldsparameter. When set tofalse(default), all aggregate list operations silently return only default fields regardless of the caller's request. - โก TOON Compression โ All bulk list responses are automatically compressed using TOON to reduce token consumption by 30โ60%.
- ๐ Required Fields & Defaults โ Each
create_*tool requires specific key fields. All other fields default to empty strings or reasonable values.
๐ ๏ธ API Tool Mapping
The server implements 34 MCP tools organized into the following categories:
๐ง Campaigns (7 tools)
list_all_campaignsโ List all campaign recordsget_campaign_by_idโ Get a single campaign by IDcreate_campaignโ Create a new campaignupdate_campaignโ Update an existing campaigndelete_campaign_by_idโ Delete a campaign by IDsend_campaignโ Queue a campaign for immediate deliveryschedule_campaignโ Schedule a campaign for future delivery
๐ฏ Segments (5 tools)
list_all_segmentsโ List all segment recordsget_segment_by_idโ Get a single segment by IDcreate_segmentโ Create a new segmentupdate_segmentโ Update an existing segmentdelete_segment_by_idโ Delete a segment by ID
๐ฅ Contacts (7 tools)
list_all_contactsโ List all contact recordsget_contact_by_idโ Get a single contact by ID, email, or external IDcreate_contactโ Create a new contactupdate_contactโ Update an existing contactdelete_contact_by_idโ Delete a contact by ID, email, or external IDupdate_contact_dataโ Shallow-merge custom data fields on a contactreplace_contact_dataโ Replace all custom data fields on a contact
๐ Forms (6 tools)
list_all_formsโ List all form recordsget_form_by_idโ Get a single form by IDcreate_formโ Create a new formupdate_formโ Update an existing formdelete_form_by_idโ Delete a form by IDsubmit_formโ Submit a form to create or update a contact
๐ Templates (5 tools)
list_all_templatesโ List all template recordsget_template_by_idโ Get a single template by IDcreate_templateโ Create a new templateupdate_templateโ Update an existing templatedelete_template_by_idโ Delete a template by ID
๐ ๏ธ Senders, Transactional Messages & System Tools (4 tools)
list_all_sendersโ List all sender recordssend_transactional_messageโ Send a transactional messagerender_transactional_messageโ Render a transactional message without sending itcheck_server_statusโ Check connectivity to the Keila backend
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.