BulkClix MCP Server
Enables AI agents to interact with the BulkClix platform for SMS, OTP, airtime, mobile money, bank transfers, data bundles, KYC, contacts, and account management via natural language.
README
Ananse MCP Server (Python FastMCP)
A Python-based MCP (Model Context Protocol) server that gives AI agents (LibreChat, Claude Desktop, Cursor, etc.) full access to ghanaian platforms via natural language.
Developed with FastMCP for simple tool declarations.
Features
- Food & Catalog Ordering: Search food menus across Accra/Bolt Food catalog, place merchant orders via SMS, collect MoMo payments.
- MongoDB Order Tracking: Save user profiles, delivery addresses, and track live order lifecycle states (
PENDING,CONFIRMED,IN_TRANSIT,DELIVERED). - SMS: Send bulk SMS, fetch campaign reports, request/list Sender IDs.
- OTP: Send and verify OTPs via SMS and Email.
- Airtime: List networks, purchase airtime via momo, and send airtime from wallet balance.
- Mobile Money: MoMo payment collections, status checks, disbursements.
- Bank Transfer: Disburse to bank accounts, list banks.
- Data Bundles: Fetch bundles, purchase data packages.
- KYC: MSISDN owner name lookups.
- Contacts: Full CRUD for contact groups & contacts.
- Account: Check wallet balance.
Installation & Running
Option 1: Docker Compose (Recommended - with MongoDB)
Run the server along with the mini MongoDB instance for tracking orders and storing user profiles:
docker-compose up -d
Option 2: Standalone via uv
Using uv is highly recommended as it automatically manages dependencies:
# Run server using uv
uv run server.py
If you want the server to use a default BulkClix key, set BULKCLIX_API_KEY before starting it:
export BULKCLIX_API_KEY="your-bulkclix-api-key"
uv run server.py mcp
To expose admin-only workflows like contact management, enable internal tools on the server:
export BULKCLIX_ENABLE_INTERNAL_TOOLS=true
The public chat-facing tools now work without caller-supplied keys. SMS and OTP tools automatically pick the first sender ID returned by BulkClix. Airtime and data purchases first collect payment through MoMo, then complete the fulfillment after payment is confirmed.
Configuration in LibreChat
Option 1: stdio transport (default)
Add this under mcpServers in your librechat.yaml:
mcpServers:
ananse:
command: uv
args:
- run
- --directory
- /path/to/ananse-mcp
- server.py
type: stdio
Option 2: HTTP / MCP transport (Remote/Streamable)
Run the server on a port (e.g. port 8000):
cd ananse-mcp
uv run server.py mcp
Then configure LibreChat to use the MCP-over-HTTP endpoint:
mcpServers:
bulkclix:
url: http://localhost:8000/
type: sse
You can then tunnel that port with localtunnel:
npx localtunnel --port 8000
If BULKCLIX_API_KEY is set on the machine running the server, the client can use the public tools without providing any per-call key.
Admin-only tools are hidden unless BULKCLIX_ENABLE_INTERNAL_TOOLS=true is set on the server.
License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (CC BY-NC-ND 4.0). See the LICENSE file for details.
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.