Nexlink Telecom MCP Server
Enables natural language interaction with telecom network operations data via MCP, providing read-only insights and role-gated write operations such as bandwidth upgrades, with progress tracking and human-in-the-loop elicitation.
README
Nexlink Telecom - MCP Server Lab
A Network Operations Center (NOC) Assistant built for Nexlink Telecom. This project implements the Model Context Protocol (MCP) over a local SQLite database to allow a local LLM to interact safely with telecom database records.
Database Architecture & ERD
The system uses SQLite (db/nexlink.db) with 5 tables: customers, users, network_nodes, services, and audit_logs.
erDiagram
users {
int id PK
string username UK
string role "NOC_Admin | NOC_Engineer | Guest"
string api_token UK
}
customers {
int id PK
string name
string industry
string sla_tier "VIP | Enterprise | Standard"
string contact_email
}
network_nodes {
int id PK
string name
string type "Fiber | 5G Core | Edge Router | Satellite"
float max_capacity_gbps
float current_load_gbps
string status "Healthy | Congested | Down | Maintenance"
string location
}
services {
int id PK
int customer_id FK
int node_id FK
float allocated_bandwidth_gbps
string status "Active | Suspended | Pending"
}
audit_logs {
int id PK
datetime timestamp
int user_id
string action
string details
}
customers ||--o{ services : "subscribes to"
network_nodes ||--o{ services : "hosts"
users ||--o{ audit_logs : "triggers"
Protocol Concerns Implementation
| Protocol Concern | Description | Implementation in server.py |
|---|---|---|
| Capability Negotiation | Handshake check | Server declares capabilities in initialize; client verifies before calling tools. |
| Notifications | Dynamic tool updates | authenticate_user triggers tools/list_changed to unlock write tools. |
| Elicitation | Mid-call human confirmation | upgrade_bandwidth calls ctx.elicit() if upgrade > 3.0 Gbps or customer is VIP. |
| Sampling | Server LLM request | analyze_incident_root_cause sends trace log to client LLM via ctx.session.create_message(). |
| Resources & Prompts | Exposed policies & prompts | Static policies in policies/ and draft_incident_report prompt template. |
| Progress Tracking | Long running task status | run_network_diagnostic calls ctx.report_progress(step, total). |
| Defensive Tool Design | Strict validation | Pydantic models with ge/gt bounds, additionalProperties=False, and role checks. |
| Transport | Dual transport support | Command line option for stdio and Streamable HTTP. |
Comparison Note (Read-Only vs Write Tools)
get_customer_network_status: Read-only tool accessible to all roles.run_network_diagnostic: Read-only tool that emits progress notifications.authenticate_user: State change tool that pushes tools/list_changed notification.upgrade_bandwidth: Write tool requiring NOC_Admin role and mid-call elicitation confirmation for VIP upgrades.analyze_incident_root_cause: Read tool utilizing protocol sampling.
Transport Choice Justification
- stdio: Used for local terminal CLI development for zero-network security.
- Streamable HTTP: Used for remote deployment across regional NOC centers behind API gateways.
How to Run
- Install dependencies:
pip install -r requirements.txt - Initialize database:
python db/setup_db.py - Run test runner:
python demo_runner.py - Run client CLI:
python agent/client.py
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.