cx-agent
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
cx-agent-mcp
A small MCP server for a telecom support assistant. The assistant can look up customers, check balance and orders, suspend a lost SIM and open tickets, all through a REST backend. It also has a tool that reads a SIP trace and tells you why a call failed.
I spent a few years in VoIP support before moving to backend work, and most "the bot is broken" tickets I saw were really telephony or integration problems. So this project focuses on those two parts: calling backend APIs safely, and reading SIP traces.
What's inside
backend/api.py mock telecom backend (FastAPI)
mcp_server/api_client.py HTTP client: auth, timeouts, retries, idempotency keys
mcp_server/server.py MCP tools, one resource, one prompt
mcp_server/sip_analyzer.py SIP trace parser and rules
agent/chat.py terminal chat client (Claude + the MCP server over stdio)
samples/trace_488.txt example failed call
tests/ pytestRelated MCP server: Nexlink Telecom MCP Server
Tools
Tool | Kind | Notes |
| read | accepts |
| read | balance, data left, line status |
| read | validates the order id before calling the API |
| write | refuses unless |
| write | handover note for the human agent; idempotent |
| local | ladder, codecs, media IPs, likely cause |
Resource: policy://escalation. Prompt: support_agent.
How API calls are handled
API key header on every request
3s timeout (configurable). A support bot can't keep a customer waiting
Retries with backoff only on 429/502/503/504 and network errors
4xx errors are never retried
Writes are retried only when they carry an
Idempotency-Key, so a retry can't suspend a line twice or open two ticketsTools never raise. On failure they return
ok: false, a sentence the bot can say, and a next step (offer_human_agentorask_customer_to_check_input)
You can see this working by starting the backend with BACKEND_FAIL_RATE=0.3. About a third of the calls return 503 and the tools still answer.
SIP analyzer
Paste a text trace from an SBC, sngrep or Wireshark. It builds the ladder and checks for:
4xx/5xx final responses with what to look at (488 codec/SRTP mismatch, 403, 404 number format, 503...)
200 OK with no ACK (the call that drops after ~30 seconds)
private IPs in the SDP
c=line (one way audio behind NAT)only compressed codecs offered (bad for speech recognition)
no
telephone-event(DTMF won't reach the bot)more than one Call-ID (B2BUA legs)
Running it
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install -r requirements.txt
# terminal 1
uvicorn backend.api:app --port 8000 # swagger at http://127.0.0.1:8000/docs
# terminal 2, pick one
npx @modelcontextprotocol/inspector python -m mcp_server.server
python -m agent.chat # needs ANTHROPIC_API_KEYSettings are read from environment variables, see .env.example.
Claude Desktop
{
"mcpServers": {
"cx-agent": {
"command": "C:\\path\\to\\cx-agent-mcp\\.venv\\Scripts\\python.exe",
"args": ["-m", "mcp_server.server"],
"env": {
"PYTHONPATH": "C:\\path\\to\\cx-agent-mcp",
"BACKEND_URL": "http://127.0.0.1:8000",
"BACKEND_API_KEY": "dev-secret-key"
}
}
}
}Things to try:
"my number is 01001234567, how much balance do I have?"
"where is ORD-5001?"
"I lost my phone, stop my line"
paste
samples/trace_488.txtand ask why the call failed
Tests
pytest -qThe tool tests route httpx straight into the FastAPI app, so no server has to be running.
Next
streamable HTTP transport
OAuth2 client credentials instead of a static key
FAQ search tool
Arabic replies
Genesys Cloud data action pointing at the backend
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Manage tickets, run agents and workflows, query tables, and search workspace knowledge.
SIP/VoIP/telecom grounding for AI agents: vendor docs, RFCs, STIR/SHAKEN, traces, configs.
Manage your Telvana AI voice, SMS and chat agents, conversations, campaigns and outbound calls.
Place calls, send WhatsApp, manage contacts, leads and campaigns, and read call records and billing
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to access curated SIP/VoIP documentation, troubleshoot traces, and analyze telecom configurations with 20+ read-only tools.MIT
- FlicenseNot gradedqualityDmaintenanceEnables 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.-
- FlicenseNot gradedqualityBmaintenanceLets hosted assistants like Claude, ChatGPT or Gemini drive a full telecom sales journey through natural-language tool calls — searching mobile, fixed and TV tariffs and devices, building and updating a cart, tokenising card payment, collecting mandatory consents, and completing an order — with server-side guard rails, rendered UI widgets and catalogue data that is edited as markdown rather than code.-
- FlicenseNot gradedqualityAmaintenanceEnables operators to retrieve and manage tickets and comments, analyze tickets and draft responses via specialized prompts, and access Help Center articles as a knowledge base.-