The TeleQuick SDK is built to work well with AI coding agents. We ship three things designed specifically for them:
  1. A documentation surface that LLMs can read directly (no HTML scraping).
  2. A native MCP server they can call as a tool.
  3. A CLI (telequick) that scaffolds projects with agent-ready AGENTS.md files baked in.
If you’re using Claude Code, Cursor, Codex CLI, or any other coding agent, point it at the resources below before asking it to write TeleQuick code.

​
MCP server

Available at: 
https://docs.telequick.dev/api/mcp
Streamable HTTP transport (POST JSON-RPC). Three tools:
ToolArgsReturns
list_pages(none)Navigation-grouped slug index of every docs page.
search_docsquery, limit? (≤25)Ranked matches with title, description, and snippet.
get_pageslug (e.g. rpc/method-ids)Full Markdown body of the page.

​
Wiring into Claude Code, Cursor, etc.

{
  "mcpServers": {
    "telequick-docs": {
      "url": "https://docs.telequick.dev/api/mcp"
    }
  }
}
Once configured, your agent will see list_pages, search_docs, and get_page as callable tools alongside its built-in toolbox.

​
Smoke test

curl -X POST https://docs.telequick.dev/api/mcp \
  -H 'content-type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

​
Plain-text documentation

For agents that don’t speak MCP (or for use as a static prompt-context drop-in), every page is also published as plain Markdown:
URLWhat it is
https://docs.telequick.dev/llms.txtShort, navigation-grouped index. Triage starts here.
https://docs.telequick.dev/llms-full.txtEvery page concatenated, page-marked. Whole-corpus context.
https://docs.telequick.dev/<slug>.mdPer-page Markdown mirror (e.g. /rpc/method-ids.md).
https://docs.telequick.dev/search-index.jsonSearchable JSON corpus (powers the MCP search_docs tool).
The format follows the llms.txt convention — drop the URL into any LLM’s context window and it knows what to do with it.

​
CLI: clutch

The clutch CLI does what the MCP server does, plus runs telephony operations against the live BFF after clutch auth login. Docs (no auth): 
clutch docs overview                          # navigation index
clutch docs search "originate trunk"          # full-text search
clutch docs get-page rpc/method-ids           # one page as Markdown
Auth: 
clutch auth login                             # browser OAuth → portal
clutch auth whoami                            # current identity + active org
Trunks + calls (after auth): 
clutch trunks list                            # tabular view
clutch trunks show <id>                       # one trunk in detail
clutch dial +15551234567 --trunk <your-trunk-id> \
    --app AI_BIDIRECTIONAL_STREAM --app-args my-agent-id
clutch dial --list-apps                       # all 13 DialplanAction values
clutch hangup <call_sid>
clutch dial defaults --app to AI_BIDIRECTIONAL_STREAM (=6). If you don’t pass --app-args <agent_id> the runtime has no agent to bridge and the call lands in silence. For raw audio piping without an AI agent, use --app ANSWER (=5).
Mid-call control verbs (each calls ExecuteDialplan server-side): 
clutch transfer <call_sid> +15551234567       # RFC 3515 SIP REFER
clutch mute     <call_sid>                    # gateway-side TX silence
clutch mute     <call_sid> --wire             # also send recvonly re-INVITE
clutch unmute   <call_sid>
clutch hold     <call_sid>
clutch unhold   <call_sid>
clutch send-dtmf <call_sid> 5 --mode rfc2833 --duration-ms 200
Override targets via env: CLUTCH_BASE_URL (portal), CLUTCH_DOCS_BASE (docs site).

​
Scaffolding agent-ready projects

telequick init <lang> <name> drops a working starter into your working directory: 
telequick init go      my-voice-agent
telequick init python  my-py-agent
telequick init typescript browser-demo
Each starter includes:
  • A working dial / event-handling sample (main.telequick / main.py / src/index.ts) that compiles against the TeleQuick SDK.
  • An AGENTS.md file tuned for that language. This is the file that agents read first when they enter the project — it captures the language-specific traps an agent will otherwise re-discover the hard way (e.g. “Emscripten corrupts byte arrays passed as std::string; use typed_memory_view instead”).
  • A .telequick.json project manifest with a pinned schema version for telequick migrate.

​
Best practices for AI-assisted development

These mirror what works for any rapidly-evolving SDK; we mention them because the TeleQuick wire format and method-ID table change between minor releases.
  1. Browse before searching. Have your agent fetch /llms.txt first so it knows what exists. Search excerpts are noisier than full pages.
  2. Fetch full pages, not excerpts. Use get_page (MCP) or get-page (CLI) when you need authoritative answers. The grouped index is for navigation; the page itself is for code.
  3. Never hand-edit serde structs. The Python, TypeScript, Go, Rust, Java, and .NET bindings are auto-generated by telequick/tools/apirpc_compiler/generate_bridges.py. If your agent wants to add an RPC field, it should update the upstream schema and regenerate, not patch the binding by hand.
  4. Run telequick migrate after bumping the SDK. Surfaces schema drift before runtime does.

​
Agent Skills

The TeleQuick Agent Skills repository ships Anthropic-format Skills — opinionated, end-to-end recipes that load into your coding agent’s context when intent matches. Drop the repo into .claude/skills/ (Claude Code) or .cursor/skills/ (Cursor) and the agent gains task-specific knowledge for these workflows: Generic recipes
  • telequick-pstn-dial — outbound PSTN dialing (auth, originate, audio frames, hangup).
  • telequick-ai-bridge — wire a live call to OpenAI Realtime / Anthropic / Gemini Live with barge-in.
  • telequick-call-events — CallEvent stream consumption, reconnection, Q.850 cause handling.
  • telequick-inbound-routing — SetInboundRouting → AnswerIncomingCall, IVR menus, queueing.
  • telequick-sip-trunk — register a carrier (Twilio, Telnyx, Bandwidth, Plivo), caller-ID rules, codecs.
  • telequick-bulk-campaign — OriginateBulk with CSV input, pacing, abort + resume.
  • telequick-recording — per-call recording, stereo, retrieval, transcription.
  • telequick-tool-calling — LLM tool / function calling: the built-in implicit telephony toolset (transfer / hold / DTMF / disconnect / supervisor), custom server-side tools, and client-side tool calls via OpenAI Realtime.
  • telequick-rag-integration — pgvector / Pinecone / Weaviate retrieval as a tool call with latency budgets and barge-in safety.
  • telequick-crm-enrichment — pre-call enrichment (Salesforce / HubSpot lookup → system prompt overrides) vs. in-call tool lookup.
Vendor bridges
  • telequick-vendor-browser-webrtc — capture mic in the browser, send PCMU over WebTransport.
  • telequick-vendor-livekit — bridge PSTN into a LiveKit room.
  • telequick-vendor-daily — bridge PSTN into a Daily room (Pipecat-friendly).
  • telequick-vendor-chime — Amazon Chime SDK Meetings or Voice Connector.
  • telequick-vendor-twilio — bridge from existing Twilio Media Streams (TwiML <Stream>) into TeleQuick.
  • telequick-vendor-vapi — bridge a Vapi.ai voice agent over Vapi’s WebSocket transport.
Each skill is self-contained: prereqs checklist, working Python/TypeScript code, “verify it works” snippet, common gotchas, and pointers back to the docs MCP for deeper reference.