io.github.msanchezgrice/talkform (MCP)

This MCP server provides access to Talkform resources: local Talkform schemas, bundled interview templates, and configuration validation for AI agents. Talkform is described as a config-driven audio intake utility that collects required fields conversationally, binds structured values into forms, and exports JSON-ready session results.

🛠️ Key Features

Local Talkform schemas and bundled interview templates
Config validation for AI agents
Core components for config schema, realtime prompt/tool generation, and session/result helpers

🚀 Use Cases

AI agents that need structured audio interview input
Workflows that require JSON-ready session results
Integration with hosted or embedded Talkform interfaces

⚡ Developer Benefits

Agent-friendly CLI and process-local transient session/HTTP helpers
Embeddable React widget for UI integration
MCP packaging located under packages/mcp for local MCP support

⚠️ Limitations

Documentation excerpt provided focuses on Talkform utilities and package structure; specific MCP tool count and interfaces are not included.

Talkform

Turn any form into a live audio interview.

Talkform is a config-driven audio intake utility. Products define the fields they need, Talkform asks for them conversationally, binds structured values directly into the form, and exports JSON-ready session results.

Workspace

apps/web: hosted app for talkform.ai
packages/core: config schema, realtime prompt/tool generation, session/result helpers
packages/react: embeddable React widget
packages/http: process-local transient session and HTTP helpers
packages/cli: agent-friendly CLI
packages/mcp: local MCP schema, template, and config-validation server
docs: markdown documentation rendered in the web app

Core commands

bash

pnpm install
pnpm dev
pnpm build
pnpm typecheck

Environment

OPENAI_API_KEY
OPENAI_REALTIME_MODEL default gpt-realtime-2.1
OPENAI_REALTIME_VOICE default marin
TALKFORM_ENABLE_IMPORT_AI_REFINEMENT optional; only true enables paid AI copy refinement after deterministic import
NEXT_PUBLIC_AUDIOFORM_VENDOR
NEXT_PUBLIC_AUDIOFORM_VENDOR_URL

Transient session APIs and public Realtime client-secret issuance are disabled in hosted production by default. A production deployment needs a durable session store, a distributed rate limiter, and server authentication before those endpoints should be enabled. The current in-memory store and quotas are development/reference implementations; they do not provide cross-instance durability or enforcement.

Machine clients use two matching environment variables:

TALKFORM_API_TOKEN: server-only bearer token accepted by the web API
AUDIOFORM_API_TOKEN: client-side token read by the Talkform CLI

For a controlled deployment, TALKFORM_ENABLE_IN_MEMORY_SESSIONS=true and TALKFORM_ENABLE_PUBLIC_REALTIME=true opt into the reference endpoints. Do not use these flags to represent the current process-local implementations as production-ready infrastructure.