Bring Chatbot Training
to Google ADK
Learn how to connect Botsonic to Google ADK and start using 12 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the Botsonic MCP Server?
Connect your Botsonic (by Writesonic) account to any AI agent and manage your AI chatbot fleet through natural conversation.
What you can do
- Bot Management — Create, update, list, and inspect AI chatbots with personality, instructions, and knowledge base configuration
- Knowledge Base Training — Add web page URLs to a bot's knowledge base and review all training sources (URLs, documents, files)
- Conversation History — Browse all chat sessions per bot and inspect the full message history of any conversation
- Live Querying — Send messages to a bot and receive AI-generated responses in real time
- Lead Capture — Retrieve all leads collected by the chatbot during customer conversations
- Performance Analytics — Track usage metrics including conversation volume, message count, resolution rate, and customer satisfaction
How it works
1. Subscribe to this server
2. Enter your Botsonic API Token from your Writesonic dashboard
3. Start managing your chatbot fleet from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Customer Support Teams — monitor bot conversations, review resolution rates, and capture leads without switching dashboards
- Product Managers — train bots with new knowledge sources and test responses through conversational AI
- Growth Teams — analyze chatbot engagement metrics and lead capture performance across all bots
Built-in capabilities (12)
Add knowledge URL
Verify connectivity
Create a bot
Get bot details
Get bot analytics
Get conversation
List all bots
List conversations
List knowledge base
List captured leads
Send message to bot
Update a bot
Why Google ADK?
Google ADK natively supports Botsonic as an MCP tool provider. declare Vinkius Edge URL and the framework handles discovery, validation, and execution automatically. Combine 12 tools with Gemini's long-context reasoning for complex multi-tool workflows, with production-ready session management and evaluation built in.
- —
Google ADK natively supports MCP tool servers. declare a tool provider and the framework handles discovery, validation, and execution
- —
Built on Gemini models, ADK provides long-context reasoning ideal for complex multi-tool workflows with Botsonic
- —
Production-ready features like session management, evaluation, and deployment come built-in. not bolted on
- —
Seamless integration with Google Cloud services means you can combine Botsonic tools with BigQuery, Vertex AI, and Cloud Functions
Botsonic in Google ADK
Botsonic and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Botsonic to Google ADK through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 3,400+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Botsonic in Google ADK
The Botsonic MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 12 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Google ADK only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Botsonic for Google ADK
Every tool call from Google ADK to the Botsonic MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I train a bot by adding web pages to its knowledge base?
Yes! The add_knowledge_url action accepts a Bot ID and a URL. Botsonic will crawl the page and add its content to the bot's training data. Use list_knowledge_base to review all sources (URLs, documents, files) currently training a specific bot.
Can I retrieve leads captured by my chatbot during customer interactions?
Yes. The list_leads tool retrieves all leads collected by a specific bot during conversations, including contact details, conversation context, and capture timestamp. This is ideal for syncing chatbot-qualified leads into your CRM.
How can I measure the performance of my chatbots?
Use get_bot_analytics with the Bot ID. It returns conversation count, total messages, resolution rate (percentage of conversations resolved without human handoff), and customer satisfaction scores. Compare across bots to identify which ones need KB improvements.
How does Google ADK connect to MCP servers?
Import the MCP toolset class and pass the server URL. ADK discovers and registers all tools automatically, making them available to your agent's tool-use loop.
Can ADK agents use multiple MCP servers?
Yes. Declare multiple MCP tool providers in your agent configuration. ADK merges all tool schemas and the agent can call tools from any server in a single turn.
Which Gemini models work best with MCP tools?
Gemini 2.0 Flash and Pro models both support function calling required for MCP tools. Flash is recommended for latency-sensitive use cases, Pro for complex reasoning.
McpToolset not found
Update: pip install --upgrade google-adk