
Connect DocsBot to ChatGPT, Claude and Gemini
Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Control and query your custom AI bots through natural conversation.
Developed, maintained, and hosted by Vinkius.
MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED
Waiting for input…
Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.
Your AI does the work. We keep it safe and sound.
No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.
Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

Each Connector runs inside its own sealed environment.
Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.
One switch stops every agent. Instantly.
One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.
Spending limits that pause instead of surprise.
Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.
Three controls, built into the layer your AI connects through.
Curated set · 10 capabilities
We ship only the actions that matter.
01-04
4 capabilities in this set.
Part of 10 available through DocsBot.
- 01
Ask bot question
Ask a specific DocsBot a technical question to get an AI-generated answer. Your agent uses this to pull information directly from your trained knowledge base.
- 02
Get docsbot account metadata
Retrieve metadata for your authenticated DocsBot account. This helps your agent understand your current account context.
- 03
List bot knowledge sources
List all the URLs, PDFs, and documents used to train a specific bot. Use this to verify what information your bot actually knows.
- 04
Get bot details
Get the specific settings and configuration details for a single bot. This provides your agent with the technical parameters of a bot's setup.
05-07
3 capabilities in this set.
Part of 10 available through DocsBot.
- 05
List bot interaction logs
Access a list of recent questions and answers from a specific bot. This is useful for auditing bot performance and user queries.
- 06
Get bot knowledge summary
Get a high-level overview of a bot's knowledge base, including total source count and size. This helps your agent gauge the scale of a bot's data.
- 07
List recently indexed bots
Identify which bots have had their knowledge bases updated recently. Use this to track the freshness of your bot's information.
08-10
3 capabilities in this set.
Part of 10 available through DocsBot.
- 08
Search bot sources
Search through your bot's knowledge sources using a keyword. This lets your agent find specific documents or URLs within a bot's training set.
- 09
List docsbot teams
List all the teams you belong to within DocsBot. This helps your agent navigate different organizational structures.
- 10
List team bots
Retrieve a list of all AI bots configured within a specific team. This allows your agent to see what capabilities are available in your workspace.
Real work
What teams actually run
Customer Support Troubleshooting
A support agent asks their bot for a specific technical fix and gets the answer immediately within their chat window.
Knowledge Base Auditing
A manager asks the agent to list all sources for a bot to ensure a new PDF was correctly uploaded.
User Intent Analysis
A product owner asks the agent to show recent questions to identify what features users are struggling with.
Bot Configuration Checks
A developer uses the agent to verify the settings of a specific bot before deploying a new update.
Automate a task
Put DocsBot to work on one thing.
Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.
One connector, every AI
DocsBot works with the most popular AI clients.
These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.
Claude
ChatGPT
Gemini
Perplexity
Grok
Microsoft Copilot
Cursor
VS Code
Windsurf
JetBrains
Cline
LangChain
Vercel AI SDK
Lovable
Z.ai
Raycast
Qwen Code
Kimi Code
Le ChatBuilding your own app? The connector is yours to use.
You don't need a client to put DocsBot to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.
Observed, not estimated
1274ms average. Fast in production.
DocsBot is checked daily against the live service.
- Fastest day
- 1274ms
- Slowest day
- 1274ms
- 14-day trend
- Stable0%
Connect your client
One URL. Every client.
Activate the Connector, copy your link, and paste it into the client you already use. 10 capabilities arrive ready to run.
Preview access · not provider authentication
The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of DocsBot, so you can see the experience inside your AI.
It does not authenticate your account with DocsBot. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.
DocsBot Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_DUvS3dfoYdN9s8Yd26fUzX2DZZJItzvIEMs195YL/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — DocsBot capabilities are ready to use.
{
"mcpServers": {
"docsbot-mcp": {
"url": "https://edge.vinkius.com/vk_preview_DUvS3dfoYdN9s8Yd26fUzX2DZZJItzvIEMs195YL/mcp"
}
}
}
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Step-by-step instructions for each client are in the guide. How to connect
Guided setup for Claude? Set up DocsBot in Claude and other AIs
Who it's for
Built for the work DocsBot owners hand off.
This MCP is built for professionals who manage or rely on custom AI chatbots for documentation and support.
- 01
Support Teams
They use the agent to quickly pull answers from documentation bots to resolve customer issues.
- 02
Knowledge Managers
They hand off the task of monitoring source coverage and indexing status to their agent.
- 03
Product Teams
They use the agent to audit interaction logs and find gaps in their product documentation.
FAQ
Questions DocsBot owners ask.
- 01
How do I connect DocsBot to my AI client?
You connect the DocsBot MCP through the Vinkius platform. Once connected, you just need to provide your DocsBot API key to authorize your agent.
- 02
Can I ask my bots questions directly through my agent?
Yes. You can use the ask_bot_question capability to send technical questions to any of your DocsBots and receive answers based on their knowledge base.
- 03
Can I see what documents my bot is using?
Yes. You can use the list_bot_knowledge_sources capability to see every URL, PDF, and document that has been used to train a specific bot.
- 04
Is it possible to audit recent bot conversations?
Yes. The list_bot_interaction_logs capability allows your agent to retrieve recent questions and answers handled by your bots.
- 05
Do I need to manage my own hosting for this MCP?
No. Vinkius hosts and manages the MCP for you, so it is ready to use as soon as you connect your client.
- 06
How do I get a DocsBot API Key?
Log in to your DocsBot account, navigate to the API section in your account settings, and you can generate or retrieve your unique API Key from there.
- 07
Can the agent train my bots?
This integration currently focuses on querying bots and auditing sources. Adding new sources or triggering full training cycles should be managed via the DocsBot dashboard.
- 08
Which AI models are used?
DocsBot supports various models including GPT-3.5 and GPT-4. The agent will retrieve results based on the specific model configured for your bot in your account.
Explore
More in Customer Support
Cody AI AI Connector
Enable your AI agent to manage knowledge-base bots, import documents, and query trained AI assistants via the
ViewDocument360 AI Connector
Manage knowledge bases via Document360 — list project versions, handle categories and articles, search content
ViewElastic Enterprise Search AI Connector
Manage enterprise search via Elastic — search engines and documents, handle indexing, and monitor search analy
ViewLucidworks Fusion (AI Search & Discovery) AI Connector
Manage AI-powered search via Lucidworks Fusion — execute semantic queries, index documents, and monitor ML tra
View
Suggestions
Typesense Vector Search AI Connector
Automate vector similarity searches via Typesense — index documents, manage collections, and execute semantic
ViewGitScrum Knowledge AI Connector
Build and query knowledge bases via GitScrum — manage notes as agent memory, maintain wiki pages, communicate
ViewMem AI (Knowledge Workspace) AI Connector
Manage your knowledge base via Mem.ai — create notes, run AI semantic search, and organize collections.
ViewAddSearch AI Connector
Equip your AI agent with AddSearch to query your indexed site content, push new documents, and retrieve search
View
Connect DocsBot to Claude, Cursor, ChatGPT & more
