How do I connect my Chaindesk account?

You need to grab your API Key from the Settings section of your Chaindesk dashboard. Once you have that, you can connect this MCP to your AI client.

Which AI clients can I use with this MCP?

You can use this with any MCP-compatible client, including Claude, Cursor, and Windsurf.

Can I update my agent's knowledge through the chat?

Yes. You can use the upsert_datasource capability to add or update data sources like URLs or documents directly through your agent.

Do I need to write code to manage my agents?

No. While this is useful for developers, the MCP is designed so you can manage agents and datastores using natural language commands.

Can I see what my agents have been saying to users?

Yes. You can use the get_messages capability to retrieve specific message threads and conversation histories.

How do I find my Chaindesk API Key?

Log in to your Chaindesk.ai account, navigate to Settings > API Keys, and generate a new key for your integration.

A Datastore is a collection of documents and URLs that your AI agent uses as its knowledge base to answer queries accurately.

Can I maintain conversation context via AI?

Yes! Provide a unique conversationId to the query_agent capability to maintain historical context across multiple turns with your custom bot.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Chaindesk 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. Manage custom AI agents and knowledge bases through natural conversation.

Ask AI about this Connector

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.

V8 Isolate01

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.

Kill Switch02

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.

FinOps per User03

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 · 11 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 11 available through Chaindesk.

01
Create agent
Create a new AI agent by specifying its name, datastore ID, and system prompt.
02
List agents
View all the AI agents you have created.
03
List conversations
Retrieve a list of chat conversations, which can be filtered by a specific agent ID.
04
Get messages
Pull the message history from a specific conversation thread.

Capability set02 / 03

05-08

4 capabilities in this set.

Part of 11 available through Chaindesk.

05
List datastores
Get a full list of all available knowledge datastores.
06
Query agent
Send a message to a specific agent to get a response based on its training data.
07
Update agent
Modify the settings or prompts of an existing agent.
08
Upsert datasource
Add new data or update existing sources within a datastore.

Capability set03 / 03

09-11

3 capabilities in this set.

Part of 11 available through Chaindesk.

09
Delete agent
Remove an agent from your Chaindesk account.
10
Get agent
Retrieve the configuration and details of a specific agent.
11
Get datastore
Fetch the details and status of a specific knowledge datastore.

Real work

What teams actually run

Automated Knowledge Updates

You can tell your agent to ingest a new URL so your support bots stay current with your latest documentation.

Agent Deployment

You can programmatically spin up new specialized agents with specific system prompts for different tasks.

Support Auditing

You can pull conversation histories to review how your agents are handling customer queries.

Internal Capability Integration

You can use your agent to query custom-trained models to provide context for other internal workflows.

Automate a task

Put Chaindesk 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

Chaindesk 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.

Building your own app? The connector is yours to use.

You don't need a client to put Chaindesk 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

942ms average. Fast in production.

Chaindesk is checked daily against the live service.

Daily averagePeak 1539ms

Oct 5Today

Fastest day: 751ms
Slowest day: 1539ms
14-day trend: Slowing+43%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 11 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 Chaindesk, so you can see the experience inside your AI.

It does not authenticate your account with Chaindesk. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Chaindesk Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_T5VjYPY8ezoZU63DLLaawQj8Wz1PrnywxCHz077q/mcp

Claude 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 — Chaindesk capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "chaindesk-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_T5VjYPY8ezoZU63DLLaawQj8Wz1PrnywxCHz077q/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 Chaindesk in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Chaindesk owners hand off.

This MCP is built for technical teams who need to manage custom AI knowledge and agents without manual data entry.

01
Developers and Ops
They use it to automate document ingestion and integrate custom models into internal capabilities.
02
Support Teams
They use it to monitor agent responses and update knowledge bases in real time.
03
Product Leads
They use it to deploy specialized assistants for different business units via simple queries.

FAQ

Questions Chaindesk owners ask.

01
How do I connect my Chaindesk account?
You need to grab your API Key from the Settings section of your Chaindesk dashboard. Once you have that, you can connect this MCP to your AI client.
02
Which AI clients can I use with this MCP?
You can use this with any MCP-compatible client, including Claude, Cursor, and Windsurf.
03
Can I update my agent's knowledge through the chat?
Yes. You can use the upsert_datasource capability to add or update data sources like URLs or documents directly through your agent.
04
Do I need to write code to manage my agents?
No. While this is useful for developers, the MCP is designed so you can manage agents and datastores using natural language commands.
05
Can I see what my agents have been saying to users?
Yes. You can use the get_messages capability to retrieve specific message threads and conversation histories.
06
How do I find my Chaindesk API Key?
Log in to your Chaindesk.ai account, navigate to Settings > API Keys, and generate a new key for your integration.
07
What is a Datastore?
A Datastore is a collection of documents and URLs that your AI agent uses as its knowledge base to answer queries accurately.
08
Can I maintain conversation context via AI?
Yes! Provide a unique conversationId to the query_agent capability to maintain historical context across multiple turns with your custom bot.

Explore

More in Knowledge Management

Connect Chaindesk to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

Create agent

List agents

List conversations

Get messages

05-08

List datastores

Query agent

Update agent

Upsert datasource

09-11

Delete agent

Get agent

Get datastore

What teams actually run

Automated Knowledge Updates

Agent Deployment

Support Auditing

Internal Capability Integration

Building your own app? The connector is yours to use.

Chaindesk Connector

Claude Desktop

Developers and Ops

Support Teams

Product Leads

How do I connect my Chaindesk account?

Which AI clients can I use with this MCP?

Can I update my agent's knowledge through the chat?

Do I need to write code to manage my agents?

Can I see what my agents have been saying to users?

How do I find my Chaindesk API Key?

What is a Datastore?

Can I maintain conversation context via AI?

Botsonic AI Connector

FlowiseAI AI Connector

VectorShift (AI Workflow & RAG Automation) AI Connector

Cognita (RAG Framework) AI Connector

Suggestions

rag-chunk-boundary-optimizer AI Connector

Writer (AI Enterprise LLM) AI Connector

CHATFLY AI Connector

Code Integrity Prover AI Connector