
Step by step, for each client
Connecting ContextQA in each client
The same hosted link plugs into every client below. Pick the one you use — each setup takes seconds — and start a new chat.

Claude
ContextQA Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcpConnecting ContextQA to Claude
About a minute, right in your Claude settings
- 1In Claude, open Customize and choose Connectors (claude.ai or the desktop app).
- 2Click +, choose Add custom connector, and paste your ContextQA link as the remote MCP server URL.
- 3Click Add and start a new chat. Ask for something real: ContextQA is now part of your Claude.
{
"mcpServers": {
"contextqa-mcp": {
"url": "https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcp"
}
}
}
ChatGPT
ContextQA Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcpConnecting ContextQA to ChatGPT
About a minute, right in your ChatGPT settings
- 1In ChatGPT, open Settings, choose Apps & Connectors, and turn on Developer mode under Advanced settings.
- 2Click Create, name it, and paste your ContextQA link as the MCP server URL. Choose No authentication and check “I trust this application”.
- 3Create it, start a new chat, and switch the connector on via the + menu. Ask for something real: ContextQA is now part of your ChatGPT.
{
"mcpServers": {
"contextqa-mcp": {
"url": "https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcp"
}
}
}
Gemini
ContextQA Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcpConnecting ContextQA to Gemini
About a minute, right in your terminal
- 1Open the Gemini CLI in your terminal.
- 2Run: gemini mcp add --transport http ContextQA <your link>. Your ContextQA link above is the HTTP URL.
- 3Run /mcp and confirm the status shows CONNECTED. ContextQA is now part of your Gemini.
{
"mcpServers": {
"contextqa-mcp": {
"url": "https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcp"
}
}
}
Perplexity
ContextQA Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcpConnecting ContextQA to Perplexity
A few minutes, in the Perplexity Mac app
- 1In the Perplexity Mac app, open Account, choose Connectors, and click Add Connector.
- 2In the Simple tab, choose MCP Connector, name it, and add the bridge command with your ContextQA link: npx mcp-remote <your link>. The link above is the URL.
- 3Click Save and check it shows Running, then turn the connector on under Sources on the homepage. ContextQA is now part of your Perplexity.
{
"mcpServers": {
"contextqa-mcp": {
"url": "https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcp"
}
}
}
Grok
ContextQA Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcpConnecting ContextQA to Grok
About a minute, at grok.com/connectors
- 1In Grok, open grok.com/connectors and click New Connector.
- 2Choose Custom, name it, and paste your ContextQA link as the remote MCP server URL.
- 3Save and enable it, finish the browser authorization if prompted, and ask Grok something real. ContextQA is now part of your Grok.
{
"mcpServers": {
"contextqa-mcp": {
"url": "https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcp"
}
}
}
Microsoft Copilot
ContextQA Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcpConnecting ContextQA to Copilot
About a minute, in VS Code's Copilot Chat
- 1In VS Code, open the Copilot Chat panel, click the tools icon and select the + icon, or run MCP: Add Server from the Command Palette.
- 2Choose your scope, name the server, and paste your ContextQA link as the server URL with HTTP transport.
- 3Confirm the server appears in your MCP list, then ask Copilot something real. ContextQA is now part of your Copilot.
{
"mcpServers": {
"contextqa-mcp": {
"url": "https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcp"
}
}
}
Cursor
ContextQA Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcpConnecting ContextQA to Cursor
About a minute, in Cursor
- 1Open Customize in the Cursor sidebar (or create .cursor/mcp.json in your project).
- 2Add an MCP server named ContextQA with the url field set to your link. The link above is the URL.
- 3Save, enable the server, and ask something real. ContextQA is now part of Cursor.
{
"mcpServers": {
"contextqa-mcp": {
"url": "https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcp"
}
}
}
VS Code
ContextQA Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcpConnecting ContextQA to VS Code
About a minute, in VS Code
- 1Run MCP: Add Server from the Command Palette (or create .vscode/mcp.json in your project).
- 2Add a server named ContextQA with type http and your link as the url. The link above is the URL.
- 3Save and ask something real in Copilot Chat. ContextQA is now part of VS Code.
{
"mcpServers": {
"contextqa-mcp": {
"url": "https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcp"
}
}
}
Windsurf
ContextQA Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcpConnecting ContextQA to Windsurf
About a minute, in Cascade
- 1In Cascade, click the MCPs icon (or go to Settings, Cascade, MCP Servers).
- 2Edit mcp_config.json and add ContextQA with the serverUrl field set to your link. The link above is the URL.
- 3Save and ask something real. ContextQA is now part of Windsurf.
{
"mcpServers": {
"contextqa-mcp": {
"url": "https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcp"
}
}
}
JetBrains
ContextQA Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcpConnecting ContextQA to JetBrains
About a minute, in Settings
- 1Go to Settings, Tools, AI Assistant, Model Context Protocol (MCP).
- 2Click Add and add ContextQA with the url field set to your link. The link above is the URL.
- 3Click OK and Apply, check the Status column, and ask something real. ContextQA is now part of your IDE.
{
"mcpServers": {
"contextqa-mcp": {
"url": "https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcp"
}
}
}
Cline
ContextQA Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcpConnecting ContextQA to Cline
About a minute, in the Cline panel
- 1In the Cline panel, click the MCP Servers icon and open the Remote Servers tab.
- 2Add a server named ContextQA with your link as the Server URL and Streamable HTTP as the transport. The link above is the URL.
- 3Click Add Server and ask something real. ContextQA is now part of Cline.
{
"mcpServers": {
"contextqa-mcp": {
"url": "https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcp"
}
}
}
LangChain
ContextQA Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcpConnecting ContextQA to LangChain
About a minute, in your code
- 1Install LangChain with the mcp extra: pip install "langchain[mcp]".
- 2Create an MCPAdapter with your ContextQA link: MCPAdapter("<your link>"). The link above is the URL.
- 3Call list_tools and pass the tools to your agent. ContextQA is now part of your LangChain agent.
{
"mcpServers": {
"contextqa-mcp": {
"url": "https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcp"
}
}
}
Vercel AI SDK
ContextQA Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcpConnecting ContextQA to the Vercel AI SDK
About a minute, in your code
- 1Install the MCP client: npm install @ai-sdk/mcp, and import createMCPClient from '@ai-sdk/mcp'.
- 2Create the client with your ContextQA link as the transport: { type: 'http', url: '<your link>' }. The link above is the URL.
- 3Call client.tools() and pass the tools to streamText. ContextQA is now part of your AI SDK app.
{
"mcpServers": {
"contextqa-mcp": {
"url": "https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcp"
}
}
}
Lovable
ContextQA Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcpConnecting ContextQA to Lovable
About a minute, in the Connectors catalog
- 1Open Connectors, select the + button in the top right of the catalog, and choose MCP server.
- 2Name the server and paste your ContextQA link as the Server URL. The link above is the URL.
- 3Choose No authentication and click Add server, then ask Lovable something real. ContextQA is now part of Lovable.
{
"mcpServers": {
"contextqa-mcp": {
"url": "https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcp"
}
}
}
Z.ai
ContextQA Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcpConnecting ContextQA to Z.ai
About a minute, in ZCode settings
- 1Open Settings, MCP Servers, then click New MCP Server in the upper-right corner.
- 2Choose the User scope, name it, and keep the type as HTTP. Paste your ContextQA link as the service URL. The link above is the URL.
- 3Click Add and confirm the server is enabled in the list, then ask something real. ContextQA is now part of Z.ai.
{
"mcpServers": {
"contextqa-mcp": {
"url": "https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcp"
}
}
}
Raycast
ContextQA Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcpConnecting ContextQA to Raycast
A few minutes, in Raycast Pro
- 1Search for the Install MCP Server command (or open Manage MCP Servers and choose Install New Server).
- 2Give the server a name and icon, select HTTP as the transport, and paste your ContextQA link as the URL. The link above is the URL.
- 3Press Install MCP Server and confirm the status shows Running, then ask something real. ContextQA is now part of Raycast.
{
"mcpServers": {
"contextqa-mcp": {
"url": "https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcp"
}
}
}
Qwen Code
ContextQA Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcpConnecting ContextQA to Qwen Code
About a minute, in your terminal
- 1Run: qwen mcp add --transport http ContextQA <your link>. The link above is the URL.
- 2Prefer a config file? Add it to ~/.qwen/settings.json (user) or .qwen/settings.json (project) with the httpUrl field. The link above is the URL.
- 3Enter /mcp in the chat to confirm the server appears. ContextQA is now part of Qwen Code.
{
"mcpServers": {
"contextqa-mcp": {
"url": "https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcp"
}
}
}
Kimi Code
ContextQA Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcpConnecting ContextQA to Kimi Code
About a minute, in the TUI
- 1Run /mcp-config in the Kimi Code TUI to add a server interactively (or edit mcp.json directly).
- 2Add a server named ContextQA with your link in the url field. The link above is the URL.
- 3Run /mcp to confirm the status, then ask something real. ContextQA is now part of Kimi Code.
{
"mcpServers": {
"contextqa-mcp": {
"url": "https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcp"
}
}
}
Le Chat
ContextQA Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcpConnecting ContextQA to Le Chat
About a minute, in Connectors
- 1In Le Chat, open Connectors and choose to add a custom connector.
- 2Paste your ContextQA link as the remote MCP server URL. The link above is the URL.
- 3Save and authorize, then ask something real. ContextQA is now part of Le Chat.
{
"mcpServers": {
"contextqa-mcp": {
"url": "https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcp"
}
}
}Claude and other AIs + ContextQA
One chat. Your ContextQA, live inside Claude and other AIs.
Real prompts, answered with live data. This is the kind of conversation you will have in Claude and other AIs once the link is in.
Waiting for input…
Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.
These prompts ship with the ContextQA Connector. Once yours is connected, they work in your chats.
The full capability set, the prompts and the observed latency live on the ContextQA Connector page.
Mission Control
See everything your agents do in ContextQA.
When your agents run a tool in ContextQA, it happens on the client side: you see the answer in the chat, but not the request itself, what data it carried, or whether a rule was broken.
Now every move lands on your screen.
Every execution is recorded, enforced, and shown to you: what ran, what it returned, what was blocked, and why.
Know exactly what needs your attention before you even look at the charts. One briefing. The full picture. The next move.
AI Agents Activities
last 30 daysRequest Volume & Latency
requests latencyEvery request your agents make through ContextQA is logged, enforced and auditable. See how AI Governance turns agent activity into accountability, and what it means for your ContextQA workflows.
What sets us apart
It's not just the Connector that stays safe. Everything your agents do through it is.
Connecting ContextQA to your AI is step one. But an open line between your agents and ContextQA is only half the story: without protection, every action they take runs unguarded.
That's why protection doesn't stop at the door.
Every action your agents take through the Connector runs inside our infrastructure: signed activity logs, automatic key rotation, spending limits that pause instead of surprise, and a sandbox that isolates every execution.
Tamper Proof Activity Log
Every request your agents make in ContextQA is recorded and signed, so any change to the history becomes detectable.
Automatic Key Rotation
We rotate security keys every 24 hours. Your ContextQA connection stays protected without any manual work.
Spending Protection
We enforce the spending limit you choose and pause actions that exceed it until approval is received. Your ContextQA actions never surprise you.
Isolated Sandbox
Every execution through ContextQA runs isolated, with 34+ security rules covering memory, CPU, network access, file handling and execution.
Security Event Streaming
Security events flow to Splunk, Datadog or your own webhook, so ContextQA activity lands in the tools you already rely on.
Instant Resume
Idle connections resume in 3 to 5 ms while preserving their state, keeping your conversations responsive across every client.
Malicious File Protection
We detect compressed files designed to exhaust system resources and block them before they ever reach ContextQA.
Credential Validation
We test your ContextQA credentials before saving them. Invalid credentials are rejected instead of being stored.
Separate Usage Limits
Usage stays isolated per account, so activity in one connection never consumes another account's allowance.
One Connector, one link, and the whole operation is protected. Not just the connection: everything your agents do through it.
These guarantees are not add-ons: they are the infrastructure every ContextQA connection runs on. Read how our infrastructure protects everything your agents do, end to end.
Inside Vinkius
Get ContextQA ready for your AI. It's easy.
You choose ContextQA from the Vinkius Catalog, sign in to your ContextQA account, and get one connection link. That's it.
You choose ContextQA
You find ContextQA in the Catalog and install the Connector with one click.
ContextQA
Active
Enable ConnectorActivating…You sign in
You connect your ContextQA account and choose what you want your AI to access. Your credentials stay encrypted and separate from your AI.
Configure Credentials
Configure credentials for {{connectorName}}
RequiredEncryptedSave & ContinueYou add the link in your AI client
Vinkius gives you one connection link. Add it to the client you use — the exact steps for each client are in the section above — and ContextQA is live everywhere in one move.
Token generated successfully
MCP Connection URL
https://edge.vinkius.com/vk_preview_arIg6fOatFWYf4ywr6Asm6h013dTDEa83NCzuGoP/mcpGo to DashboardConnection Token
vk_live_••••••••
Set it up once. Use ContextQA with the AI you already use.
FAQ
Claude access questions.
- 01
Does this work on claude.ai and in the Claude desktop app?
Yes. You add the same link under Customize and Connectors in both, and your chats work the same in each.
- 02
If I connect ContextQA to Claude, can I use the same connection in ChatGPT or Gemini later?
Yes, and that's the point: the connection is yours, not Claude's. You paste the same link in any AI you use, and there's nothing new to set up or pay again. Connect a new AI and ContextQA is already there.
- 03
Do I need to hand my ContextQA password to Claude?
Never. You sign in once at Vinkius, and we keep your logins encrypted and away from your AI. Claude only ever sees the link, and you can remove it whenever you want.
- 04
What can I actually ask Claude to do with ContextQA?
Whatever the Connector covers: check data, run actions and bring answers back into the chat. The Connector page lists every capability your AI gains, with real examples you can copy.
- 05
Claude doesn't show the Connector. What do I check?
Make sure the link was pasted exactly as copied and that the Connector is active in your Vinkius account, then reopen the connectors list in Claude. A deactivated Connector stops appearing in new chats.
- 06
Can I remove the access later?
Anytime. Remove the connector under Customize and Connectors in Claude and it's out of your chats. Your Vinkius account keeps the connection and its history either way, ready for the next AI.
More questions about ContextQA? The Connector page answers them. See everything the ContextQA Connector can do
About the Connector
What ContextQA adds to your AI.
Once you connect it, your AI gains 10 capabilities: the exact actions it can take in ContextQA when you ask. The Connector page lists every one of them in detail, alongside the latency we measure in production and prompts worth trying first.
See everything the ContextQA Connector can do