Nango MCP for AI. Audit every integration and data sync, via chat.

Q: How do I check if a client's OAuth connection is expired using listconnections?

The listconnections tool lists all instantiated connections. The output for each connection includes its current status (e.g., 'Verified,' 'Expired'). This allows you to quickly filter and identify which accounts need re-authentication.

Q: Can I use getconnection to see the specific data fields that were synced?

Yes, getconnection provides precise metadata mapping. It details the authentication payloads and token boundaries for a given connection ID, which confirms exactly what credentials are being used.

Q: What is the difference between listrecords and listconnections?

They track different things entirely. listconnections tells you if the account (the user's system) is linked to Nango. listrecords shows the actual, synchronized data (like 50 contact records) that were pulled from that linked account.

Q: How do I check for data synchronization failures with listsyncs?

The listsyncs tool gives you the history and current status of automated sync jobs. You can identify failed attempts, see the error type (like 'Rate Limit'), and determine if the failure is systemic or temporary.

Q: Does getenvironment tell me anything about my API key?

getenvironment retrieves the runtime mapping logic bounds for the Nango instance. While it gives you architectural context, use getconnection if you need details specific to a connection's authentication payload.

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Connect to your AI in seconds.

Nango provides a unified API layer for managing complex product integrations. Your agent connects to Nango to audit OAuth connections across hundreds of providers, track real-time data sync status, and access synchronized records from multiple external sources without touching a dashboard.

What your AI can do

List integrations

Lists all available integration logic configurations defined within the Nango platform.

Get integration

Pulls explicit parameters detailing a single target integration's configuration logic.

List connections

Lists all instantiated OAuth or credential connections that have been authenticated through Nango.

+ 4 more capabilities included

Check connection status and details

Use get_connection to extract specific metadata for an individual Nango connection.

List all connected accounts

Use list_connections to get a list of every OAuth or credential-based account linked through Nango.

Review sync history and status

Use list_syncs to see the current or historical synchronization status for any given connection.

Fetch synchronized data records

Use list_records to retrieve actual, unified data entries (like contacts) matched against a specific provider.

List available integration logics

Use list_integrations to see all the different types of integration logic set up in Nango.

Get environment configuration details

Use get_environment to pull the literal runtime mapping boundaries for the active Nango instance.

Ask an AI about this

Included with Plan

Waiting for input…

AI Agent

Nango (Unified API & Integration Platform): 7 Tools for Data Flow

These tools let your agent manage the full lifecycle of integrations: from listing available logic to checking live sync status and accessing unified records.

Make your AI actually useful.

Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.

Start using Nango (Unified API & Integration Platform) on Vinkius

List Integrations

Lists all available integration logic configurations defined within the Nango platform.

Get Integration

Pulls explicit parameters detailing a single target integration's configuration...

List Connections

Lists all instantiated OAuth or credential connections that have been authenticated...

Get Connection

Gets specific metadata detailing a single Nango connection's authentication payload...

List Syncs

Provides a list of the current or historical synchronization status for an account...

List Records

Lists actual data records that have been successfully synchronized and match a connected provider mapping.

Get Environment

Retrieves the runtime mapping logic bounds for the active Nango instance environment.

Security and governance baked right in.

Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.

Claude AI

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.

Start a conversation

Open a new chat. The Nango integration is available immediately — no restart needed.

Antigravity

Configure Agent Environment

Open your Antigravity agent's workspace configuration or mcp-servers.json file.

Bind the Endpoint

Add the Vinkius endpoint URL to your agent's MCP connections list:

"mcp_servers": {
  "nango-unified-api-integration-platform": {
    "serverUrl": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
  }
}

Provide your secure token in place of [YOUR_TOKEN_HERE] to ensure your agent requests are authenticated.

Execute

Start your Antigravity session. The agent will autonomously discover and utilize the Nango tools with full Vinkius guardrails applied.

VS Code Copilot

⚡

One-Click Install (Recommended)

In your Vinkius Dashboard, simply click the Add to VS Code button for this server. We'll automatically configure your local workspace.

Or configure manually

Open MCP Settings

Open VS Code, press Ctrl/Cmd + Shift + P, and search for GitHub Copilot: MCP Servers.

Add Server Config

Add the Vinkius endpoint configuration to your mcp-servers.json file:

"nango-unified-api-integration-platform": {
  "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
}

Ensure you replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.

LangChain

Install Dependencies

Install the LangChain MCP adapters for your environment:

pip install langchain-mcp-adapters

Connect the Server

Use the SSEClient in LangChain to connect to the Vinkius managed endpoint:

from langchain_mcp_adapters.client import SSEClient

# Connect to Vinkius
client = SSEClient(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
tools = client.get_tools()

CrewAI

Define the Tool

Load the Vinkius MCP tools into your CrewAI agents:

from crewai import Agent
from mcp_crewai import MCPTool

# Connect securely to Vinkius
vinkius_tools = MCPTool(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

# Assign to Agent
researcher = Agent(
    role='Data Researcher',
    tools=vinkius_tools.get_all()
)

Execute Task

Run your CrewAI process. The agent will autonomously route tasks to the Vinkius managed server.

Choose How to Get Started

Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.

Build Your Own

Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.

Import from OpenAPI, Swagger, or YAML specs
Create Agent Skills with progressive disclosure
Deploy to edge with MCPFusion framework
Built in DLP, auth, and compliance on every call
Real time usage dashboard and cost metering
Publish to catalog or keep private

Start building

Make Your AI Do More

Start with Nango (Unified API & Integration Platform), then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.

Use this MCP plus 5,100+ others, all in one place
Add new capabilities to your AI anytime you want
Every connection is secured and compliant automatically
Track usage and costs across all your servers
Works with Claude, ChatGPT, Cursor, and more
New servers added to the catalog every week

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Nango. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

VINKIUS INFRASTRUCTURE

Cloud Hosted

Managed infra

V8 Isolated

Sandboxed per request

Zero-Trust Proxy

No stored credentials

DLP Enforced

Policy on every call

GDPR Compliant

EU data residency

Token Compression

~60% cost reduction

Your data is protected. See how we built it.

Works with Claude, ChatGPT, Cursor, and more

The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.

This connection provides 7 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.

Checking connection status shouldn't require five different dashboards.

Right now, if you need to know if your client connected Salesforce (last week), HubSpot (today), and their internal ticketing system (ever?), you open three separate vendor logins. Then you click 'Settings,' find the OAuth tab, scroll through multiple pages of status lights, and manually write up a report on connection health.

With Nango's MCP Server, you just ask your agent: 'What is the current connection status for our top 10 clients?' The server uses `list_connections` to hit all those endpoints concurrently and gives you one single, summarized answer. It’s immediate state reporting.

Nango (Unified API & Integration Platform): Get the full data flow picture.

Before Nango, if a developer needed to verify that 'Contact Name X' synced from Salesforce into the internal CRM schema, they had to run multiple queries: one against the source system, and another against the target table. It was complex, slow, and prone to missing data drift.

Now, you ask your agent to fetch records for a specific model using `list_records`. The server handles the whole flow—it confirms the connection status first (via `get_connection`), then pulls the unified record set. You get the final answer without writing complex join queries.

Support 24/7 support@vinkius.com ↗

Security Vinkius Trust Center ↗

SLA Service Level Agreement ↗

Report Listing Send Report ↗

What your AI can actually do with this

Look, you're running complex integrations across a bunch of providers, and manually checking everything? Forget about it. Nango gives your agent an API layer to handle the whole mess—auditing OAuth connections, tracking data sync status, and pulling records from multiple sources without you ever having to touch a dashboard. You connect this server, and suddenly your AI client can talk directly to your integration backend.

When you need to check specific connection details, you'll use get_connection to pull the metadata for an individual Nango link; that gives you the authentication payload and exactly where the tokens start and stop. If you gotta see every single connection linked up—whether it's OAuth or just a set of credentials—you hit list_connections to get a full roster of everything authenticated through Nango.

You can also check out all the available integration logic configurations in your platform by running list_integrations; that tells you what kinds of data connections Nango supports.

To monitor how well everything's working, you use list_syncs. This tool gives you a record—current or historical—of whether an account connection actually synced its data and if there were any issues. If you need to see the actual records that got synchronized, say contacts or deals, for a specific provider mapping across your whole connected pool, you run list_records and get those unified entries right away.

You can pull the runtime mapping logic boundaries for the active Nango instance environment using get_environment; this shows you exactly how Nango is set up to manage data flow. Finally, if you need more granular info about a specific target integration's configuration—like pulling out explicit parameters or setup details—you call get_integration.

Here's the deal with getting your agent connected: You subscribe to this server on Vinkius and drop in your Nango Secret Key. After that, your AI client can manage everything. Your agent pulls every data point you need using these tools, letting you bypass any clunky dashboards. For example, if you wanna know what kind of connections are available, list_connections shows it all.

If you gotta audit the setup, get_environment reveals the mapping logic boundaries. You can review the history and status of syncs with list_syncs, or pull concrete records using list_records. It's a clean way to keep tabs on hundreds of providers without writing a single line of code.

Built · Hosted · Managed by Vinkius Nango MCP Server - Audit API Connections & Data Syncs

Server ID 019d75da-5c3d-7032-9b21-c80197065e6a

Vinkius Inspector

Compliance Grade A+

Score 100/100

Report View Report ↗

What Changes When You Connect

Use list_connections to see all connected accounts instantly. You don't have to click through dozens of vendor dashboards just to check if a client's Salesforce connection is active or expired.

The list_syncs tool tracks sync history and status, so you can pinpoint exactly when and why data failed to transfer—whether it was a rate limit error or invalid credentials. No more guessing games.

When debugging schemas, the combination of list_integrations and get_environment lets you inspect the full mapping logic and runtime constraints without needing developer access to the core Nango platform.

Need actual data? Instead of viewing abstract records, list_records pulls unified data (like contacts or deals) from all linked providers into one view. It’s instant, consolidated visibility.

get_connection provides a deep credential audit. You can verify the exact metadata and token boundaries for any specific connection, which is critical for compliance checks.

See it in action

01 01

Onboarding Audit: Checking Client Access

A Product Manager needs to confirm if three key enterprise clients (Salesforce, HubSpot, Jira) are all connected and healthy. Instead of logging into three separate vendor dashboards, they ask their agent: 'List active connections for our top 5 clients.' The agent uses list_connections and reports back the status of every single account in one reply.

02 02

Debugging a Data Gap

An Integration Lead notices that recent deal records are missing. They ask the agent to 'Show me sync logs for deals related to connection ID conn-abc.' The agent uses list_syncs, identifies a failed job, and then can use get_environment to check if the mapping logic itself changed.

03 03

Schema Verification

A Software Developer needs to build a new feature relying on contact data. They ask: 'What are the synchronized contacts for connection conn-456?' The agent uses list_records, pulling 50 records and verifying that the structure (schema) matches what their code expects, without manual SQL queries.

04 04

Pre-Deployment Check

Before launching a major feature update, an Integration Lead must confirm all integration logic is correct. They use list_integrations to review the setup parameters and then ask for 'the connection metadata' using get_integration to ensure every piece of the puzzle is accounted for.

The honest tradeoffs

Assuming Data Exists

Anti-pattern

A user sees a contact record ID in one system and assumes that data point exists across all linked providers. They try to write code using the raw data without checking its source status.

The Fix

Before accessing any records, always use list_syncs or get_connection. This proves the connection is active and provides a history of successful transfers, confirming data integrity before coding.

Over-relying on Dashboards

Anti-pattern

Manually clicking through 10 different vendor dashboards (Salesforce, Mailchimp, etc.) to compile an audit report showing which connections are expired.

The Fix

Use list_connections. This single tool aggregates the status from all sources and gives you a unified list of connected accounts in one conversational output.

Ignoring Mapping Logic

Anti-pattern

Debugging why data looks wrong, assuming it's just user error. The root problem is actually that the underlying integration logic changed.

The Fix

Call get_integration and check get_environment. This lets you inspect the actual mapping parameters and runtime constraints to see if the system itself changed how it handles the data.

When It Fits, When It Doesn't

Use Nango when your core problem is coordinating state, connections, or data across multiple, disparate third-party systems. If you need a single source of truth for external integration status (e.g., 'Is this account connected?'), this is the right tool.

Don't use it if:
1. You are only dealing with internal database tables—use direct SQL or ORM tools instead.
2. Your goal is to send a message, not audit a connection—a dedicated messaging tool works better.
3. The data source doesn't support OAuth/API authentication—you need file uploads or manual entry.

This server excels at the 'meta-layer' of integration management: proving that connections exist and confirming how the data moved, using tools like list_connections and list_syncs to build a reliable audit trail.

Questions you might have

How do I check if a client's OAuth connection is expired using list_connections? +

The list_connections tool lists all instantiated connections. The output for each connection includes its current status (e.g., 'Verified,' 'Expired'). This allows you to quickly filter and identify which accounts need re-authentication.

Can I use get_connection to see the specific data fields that were synced? +

Yes, get_connection provides precise metadata mapping. It details the authentication payloads and token boundaries for a given connection ID, which confirms exactly what credentials are being used.

What is the difference between list_records and list_connections? +

They track different things entirely. list_connections tells you if the account (the user's system) is linked to Nango. list_records shows the actual, synchronized data (like 50 contact records) that were pulled from that linked account.

How do I check for data synchronization failures with list_syncs? +

The list_syncs tool gives you the history and current status of automated sync jobs. You can identify failed attempts, see the error type (like 'Rate Limit'), and determine if the failure is systemic or temporary.

Does get_environment tell me anything about my API key? +

get_environment retrieves the runtime mapping logic bounds for the Nango instance. While it gives you architectural context, use get_connection if you need details specific to a connection's authentication payload.

How does `get_integration` help me understand required sync parameters? +

It retrieves explicit, mandatory parameters for a single integration. This output shows exactly what data fields and connection settings Nango requires from that specific provider to run the sync successfully. It's essential for initial setup validation.

Can I use `list_records` to discover all available model types (like 'deals' or 'contacts')? +

Yes, you specify the record type you want to check. Nango organizes data into specific models; by using this tool, your agent can filter and confirm if a certain model—say, 'invoices'—has any synchronized records associated with it.

What does `get_environment` tell me about connection capacity or limits? +

It reports the operational boundaries for your active Nango instance. This provides visibility into current host constraints and system quotas, letting you know if performance issues stem from hitting a predefined limit.

Can I see which customers have an expired OAuth connection through my agent? +

Yes. Use the list_connections tool to retrieve all authenticated linked accounts. Your agent will report the current status of each connection, helping you identify which users need to re-authenticate their external platforms.

How do I check if a data synchronization failed recently? +

The list_syncs tool retrieves the synchronization history for a specific connection. Your agent will expose the log outputs and status indicators, allowing you to debug data processing issues directly from your conversation.

Can my agent retrieve synchronized data records from external APIs? +

Absolutely. Use the list_records tool with a Connection ID and a model name (e.g., 'contacts'). Your agent will query Nango's storage to fetch the raw synchronized objects, bypassing external API limits natively.

Connect to your AI in seconds.

List integrations

Get integration

List connections

Nango (Unified API & Integration Platform): 7 Tools for Data Flow

Make your AI actually useful.

List Integrations

Get Integration

List Connections

Get Connection

List Syncs

List Records

Get Environment

Security and governance baked right in.

Claude AI

Open Claude Settings

Add Custom Connector

Start a conversation

Claude Code

Open your terminal

Add the MCP Server

Start coding

Cursor

One-Click Install (Recommended)

Open Cursor Settings

Add New Server

Use in Composer

Antigravity

Configure Agent Environment

Bind the Endpoint

Execute

VS Code Copilot

One-Click Install (Recommended)

Open MCP Settings

Add Server Config

Windsurf

One-Click Install (Recommended)

Open Windsurf Settings

Add Server Endpoint

LangChain

Install Dependencies

Connect the Server

CrewAI

Define the Tool

Execute Task

Choose How to Get Started

Build Your Own

Make Your AI Do More

Works with Claude, ChatGPT, Cursor, and more

Checking connection status shouldn't require five different dashboards.

Nango (Unified API & Integration Platform): Get the full data flow picture.

What your AI can actually do with this

Here's how it actually works

Who is this actually for?

What Changes When You Connect

See it in action

Onboarding Audit: Checking Client Access

Debugging a Data Gap

Schema Verification

Pre-Deployment Check

The honest tradeoffs

Assuming Data Exists

Over-relying on Dashboards

Ignoring Mapping Logic

When It Fits, When It Doesn't

Questions you might have