LangChain

Use UtilityAPI with LangChain

Set up in seconds, once. From then on, your agent gets things done for you: add one adapter call, and UtilityAPI is live in LangChain.

Ask AI about this guide

UtilityAPI Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_UQcFN9jSbPr5jD0q3QcZWex8kd0ypw9wyAD09b4d/mcp

Connecting UtilityAPI to LangChain

About a minute, in your code

  1. 1Install LangChain with the mcp extra: pip install "langchain[mcp]".
  2. 2Create an MCPAdapter with your UtilityAPI link: MCPAdapter("<your link>"). The link above is the URL.
  3. 3Call list_tools and pass the tools to your agent. UtilityAPI is now part of your LangChain agent.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "utilityapi-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_UQcFN9jSbPr5jD0q3QcZWex8kd0ypw9wyAD09b4d/mcp"
    }
  }
}

LangChain + UtilityAPI

One agent. Your UtilityAPI, live inside LangChain.

Real prompts, answered with live data. This is the kind of session your agent will run once the adapter is in.

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

These prompts ship with the UtilityAPI Connector. Once yours is connected, your agent can run them.

The full capability set, the prompts and the observed latency live on the UtilityAPI Connector page.

Mission Control

See everything your LangChain agents do in UtilityAPI.

When your LangChain agent runs a tool in UtilityAPI, it happens inside your code: you see the output, 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.

AI Briefing
Upgrade to unlock

Know exactly what needs your attention before you even look at the charts. One briefing. The full picture. The next move.

Requests
0
Total in this period
Avg Latency
0
API 88ms · Overhead 54ms
Vinkius Reliability
0
Agent 280 · Upstream 47 · Vinkius 15
Tokens
0
AI tokens processed
DLP Protected
0
Sensitive data redacted
Cost Saved
0
FinOps truncations applied

AI Agents Activities

last 30 days
30d agotoday

Request Volume & Latency

requests latency

Every request your LangChain agents make through UtilityAPI is logged, enforced and auditable. See how AI Governance turns agent activity into accountability, and what it means for your UtilityAPI workflows.

What sets us apart

It's not just the Connector that stays safe. Everything your agents do through it is.

Connecting UtilityAPI to your AI is step one. But an open line between your agents and UtilityAPI 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.

01

Tamper Proof Activity Log

Every request your agents make in UtilityAPI is recorded and signed, so any change to the history becomes detectable.

02

Automatic Key Rotation

We rotate security keys every 24 hours. Your UtilityAPI connection stays protected without any manual work.

03

Spending Protection

We enforce the spending limit you choose and pause actions that exceed it until approval is received. Your UtilityAPI actions never surprise you.

04

Isolated Sandbox

Every execution through UtilityAPI runs isolated, with 34+ security rules covering memory, CPU, network access, file handling and execution.

05

Security Event Streaming

Security events flow to Splunk, Datadog or your own webhook, so UtilityAPI activity lands in the tools you already rely on.

06

Instant Resume

Idle connections resume in 3 to 5 ms while preserving their state, keeping your LangChain sessions responsive.

07

Malicious File Protection

We detect compressed files designed to exhaust system resources and block them before they ever reach UtilityAPI.

08

Credential Validation

We test your UtilityAPI credentials before saving them. Invalid credentials are rejected instead of being stored.

09

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 UtilityAPI connection runs on. Read how our infrastructure protects everything your LangChain agents do, end to end.

Inside Vinkius

Get UtilityAPI ready for your AI. It's easy.

You choose UtilityAPI from the Vinkius Catalog, sign in to your UtilityAPI account, and get one connection link. That's it.

  1. You choose UtilityAPI

    You find UtilityAPI in the Catalog and install the Connector with one click.

    UtilityAPI

    Active

    Enable Connector
    Activating…

  2. You sign in

    You connect your UtilityAPI 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}}

    RequiredEncrypted
    Save & Continue

    Encrypted Storage

    Your credentials are encrypted at rest and in transit.

    Never Shared

    Your credentials are never shared with third parties.

    Full Control

    Revoke or update credentials at any time.

  3. You add the link in your code

    Vinkius gives you one connection link. In your agent, you create an MCPAdapter with the link as the server URL, and the tools are ready.

    Token generated successfully

    MCP Connection URL

    https://edge.vinkius.com/vk_preview_UQcFN9jSbPr5jD0q3QcZWex8kd0ypw9wyAD09b4d/mcp

    Connection Token

    vk_live_••••••••
    Go to Dashboard

Set it up once. Use UtilityAPI with the AI you already use.

FAQ

LangChain access questions.

  • 01

    Which LangChain version supports this?

    LangChain 1.4.0 or newer with the mcp extra (pip install langchain[mcp]). The MCPAdapter lives in the langchain.mcp namespace and is currently in beta.

  • 02

    If I connect UtilityAPI to my LangChain agent, can I use the same connection in Claude or ChatGPT later?

    Yes, and that's the point: the connection is yours, not LangChain'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 UtilityAPI is already there.

  • 03

    Do I need to hand my UtilityAPI password to my agent?

    Never. You sign in once at Vinkius, and we keep your logins encrypted and away from your AI. Your code only ever sees the link, and you can remove it whenever you want.

  • 04

    What can my agent actually do with UtilityAPI?

    Whatever the Connector covers: check data, run actions and bring answers back. The Connector page lists every capability your AI gains, with real examples you can copy.

  • 05

    The tools don't show up. What do I check?

    Confirm the URL matches your link exactly and that the Connector is active in your Vinkius account, then call list_tools again. A deactivated Connector stops responding.

  • 06

    Can I remove the access later?

    Anytime. Remove the MCPAdapter call from your code and the tools leave your agent. Your Vinkius account keeps the connection and its history either way, ready for the next AI.

  • More questions about UtilityAPI? The Connector page answers them. See everything the UtilityAPI Connector can do

About the Connector

What UtilityAPI adds to your AI.

Once you connect it, your AI gains 12 capabilities: the exact actions it can take in UtilityAPI 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 UtilityAPI Connector can do