Bring Retargeting
to LangChain
Learn how to connect AdRoll to LangChain and start using 7 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the AdRoll MCP Server?
Connect your AdRoll account to any AI agent and take full control of your digital advertising operations and retargeting workflows through natural conversation.
What you can do
- Campaign Orchestration — List and manage all your advertising campaigns programmatically, retrieving detailed budget settings and high-fidelity operational status in real-time
- Ad Group & Creative Intelligence — Access your complete directory of ad groups and creative assets to coordinate your visual marketing strategy across multiple channels
- Performance Reporting — Programmatically retrieve real-time metrics including clicks, impressions, and high-fidelity spend data to optimize your ROI directly through your agent
- Audience Segmentation — Access and manage your retargeting segments to ensure perfectly coordinated audience targeting and high-fidelity personalized experiences
- Infrastructure Monitoring — Access advertisable profile metadata and verify account-level settings directly through your agent for instant operational reporting
How it works
1. Subscribe to this server
2. Retrieve your API Key or Personal Access Token from the AdRoll Developer Portal
3. Start managing your advertising performance from Claude, Cursor, or any MCP client
No more manual toggling between complex ad tables or missing spend spikes. Your AI acts as your dedicated ad operations coordinator and performance analyst.
Who is this for?
- Marketing Managers — instantly retrieve campaign performance recaps and monitor spend using natural language commands
- Growth Advertisers — orchestrate audience segments and verify creative status without leaving your creative workspace
- Media Buyers — automate the retrieval of structured advertising metrics for internal reporting through simple AI queries
Built-in capabilities (7)
Get campaign details
Pass report criteria as a JSON string. Get performance report
List ad groups for a campaign
List all ads for an advertisable
List all advertisable profiles
List campaigns for an advertisable
List audience segments
Why LangChain?
LangChain's ecosystem of 500+ components combines seamlessly with AdRoll through native MCP adapters. Connect 7 tools via Vinkius and use ReAct agents, Plan-and-Execute strategies, or custom agent architectures. with LangSmith tracing giving full visibility into every tool call, latency, and token cost.
- —
The largest ecosystem of integrations, chains, and agents. combine AdRoll MCP tools with 500+ LangChain components
- —
Agent architecture supports ReAct, Plan-and-Execute, and custom strategies with full MCP tool access at every step
- —
LangSmith tracing gives you complete visibility into tool calls, latencies, and token usage for production debugging
- —
Memory and conversation persistence let agents maintain context across AdRoll queries for multi-turn workflows
AdRoll in LangChain
AdRoll and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect AdRoll to LangChain through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 3,400+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for AdRoll in LangChain
The AdRoll MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 7 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in LangChain only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
AdRoll for LangChain
Every tool call from LangChain to the AdRoll MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How do I find my AdRoll API credentials?
Log in to the AdRoll Developer Portal, navigate to your dashboard, and generate a Personal Access Token or register an app to obtain your API Key.
Can I retrieve spend metrics via AI?
Yes! The get_report tool allows your agent to retrieve high-fidelity spend and performance data by providing a JSON criteria object.
How do I check my advertisable profiles?
Use the list_advertisables tool to retrieve your complete directory of websites and brands managed within your AdRoll account programmatically.
How does LangChain connect to MCP servers?
Use langchain-mcp-adapters to create an MCP client. LangChain discovers all tools and wraps them as native LangChain tools compatible with any agent type.
Which LangChain agent types work with MCP?
All agent types including ReAct, OpenAI Functions, and custom agents work with MCP tools. The tools appear as standard LangChain tools after the adapter wraps them.
Can I trace MCP tool calls in LangSmith?
Yes. All MCP tool invocations appear as traced steps in LangSmith, showing input parameters, response payloads, latency, and token usage.
MultiServerMCPClient not found
Install: pip install langchain-mcp-adapters