Compatible with every major AI agent and IDE
What is the Kong Gateway MCP Server?
Connect your Kong Gateway Admin API to any AI agent and take full control of your API management lifecycle through natural conversation.
What you can do
- Services & Routes — List, create, and update upstream services and their associated routing rules to manage traffic flow.
- Consumer Management — Query and manage API consumers, allowing you to track users and applications interacting with your gateway.
- Plugin Configuration — Inspect and manage plugins for authentication, rate limiting, and logging across your services and routes.
- Upstreams & Targets — Configure load balancing by managing upstreams and their health-checked targets.
- SSL/TLS Management — List and update certificates and SNIs to ensure secure communication across your endpoints.
- System Health — Retrieve real-time status and information about your Kong instance to monitor performance.
How it works
- Subscribe to this server
- Enter your Kong Admin URL (and optional Admin Token)
- Start managing your API infrastructure from Claude, Cursor, or any MCP-compatible client
No more manual cURL commands or navigating complex dashboards to check a route configuration. Your AI acts as a dedicated DevOps engineer or API Architect.
Who is this for?
- DevOps Engineers — quickly check gateway status, list plugins, and verify upstream health without leaving the terminal or IDE.
- Backend Developers — create and test new services and routes instantly during the development cycle.
- API Architects — audit consumer access and plugin configurations to ensure security and compliance across the organization.
Built-in capabilities (40)
Create a new Kong Certificate
Create a new Kong Consumer
Create a new Kong Plugin
Create a new Kong Route
Create a new Kong Service
Create a new Kong SNI
Create a new Target for an Upstream
Create a new Kong Upstream
Delete a Kong Certificate
Delete a Kong Consumer
Delete a Kong Plugin
Delete a Kong Route
Delete a Kong Service
Delete a Kong SNI
Delete a Target from an Upstream
Delete a Kong Upstream
Get details for a specific Kong Certificate
Get details for a specific Kong Consumer
Retrieve general information about the Kong node
Get details for a specific Kong Plugin
Get details for a specific Kong Route
Get details for a specific Kong Service
Get details for a specific Kong SNI
Retrieve the status of the Kong node
Get details for a specific Kong Upstream
List all Kong Certificates
List all Kong Consumers
List all Kong Plugins
List all Kong Routes
List all Kong Services
List all Kong SNIs
List all Targets for an Upstream
List all Kong Upstreams
Update an existing Kong Certificate
Update an existing Kong Consumer
Update an existing Kong Plugin
Update an existing Kong Route
Update an existing Kong Service
Update an existing Kong SNI
Update an existing Kong Upstream
Why LangChain?
LangChain's ecosystem of 500+ components combines seamlessly with Kong Gateway through native MCP adapters. Connect 40 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 Kong Gateway 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 Kong Gateway queries for multi-turn workflows
Kong Gateway in LangChain
Kong Gateway and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Kong Gateway 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 | 4,000+ 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 Kong Gateway in LangChain
The Kong Gateway 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 40 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
Kong Gateway for LangChain
Every tool call from LangChain to the Kong Gateway MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How can I check if my Kong Gateway instance is running correctly?
You can use the get_status tool. It will return the current status of the Kong node, including database connectivity and server metrics.
Can I list all the plugins currently enabled on my gateway?
Yes! Use the list_plugins tool to retrieve a complete list of all configured plugins across your entire Kong instance.
Is it possible to create a new service and its route through the AI?
Absolutely. You can use create_service to define your upstream and then create_route to specify how traffic should reach that service.
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
Explore More MCP Servers
View all →
Nimbata
12 toolsTrack which marketing campaigns generate phone calls with dynamic number insertion and call attribution analytics.

Contentsquare
10 toolsManage UX analytics via Contentsquare — track site metrics, list demographic segments, audit URL mappings, and export raw data directly from any AI agent.

Smarty
7 toolsEquip your AI with enterprise-grade location intelligence to validate, autocomplete, and extract US or International addresses instantly.

Dexatel
10 toolsEquip your AI agent to send SMS messages, track communications, and manage contacts via the Dexatel API.
