MCP in the Enterprise: Governing What AI Agents Can Reach
The Model Context Protocol is how AI agents reach your systems. It is what makes agents useful, and it is also the fastest way to give software you did not write access to data you care about. Here is what MCP is, the risks to plan for, and how a gateway such as Kong lets you put agents into production with confidence.
MCP is an open protocol that lets AI agents discover and call tools and data in your systems. Treat every MCP server as a new privileged integration: keep an inventory, authorise per user and per tool, route calls through a control point, and log every one. Kong does that in the same gateway that already governs your APIs and AI model traffic, which is the quickest way to get agents into production safely.
What MCP is
MCP standardises how an AI application connects to the outside world. An MCP client runs inside the assistant or agent. An MCP server exposes tools, such as "create a ticket" or "look up an order", and resources, such as documents or records, that the client can discover and call. Before MCP, every one of those connections was bespoke. Now one server can serve many agents, and one agent can use many servers. The current specification is version 2026-07-28. MCP specification, version 2026-07-28
Servers come in two shapes. Remote servers run as services over HTTP, like any other API. Local servers run on the user's own machine and talk to the agent directly. The distinction matters for security, as the next section shows.
What the specification gives you, and what it does not
The authorisation part of the specification is sound, and built on established OAuth standards. For remote servers over HTTP it requires that:
- authorisation is based on OAuth 2.1, with the MCP server acting as a protected resource;
- clients state which server a token is for, and servers check that each token was issued specifically for them;
- servers do not accept, or pass through, tokens meant for anything else, which closes off the "confused deputy" problem where a server is tricked into acting with someone else's authority;
- clients ask only for the permissions an operation needs, and step up to more when a server asks, rather than taking everything up front.
Two things limit how much comfort that gives. First, authorisation is optional in the specification. A server can be built without it and still be a valid MCP server. Second, local servers are expected to take credentials from their environment rather than follow the OAuth flow, which in practice often means long lived tokens sitting on developer laptops. MCP authorization specification
An agent with a tool is a user with a script. Whatever an agent is allowed to do, a well crafted prompt hidden in an email, a web page or a document can ask it to do. Design permissions on the assumption that, at some point, the agent will be instructed by someone who is not you.
The risks to plan for
- Over privileged access. Agents connected with broad administrative credentials because it was quicker, so every tool call runs with far more authority than the task needs.
- Shadow MCP servers. Servers stood up by teams or individuals that nobody in security knows exist, and so nobody monitors.
- Tool poisoning and prompt injection. Malicious instructions planted in a tool's description or in the content a tool returns, which the model then follows.
- Credential sprawl. Each server holding its own secrets in its own configuration, with no central rotation or revocation.
- Chained exfiltration. One tool reads sensitive data and another sends it somewhere, each step individually permitted.
Source: Coalition for Secure AI, MCP security paper.
Controls to put in place first
- An inventory and an approved list. Know which MCP servers exist, who owns each one, what it can reach and which agents may use it. Anything not on the list does not get production credentials.
- Identity that follows the user. Agents should act with the permissions of the person they are acting for, scoped to the task, not with a shared service account that can do everything.
- A control point in front of the servers. Route MCP traffic through a gateway that handles authentication centrally, applies access rules per tool, rate limits calls and logs every one. Kong does this in the same runtime as your APIs and AI models, so agents get one front door and security gets one set of logs. Kong AI Gateway documentation.
- Read separated from write. Start with read only tools. Where a tool changes something, such as a payment, a record or an email to a customer, require confirmation from a person.
- Untrusted input stays untrusted. Treat tool descriptions and tool output the way you treat anything from the internet. Review third party servers before approving them, and pin the version you reviewed.
- Logs where security can see them. Send tool call logs to the same monitoring and security tooling as everything else, with enough detail to reconstruct what an agent did and on whose behalf.
- A rule for local servers. Decide whether local MCP servers are allowed on managed devices, and if so, which ones and with what credentials.
Your agents, your APIs and your AI models governed in one gateway. Kong puts MCP tool control in the same runtime as your API and AI model traffic, with gateways that run in your own data centres, any cloud or Kong's managed infrastructure. Security gets one place to authenticate, authorise and log everything an agent can reach.
Where to start
The fastest route to production is not to build lots of bespoke MCP servers. Most organisations already have APIs for the systems agents need, with authentication and rate limits in place. Kong can publish those existing APIs as MCP tools, so the agent gets a tool and security keeps the controls it already trusts. Pick one read only use case, expose two or three tools through the gateway, log everything, and expand from there with confidence.
MCP governance sits alongside the wider job of controlling AI traffic. Our guide to AI gateways covers the model side: cost, routing and data protection, all in the same Kong gateway.
How we help
We design and implement the control layer for AI agents on Kong: the inventory of MCP servers, the identity model so agents act with the right permissions, the gateway in front of every server, existing APIs published as governed tools, and logging into your security tooling. We work alongside your security and integration teams, so agents go into production with sign off rather than workarounds.
Ready to put AI agents into production safely?
Tell us which agents and systems are involved and where you are with security sign off. We will come back within one working day with how Kong would govern your agents and what a first phase looks like. We design and implement it end to end.
Prefer email? Reach us directly at hello@c4cgroup.co.uk.
Frequently asked questions
Is MCP secure?
MCP is secure when it is deployed well. Its authorisation specification is built on OAuth 2.1 and requires servers to check that tokens were issued for them and not to pass other tokens through. Because authorisation is optional in the specification and local servers rely on credentials in their environment, the safest approach is to route every MCP call through a gateway such as Kong, which enforces authentication, per tool access and logging centrally.
Do we need an MCP gateway?
Yes, as soon as more than a handful of MCP servers are in use. A gateway in front of them is the simplest way to centralise authentication, control which agent can call which tool, and log every call. Kong includes MCP control in the same gateway as its API and AI model controls, so it is one platform rather than another product to buy.
Can we expose our existing APIs as MCP tools?
Yes. Kong publishes existing REST APIs as MCP tools, with the gateway’s own policies applied to every call. That is the safest starting point, because the APIs already have authentication, rate limits and owners, and the gateway keeps those controls in place.
Who should own MCP in the organisation?
Usually the team that owns API management or integration, working with security. MCP servers are integrations with privileged access, so they need an owner, a lifecycle and a review process like any other integration, not just the team that wanted the agent.
Can C4C implement MCP governance for us?
Yes. C4C Group designs and implements MCP governance on Kong, including the server inventory, identity and per tool access, existing APIs published as governed tools, and logging into your security tooling.
What is a shadow MCP server?
An MCP server running without the knowledge of security or IT, often set up by a team or individual to connect an agent to a system quickly. Because nobody knows it exists, nobody monitors it, rotates its credentials or reviews what it can reach.