Services How we work Industries Work About Blog Book a call

MCP security:
what to check before you connect a third-party MCP server

MCP server security in practice: the risks named by the MCP spec, OWASP and Anthropic, a checklist to vet a server, and the settings that limit damage.

risks in OWASP's MCP Top 10, still in beta
10
any connector you add to Claude by URL, in Anthropic's words
Unverified
places Claude Code can store an MCP server's configuration
3
inbound firewall ports an MCP tunnel needs to reach a private server
0
On this page

New MCP servers arrive every week. A vendor ships one, a teammate finds one on GitHub, and connecting it to Claude takes a URL and a click. That is the point of the Model Context Protocol: any tool, one standard. It is also the risk. An MCP server gives an AI agent tools that can read your data, change it and act on your behalf, and the server decides what those tools say they do. This guide covers what to check before you connect one, drawn from the MCP specification's own security guidance, OWASP's MCP Top 10 and Anthropic's documentation.

Every risk and setting below is checked against the MCP Security Best Practices, the OWASP MCP Top 10 and Anthropic's documentation, linked in each section, as at November 18, 2026.

Five questions to ask before connecting an MCP server. Who runs it: local or remote, a named owner, a security contact, a pinned version. What can it reach: the fewest scopes, read-only first, no admin account, where data goes. What does it tell the model: tool descriptions and returned content are both untrusted text the model reads. What runs unasked: write, send and delete tools need approval, unused tools are Blocked, Always allow is rare. How to turn it off: one switch, a key you can revoke, tool calls logged, an owner on call. A strip below states the rule: trust is earned by the server, the riskiest calls wait for a person, and the agent uses credentials by name or a private server holds them
Our checklist for vetting an MCP server, drawn from the MCP specification, OWASP's MCP Top 10 and Anthropic's documentation as at November 18, 2026.

At a glance

RiskWhere it comes fromWhat to check
Tool poisoning and prompt injectionTool descriptions and tool results the model readsWho wrote the server, and which tools can act without approval
Over-broad tokensScopes granted up frontThe scopes on the consent screen, and the account behind them
Code running on your machineLocal servers started by a commandThe exact command, and what it can reach
Tools that change laterUpdates after you approved the serverA pinned version, and who reviews updates
Data leaving the organizationTool calls that send content outWhat each tool sends, and to where
No record of what happenedMissing logsWhether tool calls are logged and kept

1. Is MCP safe? What a server can actually do

MCP itself is a protocol, so "is MCP safe" really asks whether a particular server, with particular settings, is safe. Anthropic's answer for Claude is direct: a connector you add by URL connects Claude to an unverified service, and a remote MCP server gives Claude tools that can read data, create, modify or delete it, and take actions on your behalf.

The MCP specification puts the person in charge. Its tools page says there should always be a human in the loop with the ability to deny tool invocations, that clients must treat tool annotations as untrusted unless they come from trusted servers, and that clients should show tool inputs to the user before calling the server, to avoid data leaving by accident. Those three lines are the core of MCP server security: trust is earned by the server, not assumed, and the riskiest calls wait for a person.

2. MCP server risks: the six to know

Tool poisoning and prompt injection. A tool's description is text the model reads. A malicious server can hide instructions there, and OWASP lists this as MCP03, Tool Poisoning. Anthropic's custom connector guidance warns that malicious MCP servers may include hidden instructions that try to make Claude perform unintended actions. Returned content carries the same risk: Claude Code's MCP documentation notes that servers which fetch external content can expose you to prompt injection.

Tokens with more scope than the job needs. The specification's section on scope minimization describes the failure plainly: a token carrying broad scopes such as files:*, db:* or admin:*, granted up front, turns one leaked token into access to everything. OWASP lists the same pattern as MCP02, Privilege Escalation via Scope Creep, beside MCP01, Token Mismanagement and Secret Exposure.

A local server runs code as you. A local MCP server is a program started on your machine. The specification's section on local server compromise lists what goes wrong: a malicious startup command in a configuration, a malicious payload inside the server, or an insecure server left listening on localhost. It asks clients to show the exact command before running it and recommends running servers in a sandbox with minimal privileges.

Tools that change after you approved them. Anthropic tells users to monitor changes in tool behavior, because server developers may update it unexpectedly. A server you vetted last month is not the server you run today unless the version is pinned. OWASP's MCP04 covers the supply chain side.

Data leaving your organization. Every tool call can send content somewhere. OWASP's MCP10, Context Injection and Over-Sharing, covers the case where more context goes to a tool than it needs.

No record of what happened. OWASP's MCP08 is Lack of Audit and Telemetry. The specification's tools page says clients should log tool usage for audit purposes. Without logs, an incident is a guess.

For teams that build servers, the specification adds two rules worth knowing by name: a server must not accept tokens that were not issued to it (token passthrough), and a proxy server must get consent per client (the confused deputy problem). Ask any vendor whether their server follows both.

3. MCP server security checklist: vet before you connect

QuestionA good answerA red flag
Who runs it?A named organization you already trust, with a security contactAn unknown author, or no way to report a problem
Local or remote?You know which, and whyA local server that downloads and runs code you have not read
What does it ask for?The fewest scopes the job needs, read-only where possibleOmnibus scopes, or an admin account behind the token
Which tools can write or send?Few, and each needs approvalDelete, send or pay tools set to run without asking
Which version runs?Pinned, with updates reviewedAlways the latest, pulled at start-up
Where does data go?Documented, inside your agreed providersUnclear, or "we may use it to improve the service"
Is it logged?Tool calls are logged and keptNothing you can see
How do you turn it off?One switch, and a credential you can revokeShared keys nobody can rotate

A server that fails two of these is not ready for work data. A server that fails the first one is not ready for any.

4. Settings that limit the damage

Vetting decides what you connect. Settings decide what a connected server can do, and they are where a mistake gets caught.

In Claude (web, desktop and mobile). On Team and Enterprise plans, an Owner adds custom connectors for the organization (on Enterprise, also a member whose custom role allows it), and members then sign in with their own accounts. Members can turn a connector on or off for each conversation from the + menu, and set any single tool to Blocked under Customize → Connectors. Anthropic's advice is to click Always allow only for trusted servers. We covered the organization-wide connector settings in Claude connectors on by default, and the same controls carry into the new unified Claude experience.

In Claude Code. A server can be configured in one of three scopes: local and user, stored in ~/.claude.json, or project, stored in .mcp.json and shared through version control. Claude Code asks for approval before using project-scoped servers in an interactive session, and a cloned repository cannot approve its own servers. One catch: the documentation notes that in claude -p runs and Agent SDK sessions it cannot show that prompt and loads project-scoped servers without asking, so headless runs need the same vetting up front. For a whole organization, managed MCP settings support allowedMcpServers and deniedMcpServers lists.

For servers inside your network. Claude Code runs on the engineer's machine, so it reaches what that machine reaches. Connectors in claude.ai are called from Anthropic's side. For those, Anthropic's MCP tunnels open an outbound-only connection from your network, so the server needs no public endpoint and the firewall needs no inbound rules. As at November 18, 2026 they are a research preview for Enterprise organizations by request, and Anthropic still asks you to require OAuth on each server and limit it to the tools it needs.

5. How to turn an MCP server off

Decide this before you need it. In Claude, remove a connector under Customize → Connectors, or Organization settings → Connectors for an Owner, and revoke its access in the third-party service too. In Claude Code, toggle the server off in the /mcp panel, which keeps its configuration, or run claude mcp remove <name>. Then rotate any credential the server held. If you find a malicious server, Anthropic asks you to report it to its Bug Bounty Program.

MCP security at AskQuorum AI: how we connect servers

We use MCP servers every day, so this is how our own setup works, not advice from a distance.

  • We keep the list short. Our Claude Code setup connects a short list of servers for browser testing, documentation lookup and a map of the codebase, plus plugins from Anthropic's own marketplace.
  • Credentials are scoped to the engagement. Each project gets its own credentials, nothing is shared across projects, and access is revoked when the engagement ends, as our security page sets out.
  • Agents use secrets by name, never by value. A wrapper loads a secret into the one command that needs it and masks the output, so neither the model nor a saved approval ever holds the value. We explained the full setup, and the stores it works with, in Claude Code security: how we keep secrets out of the session.
  • For the most sensitive systems, the credential stays on the server. A private MCP server on the company network holds the credential and does the work. The agent calls a narrow tool, such as a read-only query on staging, and sees the result, never the secret.
  • A pasted credential is stopped. Hooks withhold a password or key pasted into the conversation before it reaches the model, and block a known secret from going into a command or a committed file.

The limits are the same as anywhere: a hook blocks the secrets it knows, and an engineer still reviews what an agent changes before it merges. If you want these rules on your own team's agents, or a private MCP server that connects Claude to a system without handing it the keys, that is part of our AI consulting and AI feature integration work.

The checklist

  1. List every connected MCP server in Claude and in each Claude Code project.
  2. Name an owner for each, and remove the ones without one.
  3. Check scopes on each consent screen; prefer read-only.
  4. Set write, send and delete tools to need approval, and block unused tools.
  5. Pin versions, and review updates before they run.
  6. Keep credentials out of the agent: by name, from a vault, or on a private server.
  7. Turn on logging for tool calls, and write down how to switch each server off.

If you are also reviewing what reaches the agent's commands, read how Claude Code secrets leak through settings.local.json in the same sitting: both decide what leaves your organization without anyone choosing it.

Common questions

The work of making sure a Model Context Protocol server, which gives an AI agent tools to read data and take actions, cannot be used to leak data, run unwanted commands or act with more access than it needs. It covers who runs the server, what credentials and scopes it holds, what its tool descriptions and results can tell the model, and what the client lets the model do without asking.

The protocol is a way to connect tools; whether a connection is safe depends on the server and the settings around it. Anthropic calls any connector added to Claude by URL an unverified service, and tells users to connect only to servers from trusted organizations, review permission scopes and watch for prompt injection. A vetted server with narrow scopes and approvals on its write tools is a reasonable risk; an unknown server with broad tokens is not.

An attack where a server hides instructions in a tool's description or other metadata. The model reads that text as context and may follow it, even though a person never sees it. OWASP lists it as MCP03 in its MCP Top 10. Anthropic's guidance warns that malicious MCP servers may include hidden instructions that try to make Claude perform unintended actions.

Prompt injection through tool descriptions and returned content, tokens with broader scopes than the job needs, a local server running code with your user's privileges, a server whose tools change after you approved them, data leaving your organization through tool calls, and too little logging to tell what happened. The MCP specification's Security Best Practices page and the OWASP MCP Top 10 cover each.

In Claude, open Customize, Connectors, select the connector and set that tool's permission to Blocked. You can also turn a connector off for a single conversation from the + menu. In Claude Code, toggle the server off in the /mcp panel, or remove it with claude mcp remove followed by the server name.

Claude Code runs on your machine, so it can reach a server your machine can reach. Connectors in claude.ai are called from Anthropic's side, so a private server needs a public endpoint or an MCP tunnel. Anthropic's MCP tunnels open an outbound-only connection from your network and need no inbound firewall rules; as at November 18, 2026 they are a research preview for Enterprise organizations by request.

We connect only servers we have checked, with credentials scoped to the engagement and revoked when it ends. Agents use secrets by name and never see the values, and where a system matters most we put the credential in a private MCP server on the client's network, so the agent sees results, not secrets. Hooks stop a pasted credential before it reaches the model.

Law and guidance as at 18 November 2026. This is general information, not legal advice.

Connecting Claude to your own systems?

We vet the MCP servers a team wants to use, set the scopes, approvals and secrets around them, and build private MCP servers that keep credentials inside your network. Tell us what you want Claude to reach and we will tell you what to check first.