MCP security risks: why MCP servers need controls
MCP lets AI agents call tools and read data through servers that anyone can publish. Each server is code or a service running with your users' access, and the model trusts what those servers tell it. Without controls, that is a new and wide open door.
Next step
AI Agent Blocklist: MCP server packages, processes and domains, so unapproved servers cannot be installed or reached
Part of one list of AI agents, coding agents and agent tools, with a risk grade on every entry and daily updates.
Is MCP a security risk?
The protocol is not the problem; unmanaged use is. The MCP specification defines an authorization model for remote servers and publishes security guidance. Those protect you only if servers and clients follow them.
The risk comes from three facts: servers are third-party code or services, local servers run with the user's rights, and the AI model reads tool descriptions and results that an attacker can shape.
Local servers (stdio)
- Started as a process on the user's machine
- Often installed straight from npm or PyPI on first use
- Can run any command they are configured with
- Reach files, keys and the local network
Remote servers (HTTP)
- A service run by the vendor or a third party
- Receive company data and access tokens
- Depend on correct OAuth handling
- Can change behaviour at any time on their side
MCP security threats, explained for admins
These are the threats described in public research and in the MCP specification's own security guidance. The tags show where each one happens.
Tool poisoning
Hidden instructions in a tool's description. Users rarely see descriptions; the model always does.
Rug pull
A server you approved changes its tools or descriptions later, so the trusted server becomes a harmful one.
Shadowing
One server's description changes how the agent uses another server's tools, without being called itself.
Injection through results
Data a tool returns, such as an issue, email or web page, contains instructions the agent follows.
Malicious packages
A server package built or modified to copy data or run hidden commands, published under a familiar name.
Local command execution
A startup command in a client configuration can run anything. One-click install flows make this easy to miss.
Confused deputy
A proxy server with a static client ID can let an attacker obtain authorization without the user's consent.
Token passthrough
A server accepts tokens not issued to it and passes them on, bypassing controls and audit trails. The specification forbids it.
Over-broad scopes
Tokens granted every scope up front give anyone who obtains one access to everything at once.
MCP risk patterns reported in 2025
Public research in 2025 showed a handful of patterns again and again. We describe the patterns, not products; each one maps to a control further down this page.
Tool poisoning demonstrated
Researchers showed a harmless-looking tool whose hidden description told the agent to read SSH keys and configuration files and send them to the server, while the agent's explanation talked only about the visible task.
Public content, private access
An agent that reads public content, such as an issue, while it holds a token for private repositories can be steered to copy private data into a public place. Narrow tokens prevent this.
Developer tools without authentication
Some tools for testing MCP servers listened on the network without authentication, so a request from outside could launch commands. Keep such tools updated and bound to the local machine.
Command injection in connection helpers
Some helper packages for connecting AI apps to remote MCP servers could be made to run commands by an untrusted server's authorization response. Connect only to servers you have reviewed.
Injected MCP configs
Prompt injection in AI code editors could create a new MCP configuration file, or swap an approved one, and run commands without a fresh prompt. Treat config files as sensitive and review every change.
A look-alike email server
A server package for sending email added a hidden blind copy of every outgoing message to an outside address after several clean releases. Pinned versions and update reviews catch this.
Common claims about MCP security: what is true and what is not
Forum threads are often harsh about MCP. Some of that is fair criticism of how it has been deployed. Here is a plain sorting of the claims.
Who is exposed to MCP risk
MCP started with developers, but it now ships in desktop AI apps and office tools too. Map who has it before you set rules.
Developers
Coding agents with MCP servers for code hosting, databases, cloud consoles and browsers.
Knowledge workers
Desktop AI apps connected to email, calendars, documents and chat through connectors.
Admins of connectors
People who add organisation-wide connectors that every user's assistant then reaches.
Signs of unmanaged MCP use
MCP servers rarely show up in software inventory, because most are started on demand by the AI client. Look for their configuration and their traffic instead.
On devices and in repositories
- .mcp.json files committed to repositories, which give every clone the same servers
- MCP entries in Claude Code's user configuration and in .cursor/mcp.json files
- mcp_servers tables in Codex's config.toml
- Server processes started by npx, uvx or similar runners from an AI client
In logs and admin consoles
- Package proxy requests for MCP server packages you never approved
- Outbound traffic from laptops to MCP services and integration platforms
- Organisation-wide connectors added in AI app admin consoles
- OAuth grants to new apps in your identity provider and SaaS tools
Questions to answer before approving an MCP server
Use these questions for every server a team requests. If you cannot answer one, the server waits.
| Question | Good answer | Warning sign |
|---|---|---|
| Who publishes and maintains it? | The vendor of the system it connects to, or your own team | An unknown account, a fork, or a name close to a known vendor |
| What can its tools do? | Read-only, or narrow writes the task needs | Run commands, send messages or delete data by default |
| Which credentials does it need? | Its own scoped, short-lived token | A personal admin token or a broad API key |
| Where does data go? | Only to the system it connects to | A third-party service in between |
| How do updates arrive? | Pinned versions you upgrade on purpose | Latest version pulled on every start |
Remote connectors in AI apps are MCP too
Many AI apps now offer connectors to email, files and work tools. Several of them are MCP servers behind a friendly name, and an admin can switch them on for everyone at once.
Organisation-wide reach
A connector added by one admin appears in every user's assistant, with each user's own access.
They follow users into tools
Claude Code, for example, fetches claude.ai connectors for signed-in users by default. Admins can switch that off with disableClaudeAiConnectors.
Same review applies
Treat each connector like a server request: who runs it, what it can do and which credentials it uses.
How to control MCP in the clients your staff use
Each AI client has its own MCP controls. Match servers by exact command or URL wherever you can; a server's name is a label a user chooses, not a security control.
| Client | Turn MCP off | Allow only approved servers |
|---|---|---|
| Claude Code | managed-mcp.json with an empty mcpServers object | allowedMcpServers by serverCommand or serverUrl, with allowManagedMcpServersOnly; deniedMcpServers always wins; disableClaudeAiConnectors for claude.ai connectors |
| Codex | An mcp_servers table that is present but empty in requirements.toml | One entry per approved server with an identity matching its command or URL |
| Cursor | MCP Configuration in the Enterprise dashboard | Allowlist by command or URL, tool limits per server, network modes such as Allowlist or Deny all |
| GitHub Copilot | The MCP servers in Copilot policy | An MCP registry URL with Registry only, in public preview |
| VS Code | The ChatMCP policy | ChatAllowedMcpServers, ChatDeniedMcpServers and ChatAllowManagedMcpServersOnly policies |
Six controls that cover most MCP risk
You do not need a new platform to start. These controls use settings you already have, plus a list of what to block.
Inventory
Find MCP configuration files on devices, connectors in your AI apps and server packages in your package proxy logs.
Default deny
Turn MCP off where nobody needs it, and allow only reviewed servers where they do, matched by command or URL.
Pin and review
Pin local server versions. Re-review when a version or a tool description changes.
Least privilege
Give each server its own scoped, short-lived credentials. Never reuse a user's broad token.
Keep approvals on
Do not let users set tool calls to always allow for servers that write, send or delete.
Block the rest
Block unapproved MCP packages and domains at the package proxy, on devices and on the network.
How the AI Agent Blocklist helps with MCP
Allowlists in each client cover the clients you manage. Our list covers the servers themselves, wherever someone tries to install or reach them.
| What we list | Examples from our file | Where you block it |
|---|---|---|
| MCP server packages on npm and PyPI | @browsermcp/mcp, @openai/codex-shell-tool-mcp | Internal package proxies and registries |
| MCP server commands and processes | firecrawl-mcp | Endpoint rules in Intune, Jamf or Defender |
| MCP services and integration platforms | Domains in our MCP servers and integrations category | Firewall, DNS filter, secure web gateway |
| Every entry | Tool name, category, identifier type and risk grade | Block all, or the higher grades first |
Put a list behind your MCP rules
The AI Agent Blocklist includes MCP servers and integrations alongside AI agents, coding agents, AI browsers and agent extensions, updated every day.
From $99 a month for one organisation. Download access is set up within one business day of your order.
See plans Ask a question- MCP server package names for npm and PyPI
- Process names and app identifiers for endpoint rules
- 2,600+ AI agent domains, including MCP services
- Plain, hosts, PAC and firewall list formats
- CSV and JSON with category and risk grade
Ask us or order a plan
Tell us what you need to block and where your rules live. We reply within one business day.
- Files for firewalls, DNS filters, secure web gateways, MDM and browser policies
- Updated every day as new AI browsers, agents and extensions appear
- Plans for one organisation, for MSPs and for product makers, or a hosted filter we run for you
Questions about MCP security
Is MCP a security risk?
What are the main MCP security issues?
What is a malicious MCP server?
Is MCP safe to use at work?
Are MCP servers listed in a directory safe?
How do I control which MCP servers employees use?
Does turning off MCP break AI coding tools?
Can an MCP server send data out without being called?
Claude, Claude Code and claude.ai are trademarks of Anthropic, PBC. Codex is a trademark of OpenAI. Cursor is a trademark of Anysphere, Inc. GitHub and GitHub Copilot are trademarks of GitHub, Inc.
VS Code, Intune and Defender are trademarks of Microsoft Corporation. Jamf is a trademark of Jamf. Browser MCP and Firecrawl are trademarks of their respective owners.
npm is a trademark of npm, Inc. PyPI is a trademark of the Python Software Foundation.
Names are used only to identify the products discussed. AI Agent Blocklist is not affiliated with, sponsored or endorsed by these companies.