MCP security checklist

MCP security checklist: audit, harden and govern the MCP servers your staff use

MCP servers give AI agents hands: they read mail, query databases and run commands with real tokens. Most companies have more of them than they think, and none were reviewed. Work through these checks in order.

Eight areas, 40 checks

Inventory5
Approval and allowlist5
Identity and tokens5
Transport and network5
Tool review5
Runtime limits5
Logging and audit5
Incident response5

Next step

AI Agent Blocklist: the MCP part of your checklist, done daily

MCP server domains, MCP packages and MCP bridge extensions in one list for firewalls, DNS filters and device policies.

From $99 a month for one organisation

Why MCP needs its own security checklist

The Model Context Protocol is the plug that connects an AI agent to tools and data. It is simple to install, which is why it spread so fast, and it sits outside most existing reviews. Six problems come up in almost every MCP security audit.

Shadow servers

Developers add servers from directories in seconds. Nobody in IT knows they exist or what they can reach.

Broad tokens

Servers run with personal access tokens or service keys that can read far more than the task needs.

Hidden instructions

Text in a tool description, a ticket or a web page can steer the agent to read files or send data.

Supply chain

A server is a package. A new version can change behaviour after you approved the old one.

Local code execution

Local servers start as processes on the laptop with the user's rights and reach whatever the user can reach.

No audit trail

Tool calls often happen without a log you can search, so an incident cannot be traced afterwards.

The 2025 patterns behind the checks

Each check below answers a pattern that public research showed in 2025. We describe the mechanism only, at the level a defender needs, and never the products involved.

  1. 2025

    Tool poisoning named. Researchers showed that hidden text in a tool description can instruct the agent, and that a server can change its descriptions after the user approved them.

  2. 2025

    Private data exposed through an issue tracker. A planted issue asked an agent to read private repositories through an MCP server and publish them. The token was broader than the task needed.

  3. 2025

    Developer tools that could run commands. Some MCP debugging tools and client proxy packages could be made to run commands by a request or server from outside. Keep such tools updated and bound to the local machine.

  4. 2025

    Database secrets copied into a support ticket. An agent with a broad database role read hidden instructions in a ticket and pasted private token data into the thread.

  5. 2025

    Servers open on the internet. Researchers found MCP servers reachable from the internet that listed their tools to anyone, without any authentication. Check that every server you run requires sign-in.

  6. 2025

    A look-alike server on a package registry. A mail server package added one line in a new version that copied every outgoing email to an outside address. Pinned versions and update reviews catch this.

The MCP security checklist

Forty checks in eight groups. Work top to bottom: you cannot approve what you have not found, and you cannot audit what you do not log. Copy it into your own wiki or ticket template.

1

Inventory: find every MCP server

An MCP security audit starts here
  • Search managed devices for MCP config files of each AI client in use, such as .mcp.json in projects
  • List installed MCP packages and CLIs, for example @smithery/cli or context7-mcp
  • Find MCP bridge extensions in browsers, such as Browser MCP bjfgambnhccakkhmkepdoekmckoijdlc
  • Pull DNS and proxy logs for hosted MCP endpoints and MCP directories
  • Ask each team lead which connectors their AI accounts use, then compare answers with the logs
2

Approval and allowlist

Only named servers, each with an owner
  • Keep one approved list with server name, version, source, owner and review date
  • Enforce it through each client's managed settings, not a wiki page (see our MCP allowlist guide)
  • Turn off automatic approval of project-level server files in coding tools
  • Block MCP directories and hosted servers that are not on the list at the network
  • Write down who can approve a new server and how fast they answer
3

Identity and tokens

The token decides the damage
  • Give each server its own token with the smallest scope that works
  • No personal admin tokens in MCP configs, and no tokens in shared project files
  • Prefer remote servers that use OAuth sign-in over pasted long-lived keys
  • Check that servers never pass the user's token through to other services
  • Set token expiry and rotate after every staff change in the owning team
4

Transport and network

Know what crosses the wire
  • Self-hosted HTTP servers listen on localhost or behind authentication, never open
  • Require TLS for every remote server
  • Retire servers still using the deprecated HTTP plus SSE transport
  • Block unapproved MCP domains at the firewall or DNS filter (see AI at the firewall)
  • Limit which internal hosts a server can reach, to avoid request forgery into your network
5

Tool review

Read what the model reads
  • Read every tool description before approval and look for instructions aimed at the model
  • Pin server versions and re-review on every update
  • Disable tools you do not need, especially write, delete and send tools
  • Check for tool names that shadow tools of another server
  • Prefer servers from the vendor of the system they connect to
6

Runtime limits

Contain what a server can do
  • Keep human approval on for tools that write, send, pay or delete
  • Run local servers in a container or sandbox where the client supports it
  • Never give a server access to the home folder, SSH keys or cloud credentials
  • Separate servers that read untrusted content from servers that can send data out
  • Block coding agents' "skip all permissions" modes in managed settings
7

Logging and audit

Make tool calls searchable
  • Log every tool call with user, server, tool, time and result
  • Send client and gateway logs to your SIEM
  • Alert on new MCP domains and new MCP packages on devices
  • Review the approved list every quarter and remove unused servers
  • Run the inventory again each month and diff it against the list
8

Incident response

Have the steps ready
  • A runbook to revoke all tokens of one server in minutes
  • A way to remove a server from every device through MDM
  • A network block you can push for one MCP domain right away
  • Contacts at the server's maintainer or vendor
  • A list of data each server could reach, ready for a breach assessment

MCP security hardening: the managed setting in each client

Checks 2 and 6 depend on settings users cannot change. Each AI client has its own. This table lists the controls we verified in each vendor's documentation; menus change, so check the current admin console before you roll out.

ClientAllow only approved serversTurn MCP offWhere it is enforced
Claude CodeallowedMcpServers and deniedMcpServers, matched by name, command or URLmanaged-mcp.json with no serversSystem folder, device management, or the Claude admin console
Codexmcp_servers entries with an identity (command or URL)Empty mcp_servers sectionrequirements.toml or macOS device management
VS Code with CopilotChatAllowedMcpServers policy, or GitHub's MCP allowlistChatMCP policy set to noneGroup Policy, macOS profile, Linux policy file, GitHub settings
CursorTeam MCP allowlist with commands and URLsAllowlist with no entriesTeam settings on the Enterprise plan
Gemini CLImcp.allowed and mcp.excludedAdmin MCP setting in system settingsSystem settings file that overrides users
Claude DesktopDesktop extension allowlistisLocalDevMcpEnabled set to falseDevice policy or organisation settings
JetBrains AI AssistantMCP servers chosen per profileUsers not allowed to add serversIDE Services AI Enterprise settings
Matching by server name alone is weak: a user can give any server an approved name. Where the client supports it, match by command or URL. Step-by-step instructions are on our MCP allowlist page and on the pages for Claude Code and Cursor.

The specification's security topics, turned into admin actions

The MCP specification, first published by Anthropic in November 2024, has a Security Best Practices page. It is written for people who build servers and clients. This table maps its topics to what an admin can check.

Topic in the specificationWhat it meansWhat you check
Confused deputy problemA proxy server reuses its own consent to act for a different clientProxy servers ask for consent per client; no shared approvals
Token passthroughA server forwards a token it was not issued forServers you approve validate tokens and never pass them on
Server-side request forgeryA malicious server makes the client fetch internal addressesClients and gateways cannot reach internal metadata or admin hosts
Session or state handle hijackingSomeone reuses an identifier to inject into another user's workServers bind identifiers to the user and use random values
Local MCP server compromiseA local server runs harmful commands on the deviceLocal servers need explicit approval and run with limited rights
Authorization URL validationA sign-in URL from a server is used to run code or phishClients are on versions that validate sign-in URLs
Scope minimisationServers ask for broad scopes up frontTokens start narrow and grow only on request
Authorization in MCP is based on OAuth 2.1. Since the June 2025 revision, servers must check that each token was issued for them. The specification is revised often, so check the current version when you review a server.

MCP security policy: clauses to put in writing

A policy gives your controls a reason people can read. These clauses fit inside an existing acceptable use policy. Our AI agent acceptable use policy page has the wider template.

Approved servers only

Staff may connect AI tools only to MCP servers on the approved list. Requests go to the named approver.

Enforced by managed settings

No secrets in configs

Tokens and keys for MCP servers live in the secret store, never in project files or chat.

Checked in code review

Least privilege

Each server gets its own token with the smallest scope that works, with an expiry date.

Checked at approval

Human approval for actions

Tools that send, pay, delete or publish need a person to confirm each call.

Enforced by client settings

Logging

Tool calls are logged centrally and kept for the same period as other security logs.

Checked each quarter

Review and removal

Approved servers are reviewed each quarter and on every version change. Unused servers are removed.

Owned by the server owner

MCP security governance: who owns what

MCP touches engineering, IT and security at once, so checks fall between teams. Name an owner for each area before the first audit.

Security

  • Owns the policy and the approved list
  • Reviews new servers
  • Runs the quarterly audit

IT and endpoint

  • Pushes managed settings
  • Runs device inventory
  • Removes unapproved servers

Network

  • Loads the block list
  • Watches DNS and proxy logs
  • Pushes emergency blocks

Engineering

  • Proposes servers with a reason
  • Keeps tokens narrow
  • Owns each approved server
Recent public guidance points the same way. In December 2025 OWASP published a Top 10 for agentic applications, and in 2026 national cyber security agencies from several countries issued joint guidance on careful adoption of agentic AI services.

How we help with the blocking part of the checklist

Several checks need a list of what MCP looks like from the outside: domains, packages and extensions. That list changes every day, and it is the part we maintain for you.

Network

  • Domains of hosted MCP servers and integrations
  • MCP directories such as smithery.ai and glama.ai
  • Firewall, DNS filter, hosts and PAC formats

Devices

  • MCP packages and CLIs with their package names
  • Process names to search for in inventory
  • Desktop agent apps with bundle and package IDs

Browsers

  • Extension IDs of MCP bridge and agent extensions
  • Ready block lists for Chrome and Edge policies
  • Risk grade on every entry, Low to Severe
Use the list for checks 1, 2, 4 and 7: inventory, network blocks and alerts. For the settings inside each client, see how to block MCP servers and how to disable MCP servers in Claude Code, Codex and VS Code. The wider risk picture is on MCP security risks.

Keep the MCP checks current without the manual work

New MCP servers, packages and bridge extensions appear every day. The AI Agent Blocklist adds them as they appear, and we set up your download access within one business day of your order.

  • 2,600+ AI agent domains, MCP servers included
  • 5,300+ identifiers: extensions, apps, packages, processes
  • CSV and JSON with category and risk grade
  • Firewall, DNS, hosts, PAC and browser policy files
  • Updated every day

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

We use your details only to answer you. No newsletters.

MCP security questions

What should an MCP security audit cover?

Four things: which MCP servers exist on your devices and in your accounts, which of them are approved, what each server can reach with its tokens, and whether tool calls are logged.

Start with an inventory from devices and network logs, then compare it with your approved list.

What are the MCP security best practices in the specification?

The MCP specification has a Security Best Practices page. Its topics include the confused deputy problem, token passthrough, server-side request forgery, session or state handle hijacking, local server compromise, authorization URL validation and scope minimisation.

Most of it is aimed at people who build servers and clients. The table above turns it into admin checks.

What is MCP tool poisoning?

Tool poisoning hides instructions in a tool's description. The model reads the description, the user usually does not, and the hidden text can tell the agent to read files or send data.

Researchers named it in April 2025. Review tool descriptions before approval and pin versions so a description cannot change silently.

Should we allow remote MCP servers or only local ones?

Both carry risk. Local servers run code on the laptop with the user's rights. Remote servers receive data and tokens over the internet.

Allow only named servers of either kind, and block unapproved hosted MCP endpoints and directories at the firewall or DNS filter.

How do we stop staff adding unapproved MCP servers?

Use the managed settings of each MCP client to allow only approved servers, block hosted MCP domains at the network, and block MCP bridge extensions in the browser. Check devices for MCP packages and config files each month.

Can we put this MCP security checklist in our own wiki or GitHub repository?

Yes. Copy the checks into your internal wiki, repository or ticket template and adapt the owners and review dates to your teams.

How often should approved MCP servers be reviewed?

At least every quarter and on every version change. Re-check the tool descriptions, the token scopes and the owner. Remove servers nobody has used for 90 days.

Anthropic, Claude, Claude Code and Claude Desktop are trademarks of Anthropic, PBC. Codex is a trademark of OpenAI. Cursor is a trademark of Anysphere, Inc. Gemini and Chrome are trademarks of Google LLC. GitHub and GitHub Copilot are trademarks of GitHub, Inc.

Microsoft, VS Code and Edge are trademarks of Microsoft Corporation. JetBrains is a trademark of JetBrains s.r.o. Smithery, Glama, Browser MCP and Context7 are trademarks of their respective owners. OWASP is a trademark of the OWASP Foundation.

Names are used only to identify the products discussed. AI Agent Blocklist is not affiliated with, sponsored or endorsed by these companies.