Chrome Enterprise Premium MCP Server
OfficialThis MCP server gives an AI agent administrator-level access to inspect and configure Chrome Enterprise Premium (CEP) security, DLP, connectors, browser telemetry, licensing, and knowledge resources.
Discover customer ID, organizational units, managed browser profiles, and browser version counts.
Check CEP subscription status and whether specific users have CEP licenses.
List, inspect, and create DLP rules, including default/starter rule sets.
Create DLP detectors: regex, URL list, and word list detectors.
Check connector policy status and enable Chrome Enterprise connectors (print, paste, file upload/download, real-time URL checks, security events).
Check and enable/disable Security Insights, and run CEP environment health diagnostics.
Check/install the Secure Enterprise Browser (SEB) extension and inspect extension policy status.
Retrieve Chrome activity audit logs for security investigations and rule tuning.
Load built-in Chrome Enterprise Premium knowledge base articles.
Authenticate to Google, check auth status, and clear cached credentials.
Provide health, optimization, and expert-persona prompts for CEP administration.
Provides tools for managing Chrome Enterprise Premium resources, including DLP rules, content detectors, connector policies, browser telemetry, and license management, allowing AI agents to inspect and configure Chrome Enterprise environments.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Chrome Enterprise Premium MCP Server list all DLP rules and their status"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Chrome Enterprise Premium MCP Server
A Model Context Protocol (MCP) server for Chrome Enterprise Premium (CEP). CEP extends Chrome's built-in security with Data Loss Prevention (DLP), real-time threat protection (phishing and malware scanning), and Context-Aware Access controls. This server exposes CEP's DLP rules, content detectors, connector policies, browser telemetry, and license management as MCP tools, so any MCP-compatible AI agent can inspect and configure a Chrome Enterprise environment.
Prerequisites
Before setting up the MCP server, ensure you have the following:
Node.js & npm: Node.js version
20.0.0or higher installed locally.Google Workspace Account:
Any Workspace edition with a Chrome Enterprise Premium license.
An administrator role in the Admin Console. Note that Super Admin is required for DLP features and running full diagnostics, while delegated roles with Chrome Management permissions are sufficient for other tools (see Administrator Role Requirements for details). Standard Workspace accounts (or Google Cloud IAM permissions alone) do not grant access.
OAuth App Trust (if required): If your organization restricts third-party app access, a Super Admin must trust the OAuth client in the Admin Console before you can authenticate.
MCP Client: A compatible MCP host application (such as Gemini CLI, Claude Desktop, Cursor, Windsurf, or VS Code).
Quick start
Get up and running in less than 2 minutes using the bundled Google-managed OAuth client. No repository cloning required!
1. Connect your MCP client
The server uses stdio transport; your MCP client launches it as a child process. Depending on your client, connect the server using one of the following methods:
If you are using the Gemini CLI, you can install this repository directly as an extension with a single command. This automatically configures the MCP connection and loads the built-in AI guidance rules:
gemini extensions install https://github.com/google/chrome-enterprise-premium-mcpFor all other MCP-compatible clients (such as Claude Desktop, Cursor, Windsurf, or VSCode), add this configuration block to your client's settings file (e.g., claude_desktop_config.json or ~/.gemini/settings.json):
{
"mcpServers": {
"cep": {
"command": "npx",
"args": ["-y", "@google/chrome-enterprise-premium-mcp@latest"],
"env": { "GCP_STDIO": "true" }
}
}
}2. Query the agent
Restart your MCP client, then ask the agent to perform a check, for example:
"How can you help me use Chrome Enterprise Premium?"
"How do I set up a rule to block uploads of credit card numbers?"
"List my Chrome Enterprise Premium DLP rules."
Authentication: The first time you run a query that calls a tool requiring authentication, the agent will prompt you to sign in.
Desktop: A browser tab will open automatically on Google's consent screen.
Headless/Remote: If you are on SSH, Cloud Shell, or a container, the agent will provide a consent URL. Open it locally, sign in, and paste the redirect URL back to the agent in the chat.
CLI Fallback: If you prefer to authenticate via the terminal, you can run:
npx @google/chrome-enterprise-premium-mcp auth login
Related MCP server: MCP Google Workspace Server
Security & Blast Radius Warning
This server is an administrator-level interface to Chrome Enterprise Premium. When you connect it to an MCP client, you can use natural-language prompts to:
Create and modify DLP rules and content detectors.
Change connector policies.
Force-install browser extensions onto every managed Chrome browser.
Enable Google Cloud APIs on your project.
An attacker who plants hidden instructions in untrusted inputs—mail, documents, scraped pages, ticket bodies—can hijack the connected MCP client through indirect prompt injection. The attacker can then run those tools without your consent.
To reduce the blast radius:
Connect this server only to MCP clients you trust, on data sources you trust.
Treat every document, message, and webpage you put in front of the agent as untrusted. It might contain hidden instructions.
Pay extra attention to mutating tools (
create_*,update_*,enable_*); they have tenant-wide security impact.Use a dedicated, least-privilege admin account when experimenting.
Workspace Scopes & Permissions
The scope set requested during the "Sign in" consent flow maps directly to the underlying Google APIs needed for the server's tools:
Scope | API | Used for |
| OpenID Connect | Identifies the logged-in admin in startup output |
| Reading and writing connector and extension policies | |
| Telemetry version counts | |
| Listing managed browser profiles | |
| Fetching Chrome activity logs | |
| Organizational Unit hierarchy | |
| Customer ID resolution | |
| CEP subscription and per-user license checks | |
| Managing DLP rules and content detectors (CRUD) | |
| Verifying and enabling required Google Cloud APIs |
OAuth App Trust Required: If your organization restricts third-party app access, a Super Admin must trust the OAuth client in the Admin Console before you can authenticate.
Advanced Authentication Options
For production environments, headless systems, or customized configurations, the server supports alternative auth pathways:
Custom OAuth Client: To run under your own Google Cloud project instead of the default managed one (enabling you to manage your own consent screen and credentials), see Use a Custom OAuth Client.
Headless / SSH Sessions: To authenticate on remote hosts or CI runners without a web browser, see Sign In from a Host Without a Browser.
Hosted Deployments: For Cloud Run, Vertex AI Agent Engine, or service-account automation, see the Authentication Setup Matrix.
Configuration
For environment variables and stdio vs. HTTP transport, see
docs/configuration.md.
Available tools and prompts
Prompts
Prompt | Description |
| Health check of the Chrome Enterprise environment (APIs, DLP, connectors, extensions). |
| Rule-by-rule review with tuning, enforcement, and cleanup recommendations. |
| Manually re-injects the expert persona and rules (useful if the agent loses context). |
Tools
The server exposes tools for reading and managing Chrome Enterprise resources:
Discovery: get customer ID, list org units, count browser versions, list customer profiles
Licensing: check CEP subscription status, check per-user license assignment
DLP: list/create DLP rules, list/create detectors (regex, word list, URL list), create default rule sets
Connectors: get connector policy status, enable Chrome Enterprise connectors
Extensions: check SEB extension status, install SEB extension
Security: get Chrome activity logs, check and enable required APIs
Knowledge: retrieve documentation from the built-in Chrome Enterprise Premium knowledge base
Architecture
The codebase has three layers: API clients in lib/api/ (one interface +
real implementation per Google API), MCP tools and prompts in tools/ and
prompts/, and the server entry point in mcp-server.js. Integration tests
redirect the real API clients at an in-process Express fake under
test/helpers/. For the directory layout, design patterns, and how the test
backends are wired, see docs/architecture.md.
Troubleshooting
For known issues with auth, permissions, Node.js setup, and MCP client
integration (including the /mcp reload tip when CEP tools do not show up
right after restart), see
docs/troubleshooting.md.
FAQ
For license requirements, Workspace edition, service-account auth,
experimental features, and other recurring questions, see
docs/faq.md.
Reporting bugs
If something isn't working:
In Gemini CLI, run
/bugto capture session diagnostics. Attach the generated file to your issue.Run
npm run presubmitand paste the output; this lets maintainers tell environmental problems from real code bugs.Describe what you expected vs. what actually happened, including the exact error message.
Contributing
Contributions are welcome! For local development setup, building, testing, and contributor guidelines, please see CONTRIBUTING.md.
Legal
This repository is provided as a reference implementation that customers can explore and adapt under the Apache 2.0 license. It is not an officially supported Google product.
License: Apache License 2.0
Terms of Service: Terms of Service
Privacy Policy: Privacy Policy
Security: Security Policy
Available Tools
25 toolscep_authA
Sign in to Google for the Chrome Enterprise Premium (CEP) MCP server. Before calling this tool, you MUST warn the user that this will open a browser tab or prompt them to sign in, and ask for their confirmation. Use this tool ONLY for the CEP MCP server. The Google Workspace MCP server has its own separate auth tool—do not use this one for that. Requests the CEP scope set: Admin SDK reports, Chrome browser management, Cloud Identity (DLP), Identity, Licensing, Service Usage. Call with no arguments to start the sign-in. If the response sets nextAction to paste-redirect-url, ask the user to paste the URL the browser was redirected to, then call cep_auth again with that string as the redirectUrl argument.
Inputs: authMethod, redirectUrl. Returns: status, authUrl, message, expiresAt, +1 more
cep_auth_clearA
Clears cached OAuth credentials for the Chrome Enterprise Premium (CEP) MCP server, forcing re-authentication on the next call. Use this tool only for the CEP MCP server; the Google Workspace MCP server has its own separate clear tool.
Inputs: no named parameters. Returns: cleared
cep_auth_statusA
Reports the current OAuth credential status and cached scopes for the Chrome Enterprise Premium (CEP) MCP server. Use this tool only for the CEP MCP server; the Google Workspace MCP server has its own separate status tool.
Inputs: no named parameters. Returns: status
check_cep_subscriptionA
Verifies the current Chrome Enterprise Premium (CEP) license assignments for an organization. This is useful for checking the actual protection state of users.
Inputs: customerId. Returns: isActive, assignments, assignmentCount
check_seb_extension_statusA
Checks if the Secure Enterprise Browser (SEB) extension is force-installed for a given Organizational Unit. The SEB extension is REQUIRED for advanced Chrome Enterprise Premium features like data masking. If not installed, use 'install_seb_extension' to fix it.
Inputs: orgUnitId (required), customerId. Returns: policies, extensionId, isInstalled
check_user_cep_licenseA
Checks if a specific user has a Chrome Enterprise Premium (CEP) license assigned. Use this to verify if an individual user (by email or unique ID) is licensed for CEP features.
Inputs: userId (required). Returns: license, hasLicense
count_browser_versionsA
Counts Chrome browser versions reported by managed devices. Use this for auditing and reporting on the distribution of browser versions across your organization or a specific Organizational Unit.
Inputs: orgUnitId, customerId. Returns: versions
create_chrome_dlp_ruleA
Creates a new Chrome DLP rule for a specific Organizational Unit. Applies browser-level protection (uploads, downloads, printing). For safety reasons, this MCP tool is disabled from creating 'ACTIVE' rules with a 'BLOCK' action. You can create 'INACTIVE' 'BLOCK' rules and enable them later in the UI, or create 'ACTIVE' 'WARN' or 'AUDIT' rules.
To ensure technical accuracy and verify trigger compatibility, you should retrieve the full technical reference using 'get_document' for '11-dlp-rule-reference' before using this tool.
Inputs: action (required), triggers (required), orgUnitId (required), displayName (required), +9 more. Returns: dlpRule
create_default_dlp_rulesA
Creates a "Starter Pack" of default Chrome DLP rules for a specific Organizational Unit. Rules included:
Audit visits to Generative AI sites.
Apply watermarks to sensitive sites (Gmail, Salesforce, Zendesk).
Warn users before pasting content on Generative AI sites (Gemini is excluded from warning).
Inputs: orgUnitId (required), customerId. Returns: failedRules, createdRules, failureCount, successCount
create_regex_detectorA
Creates a new DLP regular expression detector. Detectors are building blocks for DLP rules. After creating a detector, you must reference its resource name in a 'create_chrome_dlp_rule' condition (e.g., using the 'matches_detector' function).
Inputs: expression (required), displayName (required), customerId, description. Returns: detector
create_url_list_detectorA
Creates a new DLP URL list detector. Detectors are building blocks for DLP rules. After creating a detector, you must reference its resource name in a 'create_chrome_dlp_rule' condition (e.g., using the 'matches_detector' function).
Inputs: urls (required), displayName (required), customerId, description. Returns: detector
create_word_list_detectorA
Creates a new DLP word list detector. Detectors are building blocks for DLP rules. After creating a detector, you must reference its resource name in a 'create_chrome_dlp_rule' condition (e.g., using the 'matches_detector' function).
Inputs: words (required), displayName (required), customerId, description. Returns: detector
diagnose_environmentA
Runs a health check of the Chrome Enterprise Premium environment.
By default returns a summary with counts and pre-computed issues — no large arrays. The agent should present these findings to the user.
To drill into detail, pass a 'section' parameter:
"orgUnits" — paginated list of organizational units
"dlpRules" — paginated list of DLP rules with action types
"detectors" — paginated list of content detectors
"browserVersions" — all browser version counts
Use 'limit' and 'offset' for pagination on large datasets.
Inputs: limit, offset, section, customerId. Returns: object
enable_chrome_enterprise_connectorsA
Enables and configures selected Chrome Enterprise connectors (e.g., Print, Paste, File Upload/Download). Use this tool to ACTIVATE security protections. It will ONLY apply changes to connectors that are not already configured. To check current status without modifying, use 'get_connector_policy'.
Inputs: orgUnitId (required), connectors (required), customerId. Returns: connectors
get_chrome_activity_logA
Retrieves audit logs of Chrome browser activity (e.g., login events, policy violations, extension installs). Use this for security investigations, auditing user actions, and to help tune DLP rules.
Inputs: endTime, userKey, eventName, startTime, +2 more. Returns: activities
get_connector_policyA
Retrieves the current configuration for a specific Chrome Enterprise connector or all connectors. Use this to AUDIT or VERIFY settings for features like "printing sensitive data", "real-time URL checks", or "event reporting". Note: The 'enable_chrome_enterprise_connectors' tool can only ACTIVATE connectors that are currently unconfigured. There is currently no tool to MODIFY an already configured connector; these must be updated manually in the Admin Console.
Inputs: orgUnitId (required), policy, customerId. Returns: orgUnitId, configured, connectors, connectorType, +1 more
get_customer_idA
Retrieves the unique Google customer ID for the authenticated account. This ID (often starting with 'C') is required as a parameter for many other Chrome management tools.
Inputs: no named parameters. Returns: language, customerId, customerDomain
get_dlp_ruleA
Retrieves details for a specific Chrome DLP rule by its resource name. The response includes a direct link to the Admin Console where you can view, edit, disable, or delete the rule. Note: The agent itself cannot modify or delete rules.
Inputs: resourceName (required). Returns: dlpRule
get_documentA
Retrieves the full text of one or more knowledge base documents. Pass filename as a single value or an array (bundle). Each entry may be a filename string (e.g. "4-dlp-core-features") or a numeric articleId from a Markdown cross-link. Use the array form to load related articles in a single call.
Knowledge Index
This index is for locating relevant documentation by topic. Document summaries are not a source of truth; for authoritative technical details, exact roles, or procedures, the agent retrieves the content in real-time via 'get_document'.
Filename | Topics Covered | Source |
01-cep-overview | Comprehensive introduction to Chrome Enterprise Premium (CEP). Helps with product evaluation and implementation. Walks through the 5-step checklist: setting up Chrome management, configuring connector policies, verifying the CEP service, setting up DLP rules, and configuring activity alerts. Covers trial terms (60 days, 5,000 users) and manual license assignment. Keywords: $6/user price, trial terms, Licensing, 5-step checklist, manual license assignment, Workspace service settings. | Remote |
02-chrome-deployment-guide | Comprehensive browser deployment and enrollment guide. Use this to perform large-scale MSI/PKG installation via MDM and configure cloud management. Covers how to: deploy the Chrome Enterprise bundle, apply policy templates, use Cloud management enrollment tokens, force-install Endpoint Verification, and perform the two-step unenrollment process. | Remote |
03-ev-troubleshooting | Endpoint Verification (EV) troubleshooting and privacy guide. Helps resolve device posture sync errors and access denial issues. Covers how to: fix OS-level sync failures by investigating Native Helper status, EDR/Antivirus blocks, and firewalls; resolve OS update delays via manual "Sync Now"; and understand privacy boundaries (no browsing history collected). Keywords: Failed to sync, Native messaging host, manual sync, privacy statement, BYOD security. | Remote |
04-dlp-core-features | Guide for configuring DLP triggers (Paste, Print, Upload), screen capture protection, and Enterprise Cache Encryption. Helps protect sensitive data from accidental leaks or exfiltration. Covers how to: enable screenshot blocking on sensitive URLs, manage file scan latency via DelayDeliveryUntilVerdict, and configure Optical Character Recognition (OCR) for images. Keywords: Screen capture protection, Clipboard controls (Paste), Cache encryption, OCR supported types (BMP, GIF, JPEG, PNG, TIF), scan delay. | Remote |
05-evidence-locker | Setup and configuration guide for the Evidence Locker (forensic file storage). Helps secure sensitive data for legal and security investigations. Covers how to: configure the GCS bucket, manage access permissions, and handle unscannable files. Note: DLP more reliably detects password protection on ZIP archives than on PDF or Office documents. Keywords: Evidence Locker, GCS bucket permissions, service account keys, DelayDeliveryUntilVerdict, password reliability (ZIP vs PDF). | Remote |
06-dlp-rule-troubleshooting | DLP troubleshooting and diagnostics guide. Helps resolve rule deployment issues and ensures effective protection against data leaks. Covers how to: verify rule receipt via chrome://policy, confirm CEP license assignment, refine strict rules using "Audit only" mode, investigate client-side logs at chrome://safe-browsing, and analyze server-side log events in the Admin Console. Keywords: chrome://policy, chrome://safe-browsing, audit only mode, license assignment, investigation tool. | Remote |
07-caa-dlp-integration | Context-Aware Access (CAA) and Security Gateway integration guide. Helps protect corporate apps by ensuring only compliant devices gain access. Covers how to: troubleshoot "401 Unauthorized" errors via IAP logs and Access Level definitions, secure native applications using Certificate-Based Access (CBA), and verify Device Trust Connector (Okta) status in chrome://connectors-internals. Keywords: 401 Unauthorized, IAP policy, Security Gateway, BeyondCorp, native app security. | Remote |
08-certificate-based-access | Certificate-Based Access (CBA) and Identity Provider guide. Helps enforce high-assurance access for managed and unmanaged devices. Covers how to: upload Root CA certificates to the Admin Console and configure the "AutoSelectCertificateForUrls" policy for seamless user authentication. Keywords: CBA, Root CA upload, AutoSelectCertificateForUrls, client certificates. | Remote |
09-chrome-log-events | Chrome Reporting Connector and SIEM integration guide. Helps search security event logs in the Admin Console and stream events to SIEMs like Splunk. Covers event descriptions for Threat and Data Protection events, and how to verify local event generation and policy receipt on client machines. Keywords: Chrome log events, Audit & investigation, Threat events, Data Protection events, chrome://policy, chrome://safe-browsing, Splunk integration. | Remote |
10-chrome-policy-management | Chrome policy management and URL filtering guide. Helps control web access and manage policy conflicts. Covers how to: use wildcard syntax—example.com (includes subdomains) vs .example.com (exact host only); give cloud policies precedence via "CloudPolicyOverridesPlatformPolicy"; and bypass Safe Browsing warnings for internal sites using "SafeBrowsingAllowlistDomains". | Remote |
12-security-posture-guide | Internal evaluation criteria the agent uses to assess a Chrome Enterprise Premium environment and recommend next steps. Walks through whether the prerequisites (licenses, connectors, SEB extension) are present, whether DLP rules exist, whether they are tuned, and whether they are enforcing. Covers the telemetry dependency (logs require active rules). For agent-internal use only — do not surface labels or framework names to users. | Local |
15-rule-quality-guidelines | Internal evaluation criteria the agent uses to identify logic flaws and noise in Chrome Enterprise Premium DLP rule JSON. Covers context blindness (missing destination vectors), false negatives from broad file-type exclusions, root-OU over-scoping, low match thresholds that cause false positives, missing compound logic, mixed triggers, disproportionate actions, audit-first deployment, and orphaned rules. For agent-internal use only — do not surface heuristic names or category labels to users. | Local |
16-configurable-timeouts | Guide for configuring timeout deadlines (evaluation time limit) for Data Loss Prevention (DLP) and malware scans, including the paste action. Covers UI navigation paths, Admin privileges required, and background scan behavior. Keywords: Configurable timeouts, evaluation time limit, deep scanning protection settings, Chrome Enterprise Security Services, Chrome Enterprise Premium, scan deadline, paste deadline. | Remote |
21-dlp-limits | DLP content and scanning limits guide. Helps explain why certain files are unscanned or blocked. Covers constraints for file size, text extraction, and spreadsheets. Keywords: 50MB file limit, 10MB text limit, 50,000 cell limit, unscannable files. | Remote |
22-dlp-data-masking | Helps protect sensitive UI data in the browser using data masking. Covers configuration of masking rules and requirements for the Secure Enterprise Browser (SEB) extension. Keywords: Data masking, SEB extension, PII protection, Light/Hard obfuscation. | Remote |
23-insider-risk-monitoring | Insider risk and data loss monitoring guide. Covers how to turn on insider risk monitoring via the 1-click "Monitor data leaks and insider risk" flow, and how to configure the "Data protection insight scanning and report" setting. Explains how this automatically configures Chrome connectors, event logging, and DLP scanning. Keywords: Insider risk, 1-click enablement, Data protection insight scanning, Chrome security event logging, turn off monitoring. | Remote |
24-security-reports | Overview of Chrome security reports in the Admin Console. Helps administrators monitor threat and data protection events. Covers Malware, Unsafe Sites, PII transfers, and high-volume upload/download reports. Keywords: Data protection reports, Threat protection dashboard, security telemetry. | Remote |
27-url-blocklist-format | Detailed technical format for URL blocklist and allowlist filters. Helps with precise web access control. Covers wildcard syntax rules: example.com (matches domain and all subdomains) vs .example.com (matches exact host only). Keywords: wildcard (*), subdomain (.), URL filter syntax, blocklist vs allowlist. | Remote |
28-safe-browsing-allowlists | Helps administrators exempt trusted internal sites from Safe Browsing warnings. Covers how to bypass malware, phishing, and password reuse checks. Keywords: SafeBrowsingAllowlistDomains, trusted domains, bypass warnings. | Remote |
29-admin-privilege-definitions | Reference for administrator privileges required to manage Google Workspace and CEP features in the Admin Console. Helps resolve "Access Denied" errors. Covers privileges for User management, Reports, Security Center, Data Loss Prevention (DLP) rule management, Chrome Management, and Data Security (Context-Aware Access). Keywords: Admin console privileges, Manage DLP rules, Security Center, Service Settings, custom roles. | Remote |
30-ev-device-attributes | Comprehensive list of device posture attributes collected by Endpoint Verification. Helps with creating granular Context-Aware Access (CAA) levels. Covers OS version, serial numbers, disk encryption, and screen lock status. Keywords: Device attributes, postural data, hardware identifiers, encryption status. | Remote |
31-security-insights-data | Guide to querying Chrome Enterprise Security Insights data. Covers methods for retrieving summaries and breakdowns of content transfers and URL visits. Helps with understanding security posture and data movement. | Local |
98-agent-knowledge-addendum | Mandatory Technical "Golden Facts" and operational memory for Chrome Enterprise Premium. Covers Extension IDs for EV and SEB, Windows Certificate Store requirements for CBA, URL filtering syntax rules, and troubleshooting "Something went wrong" errors for Security Insights using specific privileges. Keywords: callobklhcbilhphinckomhgkigmfocg, ekajlcmdfcigmdbphhifahdfjbkciflj, Windows Store requirements, Security Insights Error, Chrome DLP insight setting management, SafeBrowsingAllowlistDomains. | Local |
Inputs: filename (required). Returns: missing, documents
install_seb_extensionA
Force-installs the Secure Enterprise Browser (SEB) extension for a given Organizational Unit. The SEB extension is REQUIRED for advanced Chrome Enterprise Premium features like data masking.
Inputs: orgUnitId (required), customerId. Returns: success, newlyInstalled, alreadyInstalled
list_customer_profilesA
Lists Chrome browser profiles for the customer. These profiles represent managed browser instances and provide details like OS version, platform, and associated user email.
Inputs: customerId. Returns: profiles, totalCount
list_detectorsA
Lists all custom Chrome DLP detectors (URL lists, word lists, or regular expressions). Detectors are used within DLP rules to identify sensitive content. Use this to find the 'policyName' of a detector to include in a rule.
Inputs: no named parameters. Returns: detectors
list_dlp_rulesA
Lists all Chrome DLP rules currently configured in the organization. These rules protect sensitive data by monitoring browser actions like uploads, printing, and screenshots.
Inputs: no named parameters. Returns: dlpRules
list_org_unitsA
Lists the Organizational Units (OUs) for the customer. Use this tool to find the 'orgUnitId' required by most other Chrome management and policy tools. It provides the human-readable path and unique ID for each OU.
Inputs: customerId. Returns: orgUnits
security_insightsA
Manages the enablement status of Chrome Security Insights for a customer. Use this to check, enable, or disable the security insights feature customer-wide.
Inputs: action (required), targetOus, customerId. Returns: insightsState
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 25 tools
Most tools have clear, distinct purposes (auth, DLP rules, detectors, browser management). However, there is slight overlap between some diagnostic tools (diagnose_environment, security_insights) and multiple DLP-related tools (create_chrome_dlp_rule, create_default_dlp_rules, list_dlp_rules, get_dlp_rule) could confuse an agent, though descriptions help differentiate.
All tools follow a consistent verb_noun pattern (e.g., check_cep_subscription, create_chrome_dlp_rule, list_dlp_rules). Even auth tools use cep_auth as a prefix. No mixing of camelCase or other conventions, making it predictable for an agent.
With 25 tools, the server is slightly above the ideal range (3-15). While all tools serve a purpose in Chrome Enterprise Premium management, the count feels a bit heavy, especially with many DLP and detector tools. Still, it remains manageable and not overly bloated.
The tool surface covers core operations like listing, creating, and checking licenses, but there are notable gaps: no tools to update or delete DLP rules, and no OU management beyond listing. Agents will hit dead ends when trying to modify or remove existing configurations.
Maintenance
Related MCP Connectors
The Google GKE MCP server is a managed Model Context Protocol server that provides AI applications with tools to manage Google Kubernetes Engine (GKE) clusters and Kubernetes resources. It exposes a structured, discoverable interface that allows AI agents to interact with GKE and Kubernetes APIs, enabling them to inspect cluster configurations, retrieve Kubernetes resource YAMLs, monitor operations like cluster upgrades, diagnose issues, and optimize costs—all without needing to parse text output or use complex kubectl commands.
The Google Compute Engine MCP server is a fully-managed Model Context Protocol server that provides tools to manage Google Compute Engine resources through AI agents. It enables capabilities including instance management (creating, starting, stopping, resetting, listing), disk management, handling instance templates and group managers, viewing machine and accelerator types, managing images, and accessing reservation and commitment information. The server operates as a zero-deployment, enterprise-grade endpoint at https://compute.googleapis.com/mcp with built-in IAM-based security.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
The Mercado Pago MCP Server implements the Model Context Protocol to provide AI agents and LLMs with access to Mercado Pago's APIs and tools within compatible development environments. It acts as an intermediary that translates Mercado Pago resources into executable functions (tools) that AI applications can invoke to perform actions and automate flows. The server simplifies integration, enables using documentation to implement or improve code, and optimizes operations through natural language interactions without manual implementations.
Related MCP Servers
- AlicenseBqualityDmaintenanceA Model Context Protocol server that enables AI assistants like Claude to interact with Google Cloud Platform environments through natural language, allowing users to query and manage GCP resources during conversations.9289 npm199MIT
- AlicenseAqualityDmaintenanceA Model Context Protocol server that enables AI agents to interact with Google Workspace services including Drive, Docs, and Sheets through natural language commands.8MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server that enables AI agents to control a real Google Chrome instance using specific user profiles, cookies, and extensions. It provides 18 tools for browser navigation, element interaction, and page inspection via the Chrome DevTools Protocol.MIT
- AlicenseBqualityDmaintenanceAn MCP server that provides AI models with full browser automation capabilities through Chrome. It enables navigation, interaction, screenshots, and complete DevTools access by bridging AI clients with a companion Chrome extension.993 npm3Apache 2.0