google-ads-mcp
OfficialThis MCP server lets LLMs/agents query and manage Google Ads accounts, with guarded mutations and discovery resources.
Query Google Ads data using GAQL via
search_searchwith fields, conditions, ordering, and limits.Discover accessible customer IDs and retrieve resource field, metric, and segment metadata.
Create assets such as text, image, YouTube video, sitelink, callout, and structured snippet assets.
Upload local videos to YouTube as background tasks for use as video assets in local stdio mode.
Manage labels and label associations on campaigns, customers, ad groups, and ad group criteria.
Perform mutations safely using the Propose & Confirm workflow with
validate_onlyand checksum approval.Use optional
login_customer_idfor manager/MCC account access.Read API reference resources including discovery document, metrics, segments, and release notes.
Emit structured audit logs for tool calls and support local stdio/ADC or HTTP OAuth deployments.
Provides tools and resources for interacting with the Google Ads API, enabling AI agents to search account data, retrieve resource metadata, list accessible customers, and access discovery documents, metrics, segments, and release notes.
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., "@google-ads-mcp Search for my active campaigns"
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.
Google Ads MCP Server
An MCP (Model Context Protocol) server that enables LLMs and AI agents to query and manage Google Ads accounts.
Table of Contents
Related MCP server: gads
Overview
The Google Ads MCP Server exposes MCP Tools and MCP Resources backed by the Google Ads API. It supports:
Read & reporting workflows: GAQL queries, accessible customer discovery, resource field metadata, and API reference resources.
Guarded account mutations: Asset creation, video uploads, and label management protected by a two-step Propose & Confirm workflow.
Flexible deployment: Run locally over
stdiowith Application Default Credentials, or over Streamable HTTP with FastMCP's OAuth proxy and structured audit logging.
Notes:
Connecting an LLM or agent to this server exposes your accessible Google Ads account data to that client.
API calls made by this server include an MCP telemetry header used by Google to collect usage statistics and improve the product.
Report bugs or feature requests on the GitHub issue tracker.
Quickstart & Setup
1. Prerequisites
Python &
pipx(for local non-container setups): Python 3.11+ andpipx. To run a specific released version from PyPI:pipx run --spec "google-ads-mcp==X.Y.Z" google-ads-mcpGoogle Cloud Project: Enable the Google Ads API in your Google Cloud project (how to enable APIs).
2. Choose an Authentication Mode
The server supports two authentication and transport modes out of the box:
Mode | Transport | Best For |
Mode A: Application Default Credentials (ADC) |
| Single-user local CLI/IDE agents where the MCP client spawns the server directly. |
Mode B: FastMCP OAuth Proxy |
| Shared/remote deployments or local containers where server credentials stay isolated from MCP client configs. |
Mode A: Local stdio with Application Default Credentials (ADC)
Configure Application Default Credentials (ADC) for a user or service account with access to your Google Ads accounts. Credentials must include the Google Ads API scope (https://www.googleapis.com/auth/adwords). See Manage OAuth Clients if you need to create an OAuth desktop or web client first.
Option 1 — User credentials with an OAuth client JSON file:
gcloud auth application-default login \ --scopes=https://www.googleapis.com/auth/adwords,https://www.googleapis.com/auth/cloud-platform \ --client-id-file=YOUR_CLIENT_JSON_FILEOption 2 — Service account impersonation:
gcloud auth application-default login \ --impersonate-service-account=SERVICE_ACCOUNT_EMAIL \ --scopes=https://www.googleapis.com/auth/adwords,https://www.googleapis.com/auth/cloud-platform
When the command finishes, note the credentials path printed to the console (Credentials saved to file: [PATH_TO_CREDENTIALS_JSON]) for your MCP client configuration.
Mode B: Streamable HTTP with FastMCP OAuth Proxy
Setting GOOGLE_ADS_MCP_OAUTH_CLIENT_ID and GOOGLE_ADS_MCP_OAUTH_CLIENT_SECRET enables FastMCP's OAuth proxy for dynamic per-user Google OAuth login and automatically switches the server transport from stdio to streamable-http (default endpoint: http://localhost:8080/mcp).
Run the server as a standalone process or container (see Deployment and Environment Variables Reference), then point your MCP client at the HTTP endpoint—no server secrets are stored in client configs.
3. Configure Your MCP Client
Connecting via Streamable HTTP (Mode B — Recommended for Shared or Container Setups)
Antigravity / Antigravity IDE (MCP setup docs): Use
serverUrl(required for Streamable HTTP in current Antigravity releases; do not usehttpUrl):{ "mcpServers": { "google-ads-mcp": { "serverUrl": "http://localhost:8080/mcp" } } }Codex CLI (Codex MCP docs):
codex mcp add google_ads --url http://localhost:8080/mcp codex mcp login google_ads
Spawning Locally via stdio + ADC (Mode A)
Add the following mcpServers block to your client configuration, replacing PATH_TO_CREDENTIALS_JSON and YOUR_PROJECT_ID (how to find your project ID):
{
"mcpServers": {
"google-ads-mcp": {
"command": "pipx",
"args": [
"run",
"--spec",
"git+https://github.com/googleads/google-ads-mcp.git",
"google-ads-mcp"
],
"env": {
"GOOGLE_APPLICATION_CREDENTIALS": "PATH_TO_CREDENTIALS_JSON",
"GOOGLE_CLOUD_PROJECT": "YOUR_PROJECT_ID"
}
}
}
}Tip: To pin a published PyPI release instead of tracking
main, change"git+https://github.com/googleads/google-ads-mcp.git"to"google-ads-mcp==X.Y.Z". Note thatstdiomode stores the ADC file path in the client's config; prefer Local Container Deployment if client configs are shared or synced across tools.
Manager Accounts (login_customer_id)
If you access client accounts through a Google Ads Manager Account (MCC), you can either:
Pass
login_customer_idper tool call (takes precedence when provided), orSet
GOOGLE_ADS_LOGIN_CUSTOMER_IDin the server'senvconfiguration as a default:"env": { "GOOGLE_APPLICATION_CREDENTIALS": "PATH_TO_CREDENTIALS_JSON", "GOOGLE_CLOUD_PROJECT": "YOUR_PROJECT_ID", "GOOGLE_ADS_LOGIN_CUSTOMER_ID": "YOUR_MANAGER_CUSTOMER_ID" }
See Google Ads API Call Structure (login-customer-id) for details.
Other MCP Clients (Claude Code, Cursor, VS Code)
The mcpServers JSON format works across standard MCP clients—place it in the client's configuration file (for example, ~/.claude/settings.json for Claude Code, .cursor/mcp.json for Cursor, or .vscode/mcp.json for VS Code).
Tools & Resources
Available Tools
By default, tools are mounted with their category namespace prefix (<namespace>_<tool>). Namespaces and individual tools can be customized via tools_config.yaml (see Configuring and Namespacing Tools).
Default Tool Name | Namespace | Type | Description |
|
| Read | Queries Google Ads account data using GAQL (Google Ads Query Language). |
|
| Read | Retrieves selectable, filterable, and sortable field metadata for a Google Ads API resource (e.g., |
|
| Read | Lists customer IDs directly accessible to the authenticated user. |
|
| Mutate | Creates Google Ads assets ( |
|
| Mutate | Uploads a local video file to YouTube via a background task so it can be referenced by video assets (local |
|
| Mutate | Creates, updates, and removes account labels. |
|
| Mutate | Creates and removes label associations on |
Available Resources
Resource URI | Description |
| Google Ads API REST discovery document describing the API surface, resources, methods, and schemas. (Prefer |
| Reference documentation for reporting metrics in the Google Ads API. |
| Reference documentation for reporting segments in the Google Ads API. |
| Release notes for the latest version of the Google Ads API. |
Configuration & Security
Propose & Confirm Safety Workflow
All mutate tools (assets_create_asset, assets_upload_video_asset, labels_manage_labels, and labels_manage_label_associations) enforce a mandatory two-step safety workflow:
Propose (
validate_only=True, default): Validates the operation (including a Google Ads APIvalidate_onlydry run where supported) without committing changes. Returns human-readablechange_itemsand a cryptographicchecksumbound to thecustomer_idand parameters.Confirm (
validate_only=False): After explicit user approval, pass the exact same parameters andcustomer_idalong with thechecksumfrom step 1. Missing or mismatched checksums are rejected before mutating the account.
Configuring and Namespacing Tools
Use tools_config.yaml to selectively enable or disable tool categories/tools and customize namespace prefixes. A default configuration with all categories enabled is bundled with the package.
The server resolves tools_config.yaml in the following order:
Path specified by
GOOGLE_ADS_MCP_TOOLS_CONFIG../tools_config.yamlin the current working directory.The default
tools_config.yamlbundled with the package.
If an explicitly configured file is missing or any resolved file is invalid, startup fails immediately.
namespaces:
# Enable category with default prefix -> "customers_list_accessible_customers"
customers: true
# Enable category with custom prefix -> "query_search"
search: "query"
# Fine-grained control over individual tools in a category
metadata:
enabled: true
prefix: "metadata"
enabled_tools:
- get_resource_metadata: true
# Disable mutate categories for a strictly read-only deployment
labels: false
assets: falseTool Call Auditability
Every tool invocation—including background worker runs via TasksExtension—is recorded by AuditMiddleware, which emits structured JSON events ("tool_call" and "task_execution") to the ads_mcp.audit logger:
Actor (
actor): Authentication mode (oauthoradc), opaque OAuth identifiers (sub,client_id,scopes), MCPsession_id(per-request on sessionless MCP2026-07-28connections), and MCPclient_info. Raw PII such asemailandnameis omitted.Execution context: Unique
audit_id, tool name, MCPcall_id(andtask_idfor background tasks),received_atUTC timestamp,customer_id,login_customer_id,mutation_phase(READ,PROPOSE, orCOMMIT),checksum,schema_hash,status(completed,empty,enqueued,error, orfailed), andduration_ms.Redacted arguments:
argumentswith binary/base64 media payloads and Google Ads sensitive/PII fields (in bothsnake_caseand protobuf JSONcamelCase) replaced withREDACTED.
Audit records can also be persisted to filetree, redis, firestore, or memory via the GOOGLE_ADS_MCP_AUDIT_STORAGE_* variables below. Stored records remain unencrypted redacted JSON by default so backends like Firestore stay queryable across OAuth secret rotations; set GOOGLE_ADS_MCP_AUDIT_STORAGE_ENCRYPTION_KEY to enable Fernet encryption with a dedicated HKDF salt isolated from OAuth token storage.
Environment Variables Reference
Core & OAuth Proxy
Variable | Description |
| Optional default Manager Account (MCC) customer ID when accessing client accounts through a manager. |
| Optional path to a custom |
| HTTP listen port when running in Streamable HTTP mode (default: |
| Google Cloud OAuth 2.0 Client ID. Setting both ID and Secret enables OAuth Proxy & Streamable HTTP mode. |
| Google Cloud OAuth 2.0 Client Secret. |
| Public base URL of the HTTP server (default: |
| Recommended for multi-instance or persistent HTTP deployments to sign FastMCP JWTs consistently. |
OAuth State & Audit Persistence
Both OAuth state storage (GOOGLE_ADS_MCP_STORAGE_*) and optional audit record storage (GOOGLE_ADS_MCP_AUDIT_STORAGE_*) support filetree, redis, firestore, and memory backends.
Optional backend extras: Install
pip install "py-key-value-aio[redis]"for Redis orpip install "google-ads-mcp[firestore]"for Firestore.
OAuth Storage Variable | Audit Storage Equivalent | Description |
|
| Backend type: |
|
| Directory path when using the |
|
| Redis connection URL (defaults to |
|
| GCP project for |
|
| Firestore database name (defaults to |
|
| Fernet key (or secret material) for encrypting stored records. OAuth storage falls back to JWT/OAuth secret; audit storage is unencrypted unless explicitly set. |
|
| Set to |
— |
| Optional retention TTL (in positive seconds) for persisted audit records. |
Deployment
Remote and containerized deployments run in Streamable HTTP mode using the FastMCP OAuth Proxy (GOOGLE_ADS_MCP_OAUTH_CLIENT_ID and GOOGLE_ADS_MCP_OAUTH_CLIENT_SECRET).
Local Container Deployment (Docker / Podman)
Running the server in a local rootless container isolates OAuth secrets and storage encryption keys from MCP client configurations.
Build the image:
docker build --tag google-ads-mcp:latest . # or with Podman: podman build --tag localhost/google-ads-mcp:latest --file Dockerfile .Run with isolated secrets and persistent OAuth state: Keep your
.envfile outside the repository with owner-only permissions, bind port8080strictly to127.0.0.1for local agents, and mount a dedicated volume forfiletreeOAuth state (GOOGLE_ADS_MCP_STORAGE_PATH=/var/lib/google-ads-mcp):docker run -d --name google-ads-mcp \ -p 127.0.0.1:8080:8080 \ --env-file /absolute/host/path/google-ads-mcp.env \ -v google-ads-mcp-oauth:/var/lib/google-ads-mcp:rw \ --read-only --security-opt no-new-privileges --cap-drop ALL \ google-ads-mcp:latestFor systemd/Podman Quadlet setups, the equivalent
.containerunit is:[Container] Image=localhost/google-ads-mcp:latest PublishPort=127.0.0.1:8080:8080 EnvironmentFile=/absolute/host/path/google-ads-mcp.env Volume=google-ads-mcp-oauth.volume:/var/lib/google-ads-mcp:rw ReadOnly=true NoNewPrivileges=true DropCapability=all
HTTP Interoperability Notes
Stateful Streamable HTTP: Keep stateful Streamable HTTP enabled (the default). It serves both MCP 2025 clients (
Mcp-Session-Id+GETSSE) and MCP 2026 clients (sessionlessPOST+subscriptions/listen). Do not enable FastMCP'sstateless_httpoption on a shared endpoint, as it removes the legacyGETSSE channel.FastMCP 4 & OAuth callback compatibility: The server targets
fastmcp>=4.0.6,<5andmcp[cli]>=2.0.0,<3. TheDockerfileapplies a version-guarded patch that stops advertising RFC 9207authorization_response_iss_parameter_supportedas mandatory for compatibility with Codex CLI OAuth callbacks, failing the build loudly if the upstream FastMCP target changes.
Google Cloud Run Deployment
Prerequisites
A Google Cloud project with billing enabled.
The
gcloudCLI authenticated and configured:gcloud config set project YOUR_PROJECT_ID
Step 1: Build and Push the Container Image
Create an Artifact Registry repository and build with Cloud Build (no local Docker required):
gcloud artifacts repositories create mcp-servers \
--repository-format=docker \
--location=us-central1
gcloud builds submit \
--tag us-central1-docker.pkg.dev/YOUR_PROJECT_ID/mcp-servers/google-ads-mcp:latest .Using Firestore for persistent OAuth/audit storage on Cloud Run:
Install the Firestore extra in your
Dockerfile(RUN uv pip install --system ".[firestore]").Provision a Firestore database in your GCP project and grant the Cloud Run service account
roles/datastore.user.Note that
py-key-value-aio's Firestore store filters expired entries on read without deleting them (and writesexpires_atas a string rather than a native timestamp), so plan a periodic cleanup job for long-running deployments—or use Redis (GOOGLE_ADS_MCP_STORAGE_TYPE=redis), which expires keys natively.
Step 2: Deploy to Cloud Run
Deploy the service with your OAuth credentials, persistent JWT signing key, and storage backend. On first deploy, you can omit GOOGLE_ADS_MCP_BASE_URL until Cloud Run assigns your service URL, then update it:
gcloud run deploy google-ads-mcp \
--image us-central1-docker.pkg.dev/YOUR_PROJECT_ID/mcp-servers/google-ads-mcp:latest \
--platform managed \
--region us-central1 \
--allow-unauthenticated \
--set-env-vars="GOOGLE_CLOUD_PROJECT=YOUR_PROJECT_ID,GOOGLE_ADS_MCP_OAUTH_CLIENT_ID=YOUR_CLIENT_ID,GOOGLE_ADS_MCP_OAUTH_CLIENT_SECRET=YOUR_CLIENT_SECRET,GOOGLE_ADS_MCP_BASE_URL=https://your-cloud-run-url.a.run.app,GOOGLE_ADS_MCP_JWT_SIGNING_KEY=YOUR_JWT_SIGNING_KEY,GOOGLE_ADS_MCP_STORAGE_TYPE=firestore"Add GOOGLE_ADS_LOGIN_CUSTOMER_ID=YOUR_MANAGER_CUSTOMER_ID to --set-env-vars if your accounts are accessed via a manager account.
Step 3: Connect Your MCP Client
Point your MCP client at the Cloud Run /mcp endpoint:
{
"mcpServers": {
"google-ads-mcp": {
"serverUrl": "https://your-cloud-run-url.a.run.app/mcp"
}
}
}Try It Out
Launch your MCP client and verify that google-ads-mcp appears in the connected servers list. Try prompts such as:
What can the google-ads-mcp server do?What customers do I have access to?How many active campaigns do I have for customer ID 1234567890?How is my campaign performance this week for customer ID 1234567890?
Tip: Most tools require a
customer_id. Including the customer ID directly in your prompt makes switching across multiple accounts faster.
Contributing
Contributions are welcome! See the Contributing Guide to get started. Project maintainers can find the Trusted Publishing and release workflow in the Release Guide.
Available Tools
7 toolsassets_create_assetAssets Create AssetA
Creates a new Google Ads asset under the specified customer account.
Required & Optional parameters per asset_type:
TEXT: Requires
text_asset_text.IMAGE: Requires either
image_asset_path(absolute local path, local stdio mode only) ORimage_asset_data(base64 encoded string). Ifimage_asset_datais provided,image_asset_mime_typeis also required (e.g. 'IMAGE_PNG', 'IMAGE_JPEG', 'IMAGE_GIF').YOUTUBE_VIDEO: Requires
youtube_video_id.SITELINK: Requires
sitelink_link_textand root-levelfinal_urls. Accepts optionalsitelink_description1andsitelink_description2.CALLOUT: Requires
callout_text.STRUCTURED_SNIPPET: Requires
structured_snippet_headerandstructured_snippet_values.
Root-level URL and tracking configurations (optional except where noted):
name: Optional display name for the asset.final_urls: Required for SITELINK. A list of URLs.final_mobile_urls: List of mobile-specific destination URLs.tracking_url_template: Template for constructing a tracking URL.final_url_suffix: Suffix appended to the final URL.url_custom_parameters: Custom parameters represented as a list of dicts (with 'key' and 'value').
For any other asset type, provide extra_params as a dict representing the sub-asset message fields.
Propose & Confirm Workflow (validate_only and checksum):
Call
create_assetwithvalidate_only=True(the default). After validation passes, the tool returns structuredchange_itemsand achecksumwithout committing changes.Present the
change_itemsto the user and wait for explicit user approval.Only after user confirmation, call
create_assetwithvalidate_only=Falsealong with the exact same parameters and thechecksumreturned by the previousvalidate_only=Truecall.
Inputs: asset_type (required), customer_id (required), name, checksum, +19 more. Returns: result
assets_upload_video_assetAssets Upload Video AssetA
Uploads a video to YouTube natively via the Google Ads API.
Once a video has been uploaded, it can be used to create a video asset.
This operation executes via a FastMCP background task to gracefully handle large file uploads
(supported in local stdio mode only).
Once the upload finishes successfully, using the search tool and querying the you_tube_video_upload
resource matching the returned ID allows you to retrieve the YouTube Video ID and processing status.
Propose & Confirm Workflow (validate_only and checksum):
Call
upload_video_assetwithvalidate_only=True(the default). After validation passes, the tool returns structuredchange_itemsand achecksumwithout uploading the video.Present the
change_itemsto the user and wait for explicit user approval.Only after user confirmation, call
upload_video_assetwithvalidate_only=Falsealong with the exact same parameters and thechecksumreturned by the previousvalidate_only=Truecall.
Inputs: video_path (required), customer_id (required), video_title (required), video_description (required), +5 more. Returns: result
customers_list_accessible_customersCustomers List Accessible CustomersARead-only
Returns ids of customers directly accessible by the user authenticating the call.
Use this tool first to discover available customer IDs if the user hasn't provided one. Most other tools require a valid customer ID as input.
Inputs: no named parameters. Returns: result
labels_manage_label_associationsLabels Manage Label AssociationsADestructive
Manages associations between labels and Campaign, Customer, Ad Group, or Ad Group Criterion.
Supports CREATE and REMOVE operations.
Propose & Confirm Workflow (validate_only and checksum):
Call
manage_label_associationswithvalidate_only=True(the default). After validation passes, the tool returns structuredchange_itemsand achecksumwithout committing changes.Present the
change_itemsto the user and wait for explicit user approval.Only after user confirmation, call
manage_label_associationswithvalidate_only=Falsealong with the exact same parameters and thechecksumreturned by the previousvalidate_only=Truecall.
Inputs: operation (required), customer_id (required), association_type (required), checksum, +5 more. Returns: result
labels_manage_labelsLabels Manage LabelsADestructive
Manages Label resources. Supports CREATE, UPDATE, and REMOVE operations.
Propose & Confirm Workflow (validate_only and checksum):
Call
manage_labelswithvalidate_only=True(the default). After validation passes, the tool returns structuredchange_itemsand achecksumwithout committing changes.Present the
change_itemsto the user and wait for explicit user approval.Only after user confirmation, call
manage_labelswithvalidate_only=Falsealong with the exact same parameters and thechecksumreturned by the previousvalidate_only=Truecall.
Inputs: operation (required), customer_id (required), name, checksum, +5 more. Returns: result
metadata_get_resource_metadataMetadata Get Resource MetadataARead-only
Retrieves the selectable, filterable, and sortable fields for a specific Google Ads resource, including compatible metrics and segments.
Use this tool to find out which fields you can select, filter by, or sort by when querying a specific resource (e.g., 'campaign', 'ad_group'). This tool also returns metrics and segments that can be selected with the resource. Their names start with 'metrics.' and 'segments.' respectively.
Do not guess fields, you MUST use this tool to discover them before constructing a query for the
search tool.
The responses of this tool should be cached, as they don't change frequently.
Inputs: resource_name (required), login_customer_id. Returns: object
search_searchSearch SearchCRead-only
Fetches data from the Google Ads API using the search method
Inputs: fields (required), resource (required), customer_id (required), limit, +3 more. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 7 tools
Each tool targets a distinct resource+action: asset creation, video upload, label management, label associations, customer discovery, metadata discovery, and search. The only mild overlap is between assets_create_asset (which can create a YOUTUBE_VIDEO asset from an existing ID) and assets_upload_video_asset, but the descriptions make the boundary clear. Overall agents can reliably select the right tool.
All tools follow a consistent namespace_verb_noun pattern (assets_create_asset, labels_manage_labels, customers_list_accessible_customers), which is predictable and readable. Minor deviations like 'search_search' (redundant verb/noun) and the generic 'manage' verb for labels slightly reduce clarity but the convention holds.
Seven tools is a well-scoped, lean set for this server's apparent purpose of providing a focused Google Ads API surface. Each tool earns its place (discovery, schema, search, and a few mutation domains) without bloat.
Read coverage is broad because search_search can query any resource and metadata_get_resource_metadata exposes schema, but write/mutation coverage is thin—only assets and labels can be created or modified. Core lifecycle operations like creating campaigns, ad groups, budgets, or ads are absent, which will block common workflows.
Maintenance
Related MCP Connectors
Google Ads MCP server — manage campaigns, keywords, and metrics.
Google Ads MCP server: run Search, Display, Demand Gen and PMax campaigns from AI.
MCP server for querying and analyzing data from ad platforms, analytics tools, and spreadsheets
Hosted Google Ads MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
Related MCP Servers
- AlicenseAqualityFmaintenanceA read-write MCP server for managing Google Ads campaigns, ad groups, keywords, and ads via natural language.122-
- FlicenseNot gradedqualityDmaintenanceA Google Ads API MCP server that enables searching and listing accessible customers via natural language queries.2-
- AlicenseNot gradedqualityDmaintenanceMCP server for managing Google Ads campaigns through the official Google Ads API, covering accounts, campaigns, budgets, keywords, search terms, and keyword ideas. It provides tools for both reading and mutating live ads data, such as pausing campaigns, updating budgets, and adding keywords.MIT
- AlicenseNot gradedqualityFmaintenanceMCP server for Google Ads API that enables LLMs to search and query Google Ads accounts, retrieve resource metadata, and generate keyword ideas.Apache 2.0