mcpField
C
ConsentStack MCP

ConsentStack MCP

VerifiedFeaturedRemote
consentstack.ioData & Analytics1Updated 8w ago

About ConsentStack MCP

ConsentStack MCP is a hosted server for configuring cookie consent through an AI agent. It supports site setup, banner publication, tracker review, and compliance scans, with draft changes kept separate until approved.

Key features

  1. 01Create sites and manage domains
  2. 02Configure and publish consent banners
  3. 03Generate site-specific install snippets
  4. 04Scan for trackers and compliance issues
  5. 05Review consent analytics and logs
  6. 06Search ConsentStack documentation

Use cases

  1. 01Set up a consent banner on a website
  2. 02Review trackers found by a compliance scan
  3. 03Adjust banner settings before publishing

MCP support

Exposes 22 ConsentStack tools to MCP clients over Streamable HTTP, using OAuth 2.1 sign-in. Tools cover site setup, banner configuration, tracker management, scans, analytics, logs, and documentation.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://app.consentstack.io/api/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

ConsentStack MCP Server

Set up GDPR and CCPA cookie consent from your AI agent. Create a site, publish a banner, get the install snippet, run a compliance scan, and categorize the trackers it finds, all through the Model Context Protocol.

If you built your site with Claude, Cursor, Lovable, or Replit, this is the shortest path to a working cookie banner: the same agent that built the site can install consent on it.

Hosted server. Nothing to install, no API keys.

Server URLhttps://app.consentstack.io/api/mcp
TransportStreamable HTTP
AuthenticationOAuth 2.1 (sign in with your ConsentStack account)
Registry nameio.consentstack/cookie-consent
Docshttps://www.consentstack.io/docs/developers/mcp

About this repository. ConsentStack's MCP server is hosted, so this repo holds the server manifest, connection instructions, and tool reference rather than the server's source. Issues and questions are welcome here.

Connect

Claude Code

claude mcp add --transport http consentstack https://app.consentstack.io/api/mcp

Claude desktop or claude.ai

Settings > Connectors > Add custom connector, then paste the server URL.

Cursor (.cursor/mcp.json)

{
  "mcpServers": {
    "consentstack": {
      "url": "https://app.consentstack.io/api/mcp"
    }
  }
}

Any other client that supports remote MCP servers over streamable HTTP with OAuth: give it the URL and sign in when prompted.

On first connect your client opens a browser window to sign in with the same account you use for the dashboard. No account yet? Sign up free; the Basic tier costs nothing.

Tools

22 tools, grouped by job.

JobTools
Sites and setuplist_sites, get_site_overview, create_site, manage_domains, get_setup_guide
Banner configurationget_config, update_appearance, update_content, update_compliance, update_settings, publish_config, discard_draft
Trackers and blockinglist_detected_trackers, set_tracker_category, clear_tracker_override, set_hostname_policy
Compliance scanningstart_scan, get_scan_result
Analytics and logsget_consent_analytics, get_consent_logs
Documentationsearch_docs, get_doc

get_setup_guide returns install snippets with your real site key filled in, so the agent can paste working tags straight into your codebase.

A full run

  1. Create. create_site adds a site on the free Basic tier. manage_domains registers where it runs.
  2. Install. get_setup_guide returns the install tags with your real site key.
  3. Configure. The agent stages appearance, text, and compliance settings as drafts. Drafts never touch your live site.
  4. Publish. After you approve the changes in conversation, publish_config makes them live.
  5. Verify. start_scan runs the compliance scanner against the live site: a real browser visits, declines the banner, and reports any tracker that fired anyway. The agent categorizes what the scan finds and rescans until it comes back clean.

Scan findings come back with remediation hints naming the exact tool that fixes them, so an agent can close the loop on its own.

Access and permissions

Every request runs under your account with your team role, the same as the dashboard. Read tools work for any team member. Config writes (update_*, publish_config, tracker overrides) require the admin or owner role. The server's own instructions direct agents to summarize pending changes and get your explicit go-ahead before publishing anything.

Authentication is OAuth 2.1 with standard protected-resource discovery, so clients negotiate sign-in automatically. Tokens are issued to your account, never to a shared key, and every database query enforces the same row-level security the dashboard uses. There are no long-lived API keys to leak or rotate.

Cost

MCP access is included on every plan, including the free Basic tier, and create_site creates Basic sites. Features belonging to paid plans (consent analytics and logs, for example) stay plan-gated exactly as they are in the dashboard. The tools tell your agent which plan unlocks them rather than working around the limit.

Links

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.