Skip to main content

Using the Archive MCP Server

Written by Anne Buzzi

πŸ“‹ Available on: the same 2026 plans that include API access β€” Startup, Growth, Enterprise, Agency, and Custom 2026. Not available on Agency Standard 2026, legacy, or Free plans.

The Archive MCP server connects your AI assistant directly to your Archive data. Instead of writing API queries, you add Archive as a connector in your assistant once, then just ask in plain language β€” "find this creator", "pull the transcript for this video", "show my competitor brands" β€” and the assistant calls Archive for you.

MCP (Model Context Protocol) is an open standard supported by many AI assistants, including Claude (claude.ai, Claude Desktop, Claude Code), ChatGPT, Cursor, Windsurf, Cline, and VS Code.


What You Can Do With It

The MCP server is read-only β€” every tool reads or searches your data; nothing is created, changed, or deleted. You can ask your assistant to:

  • Workspaces β€” list the workspaces you can access and see what each one tracks (hashtags, mentions, keywords, connected accounts).

  • Content β€” search tracked posts and videos, pull the underlying media, get video transcriptions, and resolve a post URL to its item in Archive.

  • Creators β€” search creators, open a single creator or social profile, and pull a profile's historical engagement.

  • Competitors β€” list tracked competitor brands and pull their content.

  • Campaigns & more β€” read campaigns, saved views and filter presets, custom attribute definitions, and the status of long-running operations.

Anything that changes data β€” refreshing engagement, uploading content, adding to collections β€” isn't part of the MCP server today; those live in the full Archive API. Write actions for the MCP server are planned for a later release.


How to Connect

In Archive, go to Settings β†’ API β†’ Connect an agent. The server URL is:

https://app.archive.com/api/v2/mcp

There are two ways to connect β€” the screen shows ready-to-copy steps for each assistant.


Browser sign-in (recommended)

One-click sign-in through Archive in your browser β€” no API token to copy or store, and access is tied to you personally. Available for Claude, ChatGPT, Claude Code, Cursor, and VS Code.

In your assistant:

  1. Open Settings β†’ Connectors.

  2. Choose Add custom connector (or MCP server).

  3. Paste the server URL above.

  4. Click Connect and sign in with Archive. The connection stays live after that.


Config file

A manual alternative for desktop clients that don't yet support browser sign-in (such as Claude Desktop, Windsurf, and Cline), for scripted setups, or for pinning an agency token across an organization. It bridges the connection using your API token.

Copy the per-client snippet from Settings β†’ API, or see api-docs.archive.com/getting-started. To generate a token, see Generating an API Token.


Managing Connections

Browser sign-in is per person β€” each user authorizes their own assistant under the workspace. You can see and revoke connections at any time under Authorized connections on the same Settings β†’ API screen; anyone in the workspace can revoke any listed connection.


Good to Know

  • Read-only. The MCP server only reads and searches β€” it can't change anything in your workspace.

  • Multiple workspaces. If your access spans more than one workspace, tell the assistant which workspace to use (it can list them first). With a single-workspace token this is automatic.

  • Rate limit. Requests share the same limit as the API β€” up to 5 requests per second per workspace.

  • Agencies. An agency-level token works through the MCP server the same way it does on the API.


For the full technical reference and per-client setup snippets, see api-docs.archive.com/getting-started. Questions? Reach out to your Customer Success Manager or contact Archive Support via Intercom chat or at [email protected].

Did this answer your question?