What is the Condens MCP Server?
MCP (Model Context Protocol) is an open standard that allows AI tools to securely connect to external data sources. The Condens MCP Server implements this protocol, giving any MCP-compatible AI assistant or your own LLM infrastructure read-only access to your published research.
This means you can:
Ask questions about your research in natural language and get instant answers
Query across multiple Condens workspaces simultaneously
Combine Condens with other MCP-compatible tools (Notion, Jira, Linear, etc.) in the same conversation.
Important limitations
Only published Artifacts are accessible through the MCP server
You only see workspaces, projects, and Artifacts you already have access to in Condens
AI cannot create, edit, or delete any content in Condens
You can use the MCP server to connect Condens to any LLM that suports this connection. You must have a paid plan with Claude (Pro or higher) or ChatGPT (Plus or higher) to use MCP servers with these AI assistants.
How to connect Condens to a LLM
As an Admin, you'll add and configure custom MCP clients in Condens, set access permissions to control which users, roles, or user groups can use each client, and provide setup instructions to guide your team through the connection process.
Once you've authorized an MCP client and assigned permissions, it automatically appears in Settings → Integrations for authorized users. They can then follow your setup instructions to connect their AI assistant and start querying Condens immediately.
Note: Claude and ChatGPT are preconnected by default, but you still need to set access permissions for them to appear in the Integrations list for selected users.
Adding a custom MCP client
A Condens Admin needs to:
In Condens, go to Settings > Account > API & MCP Server and click Add MCP Client.
Enter client details:
Client name: The name that will appear in your authorized apps list
Logo: Upload a logo to help users identify the client easily
Description: Add a short description displayed on the app card (visible to users when browsing authorized apps)
Enter the OAuth2 redirect URI where your service sends users after login. This is required for the authorization flow to work correctly.
For in-house LLMs, consult your development team
For public clients, contact us at hello@condens.io.
Wildcard support
Redirect URIs may include a single trailing wildcard (*). This allows clients with dynamic redirect URIs (like Copilot Studio) to be authorized using a common prefix. The wildcard must appear only at the end of the URL and matches any characters after the prefix.
Example pattern: https://custom-llm-client.app/connector/*
This would allow redirect URIs such as:
Configure which users, roles, or user groups can use this MCP client. Only authorized users will see this client in their Integrations list.
Add setup instructions for your team:
Write step-by-step instructions explaining how to connect to this client.
These instructions appear in Settings > Integrations for authorized users
Tip: Include any necessary URLs, configuration details, or troubleshooting tips.
Click Create.
Once saved, the custom MCP client will appear in the authorized apps list and in Integrations for users who have permission to use it.
Authorizing the MCP client on a user-level
As a final step, each user needs to individually connect the MCP client to their Condens account.
In Settings > Integrations, you'll find the setup instructions provided by the Admin by clicking Show setup instructions. Please bear in mind that the authorization itself happens in the MCP client, not in Condens.
The toggle next to the MCP client in Integrations shows the connection status. If it's off, the authorization step hasn't been completed yet. Once you've authorized Condens in your MCP client, the toggle will automatically turn on.
Creating a dedicated user account to connect with MCP server
If individual user accounts aren't a viable option for your setup, you can instead create a dedicated Condens Viewer account to serve as the MCP connection for your entire company.
Note: This approach gives everyone access to the same set of data. Unlike individual integrations, access cannot be managed or scoped on a per-user level. Everyone using the LLM sees the same Condens content.
This is useful when:
Users don't have individual Condens accounts
You want to control exactly which insights are exposed (e.g., only executive summaries or specific product research)
You're connecting a company chatbot or internal AI assistant
How it works
Instead of each user connecting their own Condens account, you create a single Condens account that acts as the MCP connection for your entire company. The MCP server will only have access to what this account can see in Condens.
Create a dedicated Condens user account.
Use a generic email like company-llm@yourcompany.com or research-bot@yourcompany.com
Set the user role to Viewer (this doesn't require a paid seat)
Configure access permissions for this account:
Grant access only to the workspaces and projects you want exposed through the LLM
Use multiple Magazines to create curated views:
Create a "C-Level Insights" Magazine for executive summaries
Create product-specific Magazines for different teams
Only publish content you want accessible company-wide
Set up the custom MCP client in Condens:
As an Admin, go to Settings → Account → API & MCP Server
Add your custom MCP client (following the steps above)
Configure access permissions for who can use this client and add this dedicated user account.
Connect the MCP client using this account:
Open an incognito/private browser window
Log into Condens with the dedicated account credentials
Go to Settings > Integrations and authorize the connection in your MCP client.
This gives your custom or internal LLM access to select data in Condens, regardless of whether users of that LLM have Condens accounts.
Check the MCP servers directory for more available integrations.
