Plain is a modern B2B customer-support platform with API-first workflows and a flat, thread-based model. Connecting Plain to clariBI surfaces every thread, customer, tenant, and label so support-volume, response-time, and customer-health questions get answered against the source of truth.
Why connect Plain
Plain's built-in reporting covers volume and first-response time, but the cross-cuts product and success teams want — tickets by customer tier, theme breakdowns, response time correlated with retention — usually need a separate analytics pipeline.
With Plain connected, you can ask "Which customer tiers drove the most tickets last quarter?", "What's the median first-response time on bug-tagged threads?", or "Which threads sat unassigned longer than 24 hours in November?" and the AI engine routes through Plain. Plain stays the source of truth; clariBI never replies, assigns, or modifies threads — write actions in the Plain MCP require explicit confirmation that clariBI doesn't request.
How the connection works
clariBI talks to Plain through its hosted MCP server at https://mcp.plain.com/mcp. Authentication uses an OAuth flow against an OAuth app you register in the vendor's developer console. Tokens stay encrypted server-side and never leave clariBI in clear form.
sequenceDiagram
actor U as You
participant C as clariBI
participant V as Plain
U->>C: Click Authorize with Plain
C->>V: Open OAuth authorization
V-->>U: Grant read access?
U->>V: Approve
V-->>C: Authorization code
C->>V: Exchange code for tokens
V-->>C: Access + refresh tokens
C->>C: Encrypt and store credentials
C-->>U: Connection ready
Available tools
clariBI exposes the read-only Plain tools that the vendor's MCP server publishes at connection time. Write operations (create, update, delete, send, refund) are filtered out by a name-pattern blocklist before any tool reaches the analysis engine, so connecting Plain cannot modify data on the vendor side.
The exact tool inventory depends on the Plain features your account has access to. After connecting, try a few natural-language questions to see what Plain data clariBI can pull.
Data flow during analysis
When you ask a question that maps to Plain, the AI engine routes to the right tool, reads the result, and pairs the answer with a chart you can pin to a dashboard.
sequenceDiagram
actor U as You
participant C as clariBI
participant AI as AI engine
participant V as Plain
U->>C: Ask a question about customer-support thread and customer data
C->>AI: Plan the analysis
AI->>V: Call the right tool
V-->>AI: Tool result
AI->>AI: Summarize and chart
C-->>U: Answer plus visual
Setting up the connection
- Open Data Sources in the clariBI sidebar.
- Click Add data source.
- Open the MCP Servers tab.
- Click the Plain card.
- Click Authorize with Plain.
- Sign in to Plain in the popup window and grant the requested read scopes.
- Back in clariBI, give your data source a name.
- Click Finish.
Permissions and data access
clariBI inherits the permissions of the connected Plain user via OAuth 2.0 with PKCE. Read access covers threads, customers, tenants, help-center articles, labels, and workspace data. clariBI never invokes Plain's write tools (reply, assign, mark done, snooze, upsert) — those are filtered out at the catalog layer. Disconnect anytime from Settings → Integrations or revoke access from your Plain workspace settings.
Troubleshooting
| Error | Cause | Fix |
|---|---|---|
| "Permission denied" on a thread | The connected Plain user does not have access to that thread in Plain. | Adjust the user's role in Plain or reconnect using a user with broader access. |
| "No threads found" | The filter applied by the AI engine matched no threads in your workspace, or your search window excluded the right time range. | Broaden the question or use a wider date range. |