Charla
Charla is a live chat and AI customer-support platform whose public API manages property contacts, conversation exports, and knowledge base articles and categories.
Integration
- Vendor
- Charla
- Category
- communication
- Auth
- API_KEY
- Tools
- 9
- Composio slug
charla
Tools
- Create Knowledge Base Article
Create a knowledge base article. Charla generates its URL slug from the title and may use it for chatbot training according to the property's AI settings. Defaults to a private draft.
- Delete Knowledge Base Articledestructive
Permanently delete one knowledge base article by ID. This cannot be undone, and deleting an already-missing article fails.
- Get Contact
Return one contact in the connected Charla property by UUID.
- Get Knowledge Base Article
Return the full content and metadata of one knowledge base article by ID.
- List Contacts
Return one page of contacts for the connected Charla property, ordered by most recently modified.
- List Conversations
Export one page of conversations grouped by contact for the connected Charla property, including message history.
- List Knowledge Base Articles
Return one page of knowledge base article summaries for the connected Charla property, newest first.
- List Knowledge Base Categories
Return all knowledge base categories available in the connected Charla property.
- Update Knowledge Base Article
Replace every writable field of an existing knowledge base article. Charla regenerates the URL slug from the replacement title and may retrain chatbot content according to the property's AI settings.
Setup
- Create or open a Switchy Project.
- Open Integrations and connect Charla.
- Authorise through api_key. Switchy stores the connection against your org.
- Everyone in the Project can now @-mention the Charla tools in chat.
What teammates see: by default, memories from Charla are scoped to the Project (PROJECT visibility) - you can mark any memory PRIVATE or share it ORG-wide.
Works well with
Top models
Compatibility data appears once enough Projects have used this MCP together with a given model.