chatwoot-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CHATWOOT_URL | Yes | The URL of your Chatwoot instance (e.g., https://your-instance.chatwoot.com) | |
| MCP_HOST_PORT | No | Port to expose the HTTP server on when using Docker (optional) | 8000 |
| CHATWOOT_API_TOKEN | Yes | Your Chatwoot API access token (found under Profile Settings → Access Token) | |
| CHATWOOT_ACCOUNT_ID | Yes | Your Chatwoot account ID |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| chatwoot_get_summaryA | Returns the account summary: conversations, response times, resolution rate, and CSAT. |
| chatwoot_get_bot_summaryB | Returns overall bot performance: handoffs, autonomous resolution rate, and average response time. |
| chatwoot_get_conversation_trafficA | Returns a conversation traffic heat map (hour × day of week). |
| chatwoot_list_agentsA | Lists all agents in the account with ID, email, and availability status. |
| chatwoot_get_agent_performanceA | Returns performance metrics for a specific agent. |
| chatwoot_list_conversationsB | Lists conversations with filters by status, assignee, inbox, team, and label. |
| chatwoot_search_conversationsA | Searches conversations and messages by text. |
| chatwoot_get_conversationC | Returns the full details of a specific conversation. |
| chatwoot_get_conversation_messagesC | Returns the complete message history of a conversation. |
| chatwoot_list_labelsA | Lists all labels in the account with ID, color, and description. |
| chatwoot_get_label_performanceA | Returns performance metrics for a specific label. |
| chatwoot_list_inboxesB | Lists all inboxes (channels) in the account: WhatsApp, email, widget, etc. |
| chatwoot_get_inbox_performanceB | Returns performance metrics for a specific inbox. |
| chatwoot_list_teamsC | Lists all teams in the account. |
| chatwoot_get_team_performanceB | Returns performance metrics for a specific team. |
| chatwoot_list_captain_assistantsA | Lists all Captain (AI) assistants configured in the account. |
| chatwoot_get_captain_metricsB | Returns performance metrics for a Captain (AI) assistant. |
| chatwoot_get_csat_responsesA | Returns customer satisfaction survey (CSAT) responses. |
| chatwoot_get_csat_metricsB | Returns the aggregated CSAT summary: total responses, breakdown by score, and response rate. |
| chatwoot_get_live_metricsB | Returns real-time conversation counts: open, unattended, unassigned, and pending. |
| chatwoot_get_live_grouped_metricsB | Returns real-time conversations grouped by team or agent. |
| chatwoot_search_contactsA | Searches contacts by name, email, phone, or identifier. |
| chatwoot_get_contactA | Returns the full details of a specific contact. |
| chatwoot_get_contact_conversationsA | Returns the full conversation history of a specific contact. |
| chatwoot_get_captain_faq_statsB | Returns usage and effectiveness statistics for a Captain assistant's knowledge base (FAQ). |
| chatwoot_get_captain_overviewA | Returns overview metrics for a Captain assistant with period-to-period comparison. |
| chatwoot_get_captain_resolution_flowA | Returns the conversation resolution funnel for a Captain assistant (steps to resolution). |
| chatwoot_get_captain_resolution_trendA | Returns the resolution rate trend for a Captain assistant over time. |
| chatwoot_get_inbox_label_matrixA | Returns the conversation distribution between inboxes and labels (inbox × label matrix). |
| chatwoot_get_first_response_distributionB | Returns a histogram of first response time distribution. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 30 tools
Each tool has a clearly distinct purpose: list vs. get vs. search, and per-entity performance metrics are separated by resource (agent, inbox, team, label, captain). Even the Captain analytics tools (FAQ stats, overview, resolution flow, resolution trend) are differentiated by their focus, reducing selection ambiguity.
All tools follow a strict chatwoot_<verb>_<noun> pattern with consistent verbs (get, list, search). The naming is uniform across all 30 tools, making the API predictable and easy to navigate.
At 30 tools, the server is on the heavier side, but the breadth of Chatwoot's feature set (agents, inboxes, teams, labels, contacts, conversations, CSAT, Captain AI, live metrics, analytics) justifies the count. Each tool covers a distinct aspect, so the number feels appropriate for a comprehensive analytics-focused MCP.
The server is strong for read-only analytics and reporting, covering the main entities and metrics. Minor gaps exist: no single-entity detail tools beyond list (e.g., get_inbox, get_team), and no write operations, but that aligns with its apparent reporting purpose. The core lifecycle of querying and analyzing data is well covered.