MCP server for interacting with your LINE Official Account
Chatwoot MCP by usefulapi is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
Read conversations and contacts; add replies or notes, set status and assign in Chatwoot.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http chatwoot-mcp-by-usefulapi https://chatwoot.usefulapi.io/mcp
# 2 — ask your agent for something these tools do
# chatwoot_get_account, chatwoot_list_conversations, chatwoot_get_conversation_counts and 15 more
Chatwoot MCP by usefulapi costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http chatwoot-mcp-by-usefulapi https://chatwoot.usefulapi.io/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
18 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Get the configured Chatwoot account: name, locale, features and plan. Chatwoot API: GET /api/v1/accounts/{account_id}.
No parameter schema on file.
List conversations, 25 per page, filtered by status, assignee, inbox, team, labels or a text query. Chatwoot API: GET /api/v1/accounts/{account_id}/conversations.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| status | string | no | Default open. |
| assignee_type | string | no | Default all. |
| inbox_id | integer | no | — |
| team_id | integer | no | — |
| labels | array | no | Only conversations with all these label titles. |
| q | string | no | Free-text search. |
| page | integer | no | Page number, starting at 1. |
Get the open, unassigned and total conversation counts for a status, inbox or team. Chatwoot API: GET /api/v1/accounts/{account_id}/conversations/meta.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| status | string | no | — |
| inbox_id | integer | no | — |
| team_id | integer | no | — |
| q | string | no | — |
Get one conversation with its status, priority, assignee, team, labels and contact. Chatwoot API: GET .../conversations/{conversation_id}.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| conversation_id | integer | yes | Conversation id (from chatwoot_list_conversations). |
List the messages of one conversation, oldest first. Chatwoot API: GET .../conversations/{conversation_id}/messages.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| conversation_id | integer | yes | — |
| before | integer | no | Only messages with an id below this value. |
| after | integer | no | Only messages with an id above this value. |
List resolved contacts (those with an email, phone number or identifier), 15 per page. Chatwoot API: GET .../contacts.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| page | integer | no | Page number, starting at 1. |
| sort | string | no | — |
Search resolved contacts by a text key (name, email or phone). Chatwoot API: GET .../contacts/search.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| q | string | yes | Search text. |
| page | integer | no | Page number, starting at 1. |
| sort | string | no | — |
Get one contact with its attributes, labels and custom attributes. Chatwoot API: GET .../contacts/{id}.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| contact_id | integer | yes | Contact id (from chatwoot_list_contacts or chatwoot_search_contacts). |
List all conversations of one contact. Chatwoot API: GET .../contacts/{id}/conversations.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| contact_id | integer | yes | — |
List all labels of the account. Chatwoot API: GET .../labels.
No parameter schema on file.
List the inboxes (channels) of the account. Chatwoot API: GET .../inboxes.
No parameter schema on file.
List the agents of the account with their roles. Chatwoot API: GET .../agents.
No parameter schema on file.
List the teams of the account. Chatwoot API: GET .../teams.
No parameter schema on file.
List the saved reply templates (canned responses) of the account. Chatwoot API: GET .../canned_responses.
No parameter schema on file.
Add a message to a conversation. Default: a private note that the customer never sees. Set private to false to send a reply that the customer receives by email or chat. Chatwoot API: POST .../conversations/{conversation_id}/messages.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| conversation_id | integer | yes | — |
| content | string | yes | The message text. |
| private | boolean | no | true (default) = internal note; false = customer-visible reply. |
Set a conversation to open, resolved, pending or snoozed. For snoozed, snoozed_until is a Unix time in seconds (optional). Chatwoot API: POST .../conversations/{conversation_id}/toggle_status.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| conversation_id | integer | yes | — |
| status | string | yes | — |
| snoozed_until | integer | no | Unix time in seconds; only with status snoozed. |
Set a conversation priority: urgent, high, medium, low, or none (clears it). Chatwoot API: PATCH .../conversations/{conversation_id}.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| conversation_id | integer | yes | — |
| priority | string | yes | — |
Assign a conversation to an agent (assignee_id) or to a team (team_id). Give exactly one. Chatwoot API: POST .../conversations/{conversation_id}/assignments.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| conversation_id | integer | yes | — |
| assignee_id | integer | no | Agent user id (from chatwoot_list_agents). |
| team_id | integer | no | Team id (from chatwoot_list_teams). |
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Chatwoot MCP by usefulapi or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| chatwoot_get_account | no tags | |
| chatwoot_list_conversations | no tags | |
| chatwoot_get_conversation_counts | no tags | |
| chatwoot_get_conversation | no tags | |
| chatwoot_list_messages | no tags | |
| chatwoot_list_contacts | no tags | |
| chatwoot_search_contacts | no tags | |
| chatwoot_get_contact | no tags | |
| chatwoot_list_contact_conversations | no tags | |
| chatwoot_list_labels | no tags | |
| chatwoot_list_inboxes | no tags | |
| chatwoot_list_agents | no tags | |
| chatwoot_list_teams | no tags | |
| chatwoot_list_canned_responses | no tags | |
| chatwoot_send_message | external-sinkstate-write | external-sink: keyword "send_message"; state-write: declares destructiveHint: true |
| chatwoot_set_conversation_status | no tags | |
| chatwoot_set_conversation_priority | no tags | |
| chatwoot_assign_conversation | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.3.5.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish Chatwoot MCP by usefulapi can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.