Read and update Chatra visitors; send, edit and delete chat and pushed messages. Hosted by usefulapi — connect from Claude, ChatGPT, Cursor, or any MCP client.
Team and Enterprise: an Owner adds the connector for the organization first.
Run this command, then run /mcp in Claude Code to log in:
Add to Cursor or add this to ~/.cursor/mcp.json:
{
"mcpServers": {
"chatra": {
"url": "https://chatra.usefulapi.io/mcp"
}
}
}Add to VS Code or add this to .vscode/mcp.json:
{
"servers": {
"chatra": {
"type": "http",
"url": "https://chatra.usefulapi.io/mcp"
}
}
}No Add custom MCP server option? It depends on your account or workspace settings: see OpenAI's guide.
Run these commands. The second one opens the login page:
Other MCP clients (Windsurf, Cline, Zed and more): add the URL as a remote MCP server (Streamable HTTP). The client then opens the login page in your browser. Do not add an Authorization header: see Before you connect.
The login page asks for your Public API key and Secret API key.
Find both keys in Chatra under Settings → Preferences → API keys. The keys act for your whole Chatra account and messages you send reach real visitors. They are used only to call the Chatra API on your behalf and are never shown to anyone.
Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your Public API key and Secret API key. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
Turn on the Chatra connector, then ask in plain words. The AI picks the tools.
| Tool | Type | What it does |
|---|---|---|
chatra_get_visitor | read | Get visitor A chat visitor by id: name and contact details (basicInfo, integrationData and the merged `info`), custom form answers, location, browser, the link to the chat in the Chatra dashboard, the agent group, and the pages viewed in the latest visit. The id is the `clientId` your website passed to the widget or the visitor id from a Chatra webhook; Chatra has no endpoint to list or search visitors. GET /clients/{id}. |
chatra_update_visitor | write | Update visitor WRITE: edit a visitor's basic info (name, email, phone, notes) exactly as if an agent edited it in the Chatra dashboard. Only the fields you pass change; `null` removes a value. Returns the updated visitor. PUT /clients/{id}. |
chatra_get_message | read | Get message One chat message by id (a visitor's or an agent's): type (agent or client), text, visitor id, agent id, timestamp (ms) and receivedFrom. Chatra has no endpoint to list a conversation, so the id must come from a send call or a webhook. GET /messages/{id}. |
chatra_send_message | write | Send message as an agent WRITE: send a chat message to a visitor as a Chatra agent. The visitor sees it immediately in their chat window as if the agent typed it, so only call it with text the user asked you to send. It cannot be unsent except by deleting it. Say which agent writes: agent_id, or agent_email + agent_name + received_from (a dummy agent is created in Chatra when the email is unknown). For automated notices (order status, announcements) use chatra_push_message instead. Returns the new message with its id. POST /messages/. |
chatra_edit_message | write | Edit agent message WRITE: replace the text of an agent message that was sent earlier. Only agents' messages can be edited, not visitors'. The visitor sees the edited text. Returns the updated message. PUT /messages/{id}. |
chatra_delete_message | write | Delete agent message WRITE, IRREVERSIBLE: delete an agent message from the conversation. Only agents' messages can be deleted, not visitors'. Returns the deleted message. DELETE /messages/{id}. |
chatra_get_pushed_message | read | Get pushed message One pushed (automated) message sent earlier by id: text, visitor id, agent id, timestamp (ms), isPushed. GET /pushedMessages/{id}. |
chatra_push_message | write | Push message to a visitor WRITE: send an automated message (order status, product update, announcement) to a visitor whose account is bound to Chatra through a clientId. It is delivered into the visitor's chat on behalf of a random agent, a given agent (agent_id) or a random agent of a group (group_id). It reaches a real customer and cannot be unsent except by deleting it, so only call it with text the user asked you to send. Returns the new message with its id. POST /pushedMessages/. |
chatra_edit_pushed_message | write | Edit pushed message WRITE: replace the text of a pushed message sent earlier; the visitor sees the edited text. Returns the updated message. PUT /pushedMessages/{id}. |
chatra_delete_pushed_message | write | Delete pushed message WRITE, IRREVERSIBLE: delete a pushed message sent earlier. Returns the deleted message. DELETE /pushedMessages/{id}. |
chatra_usage_status | Usage status (free-tier meter) Report the caller's current usage: the plan, calls used this month, the limit of the plan (the free monthly cap or the Pro fair use limit), remaining, and whether the limit is reached. Read-only; does not count against the meter. | |
chatra_request_feature | Request a missing feature Tell usefulapi that the user needs something the Chatra tools cannot do yet (a missing tool, field or filter). Call it only when the user asks for something none of the tools can do, and tell the user that you send the request. Do not call it for errors or for normal requests. Do not include personal data, credentials or customer records. Stored with the product name and the client type (for example Claude or Cursor), without the user's account. At most 5 requests per day. Does not count against the meter. | |
chatra_upgrade | Upgrade to Pro (unlimited*) Get Pro: unlimited tool calls (fair use limit: 10,000 a month) on Chatra (the free tier caps monthly usage). Plans: "monthly" — $9/month; "yearly" — $90/year (2 months free). Cancel any time: Pro then runs to the end of the paid period, so it also suits a one-time job. *A fair use limit applies. For heavy use (near Pro's limit): "plus" or "plus_yearly" — Pro+, $19/month or $190/year, unlimited tool calls (fair use limit: 100,000 a month); an existing Pro subscription changes to Pro+ in place (needs confirm: true; the price difference for the rest of the period is charged at once). Otherwise returns a short link to open in your browser (it opens Stripe Checkout); after payment the account upgrades automatically. Does not count against the meter. | |
chatra_cancel_subscription | Cancel the Pro subscription Cancel the caller's Chatra Pro subscription at the end of the paid period (no refund for the current period; Pro continues until then, then the free tier applies). Requires confirm: true. Run chatra_upgrade later to undo the cancel before the period ends. Does not count against the meter. |
| Plan | Price | Limit |
|---|---|---|
| Free | $0 | 50 tool calls / month |
| Proper user | $9/mo · $90/yr | Unlimited* |
*Pro fair use limit: 10,000 tool calls a month on this server. For more, write to [email protected].
Pro covers this Chatra server only. Subscribe with chatra_upgrade (it returns a Stripe Checkout link). Cancel any time with chatra_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running chatra_upgrade before then undoes the cancel. Or write to [email protected].
No. usefulapi is an independent service. It is not affiliated with or endorsed by Chatra. The server calls the Chatra API with your own Chatra access, so it sees only the data that your account can see.
Yes. In Claude, add this server's URL as a custom connector. In ChatGPT, add it as a custom MCP server in Plugins. Then log in once. Cursor, VS Code, Claude Code and Codex work too. See the setup steps.
The login page asks for your Public API key and Secret API key. See Before you connect for where to find them.
No. Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your Public API key and Secret API key. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
The login stores them encrypted in the authorization grant of your connection. The server uses them to call the Chatra API for you and to derive a private account id for usage metering. usefulapi does not show them on any page or in any reply. To stop all access, remove the connector and change or delete these credentials in Chatra.
Yes, if you approve it. 7 of the 10 Chatra tools can create or change data. The other 3 are marked read-only. Most MCP clients ask you to approve a tool call before it runs.
The Free plan gives 50 tool calls / month. Pro costs $9/mo or $90/yr, with unlimited tool calls (fair use limit: 10,000 tool calls a month), for this Chatra server only. Cancel any time: Pro then runs to the end of the paid period. Run chatra_usage_status to see how many calls you used.
Ask the AI to run chatra_upgrade: it returns a Stripe Checkout link. To cancel, run chatra_cancel_subscription. Pro continues to the end of the paid period.
Tell the AI what you wanted to do. It can send the request with chatra_request_feature. We store the text with the server name, the type of AI client and the tool you tried, not with your account, and read every request when we plan new tools. You can send up to 5 requests per day.
Any client that supports remote MCP servers (Streamable HTTP) with OAuth login: Claude (web and desktop), Claude Code, ChatGPT, Codex, Cursor, VS Code, Windsurf and others.
This is a Model Context Protocol endpoint — meant to be connected from an AI client, not opened in a browser. An invalid_token response at the URL is the auth gate working as designed; clients authenticate automatically.