Read Textline conversations, contacts and reports; send a text, add notes, resolve or transfer. 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": {
"textline": {
"url": "https://textline.usefulapi.io/mcp"
}
}
}Add to VS Code or add this to .vscode/mcp.json:
{
"servers": {
"textline": {
"type": "http",
"url": "https://textline.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 Textline API access token.
In Textline go to Settings → Tools & Integrations → Developer API and copy the access token. API access depends on your Textline plan. The server acts as the agent the token belongs to and sees only what that agent may see. Your token is used only to call the API on your behalf and to derive a private account id; it is 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 Textline API access token. 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 Textline connector, then ask in plain words. The AI picks the tools.
| Tool | Type | What it does |
|---|---|---|
textline_list_conversations | read | List conversations List conversations (one per contact) in a department of the Textline shared inbox, with the contact and resolved status. Optional keyword search. GET /api/conversations.json. |
textline_get_conversation | read | Get conversation messages Retrieve one conversation and its posts (messages in and out, internal whispers, resolve/transfer events), newest page first. Page with page/page_size or with before_uuid/after_uuid (a post uuid). GET /api/conversation/{uuid}.json. |
textline_get_conversation_by_phone | read | Get conversation by phone number Retrieve the conversation with a phone number (in a department) and its posts (messages). GET /api/conversations.json?phone_number=…. |
textline_list_customers | read | Search contacts List or search contacts (customers) in the Textline address book: name, phone, email, tags, notes, custom fields, consent and reachability. GET /api/customers.json. |
textline_get_customer | read | Get contact Retrieve one contact (customer) from the address book by UUID. GET /api/customer/{uuid}.json. |
textline_get_customer_by_phone | read | Get contact by phone number Retrieve one contact (customer) from the address book by phone number. GET /api/customers.json?phone_number=…. |
textline_list_custom_fields | read | List contact custom fields List the address book's custom fields (name, data type, UUID). Use the UUIDs with textline_update_customer. GET /api/address_book/custom_fields.json. |
textline_list_saved_searches | read | List saved searches List the address book's saved searches (contact segments) with name, description and UUID. GET /api/address_book/saved_searches.json. |
textline_get_organization | read | Get organization Retrieve the organization (account) name, optionally with its departments and agents. GET /api/organization.json. |
textline_list_departments | read | List departments List the departments (groups / inbox phone lines) the token's agent can see: name, UUID, phone number, type (sms, facebook, smart_sms) and member agent UUIDs. GET /api/groups.json. |
textline_list_agents | read | List agents List the agents (users) in the organization: name, email, UUID, permission level, availability and department UUIDs. GET /api/organization.json?include_users=1. |
textline_get_agent | read | Get agent Retrieve one agent (user) by UUID or email: name, permission level, availability (on_call) and departments. GET /api/users.json. |
textline_list_dispositions | read | List dispositions List the dispositions (resolution reasons) set up in the account, optionally for one department. Use a UUID with textline_resolve_conversation. GET /api/dispositions.json. |
textline_list_surveys | read | List surveys List surveys (NPS, CSAT, custom) with their type and UUID. GET /api/surveys.json. |
textline_list_survey_responses | read | List survey responses List the responses to one survey (ratings, follow-up text, contact, tags). Default: the last 30 days. GET /api/survey/{uuid}/responses.json. |
textline_report_conversations | read | Report conversations by date Reporting API: list a department's conversations filtered by created/updated time, resolved, archived or blocked, with total_records. To get the next page pass the returned next.search_uuid, next.page and next.page_size exactly (the same filters are kept). Then use textline_report_posts per conversation. GET /api/reporting/conversations.json. |
textline_report_posts | read | Report posts of a conversation Reporting API: list all posts (messages, whispers) of one conversation with creator, thread, first-response flags, filtered by created time, with total_records. To get the next page pass the returned next.search_uuid, next.page and next.page_size exactly. GET /api/reporting/conversation/{uuid}/posts.json. |
textline_send_message | write | Send SMS message SENDS A REAL SMS/MMS to ONE contact from your Textline number — the customer receives it immediately and it cannot be unsent; it consumes message credits. Address it by conversation_uuid or by phone_number (+ optional department). Confirm the recipient and text with the user first. One recipient per call; no bulk sends. POST /api/conversation/{uuid}.json or POST /api/conversations.json. |
textline_add_whisper | write | Add internal note (whisper) WRITE: add an internal whisper (a note only your agents see, never sent to the customer) to a conversation, by conversation_uuid or phone_number. POST /api/conversation/{uuid}.json or POST /api/conversations.json with a whisper. |
textline_resolve_conversation | write | Resolve conversation WRITE: mark a conversation resolved (closed), optionally with a disposition from textline_list_dispositions. Nothing is sent to the customer. POST /api/conversation/{uuid}/resolve.json. |
textline_transfer_conversation | write | Transfer conversation WRITE: assign a conversation to another agent of the same department, by agent UUID or email (one of them). Nothing is sent to the customer. POST /api/conversation/{uuid}/transfer.json. |
textline_create_customer | write | Create contact WRITE: add a contact (customer) to the Textline address book. Sends nothing to the contact. POST /api/customers.json. |
textline_update_customer | write | Update contact WRITE: update a contact's name, email, notes, tags (add, remove or replace) or custom fields (by custom-field UUID from textline_list_custom_fields). Overwrites the fields you pass; sends nothing to the contact. PUT /api/customer/{uuid}.json. |
textline_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. | |
textline_request_feature | Request a missing feature Tell usefulapi that the user needs something the Textline 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. | |
textline_upgrade | Upgrade to Pro (unlimited*) Get Pro: unlimited tool calls (fair use limit: 10,000 a month) on Textline (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. | |
textline_cancel_subscription | Cancel the Pro subscription Cancel the caller's Textline 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 textline_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 Textline server only. Subscribe with textline_upgrade (it returns a Stripe Checkout link). Cancel any time with textline_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running textline_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 Textline. The server calls the Textline API with your own Textline 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 Textline API access token. See Before you connect for where to find it.
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 Textline API access token. 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 Textline 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 Textline.
Yes, if you approve it. 6 of the 23 Textline tools can create or change data. The other 17 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 Textline server only. Cancel any time: Pro then runs to the end of the paid period. Run textline_usage_status to see how many calls you used.
Ask the AI to run textline_upgrade: it returns a Stripe Checkout link. To cancel, run textline_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 textline_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.