trackmcp
Back to directory

Public REST API and MCP server of DOS AI: AI assistants (chatbots) for WhatsApp and Telegram with built-in CRM. OpenAPI spec, MCP tools, runnable examples.

0 starsOthers Updated Aug 14, 2026
ai-agentchatbotcrmllmmcp-serverno-codeopenapitelegram-botwhatsapp-apiwhatsapp-bot

Documentation

DOS AI API and MCP server

Public interfaces of DOS AI, a platform for AI assistants (chatbots) in WhatsApp and Telegram with a built-in CRM.

This repository holds the machine-readable contract and runnable examples. The platform itself is hosted, so there is nothing to install: you get an API key in the cabinet and call the endpoints below.

  • OpenAPI spec: https://dosai.pro/api/openapi.json
  • MCP endpoint: `https://dosai.pro/api/mcp`
  • Agent primer: https://dosai.pro/llms.txt
  • Full public corpus (guide + course + articles): https://dosai.pro/llms-full.txt
  • Human docs: https://dosai.pro/docs/guide/08-developers/80-public-api

What the platform does

A project in DOS AI is one bot: its instructions, its knowledge base, its channel (WhatsApp via QR or Telegram), its balance and its clients. The bot answers incoming messages in natural language, books time slots from a Google Calendar or Sheet, issues invoices in the chat, files every conversation as a lead, and hands the dialog over to a human when your rules say so.

The API exposes that same data: projects, conversations, messages, leads, analytics and balance.

Authentication

Every request carries an API key issued in the cabinet:

code
Authorization: Bearer dos_sk_live_...

The key authenticates as the user who created it, so it inherits that user's access. Only a SHA-256 hash of the key is stored, which means a lost key cannot be recovered, only revoked and reissued. Keys can be scoped to a single project and to read-only access.

Rate limit: 120 requests per minute per key, plus a stricter per-endpoint budget. On 429 the `Retry-After` header tells you how many seconds to wait.

REST in one minute

bash
export DOSAI_KEY="dos_sk_live_..."

# projects visible to this key
curl -s https://dosai.pro/api/projects \
  -H "Authorization: Bearer $DOSAI_KEY"

# leads of one project
curl -s "https://dosai.pro/api/projects/$PROJECT_ID/leads?limit=20" \
  -H "Authorization: Bearer $DOSAI_KEY"

# analytics for a period
curl -s "https://dosai.pro/api/projects/$PROJECT_ID/analytics?from=2026-08-01&to=2026-08-14" \
  -H "Authorization: Bearer $DOSAI_KEY"

Available paths (full schemas in the OpenAPI file):

PathWhat it gives
`/api/projects`list of projects
`/api/projects/{id}`one project, including its prompt
`/api/projects/{id}/conversations`dialogs with filters and paging
`/api/projects/{id}/leads`leads with status and source
`/api/projects/{id}/leads/export`leads as CSV
`/api/projects/{id}/analytics`dialogs, leads, conversion, response time
`/api/projects/{id}/functions`functions the bot can call
`/api/projects/{id}/integrations`connected Google and CRM integrations
`/api/projects/{id}/reports`owner reports
`/api/projects/{id}/tokens`balance
`/api/projects/{id}/tokens/history`balance movements

Responses come wrapped in an envelope (`{ "data": ... }`), so unwrap before use. The OpenAPI file is the authority here and is generated from the same source the routes are checked against.

MCP: connect an AI assistant

The platform ships a Model Context Protocol endpoint, so an AI assistant can read and manage your bots directly. Point your MCP client at:

code
https://dosai.pro/api/mcp

Tools exposed (all prefixed `dosai_`):

`list_projects`, `get_project`, `get_prompt`, `update_prompt`, `list_functions`, `list_leads`, `get_lead`, `update_lead`, `list_conversations`, `get_messages`, `send_operator_message`, `get_analytics`, `get_balance`.

Two design decisions worth knowing:

No destructive tools. There is no delete-project, no payment, no member management. Adding one would be a conscious decision, not a reflex, and a test guards the list.

Every tool calls the public REST route over HTTP, not an internal service layer. That way a read-only key stays read-only, project scoping and rate limits apply exactly once, and the agent cannot reach anything a human with the same key could not.

Example client config (Claude Desktop style):

json
{
  "mcpServers": {
    "dosai": {
      "url": "https://dosai.pro/api/mcp",
      "headers": { "Authorization": "Bearer dos_sk_live_..." }
    }
  }
}

Webhooks

Instead of polling, you can receive events on your own endpoint: new lead, new message, stage change. Signature verification and payload shapes are documented at https://dosai.pro/docs/guide/08-developers/81-custom-webhooks

Examples

Getting a key

1. Register at https://dosai.pro/register (a starting balance is granted, no card required)

2. Create a project and connect a channel

3. Open the cabinet, section API keys, and issue a key with the scope you need

  • Platform: https://dosai.pro
  • Guide: https://dosai.pro/docs/guide
  • Free course: https://dosai.pro/learn
  • Articles: https://dosai.pro/blog
  • Contact: adsytd1@gmail.com

License

Examples in this repository are MIT. The platform itself is a hosted commercial service.

Frequently asked questions

What is dosai-api?

dosai-api is Public REST API and MCP server of DOS AI: AI assistants (chatbots) for WhatsApp and Telegram with built-in CRM. OpenAPI spec, MCP tools, runnable examples.

How do I install dosai-api?

Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.

Is dosai-api open source?

Yes — it is hosted on GitHub at https://github.com/adsytd1/dosai-api.

Related MCP tools

Run your own MCP server? See who uses it and what to fix.

Measure it with TrackMCP