Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Aspro Cloud MCP Show me all open deals in the 'New Clients' pipeline"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server for Aspro Cloud — work with CRM deals and tasks directly from AI assistants (Claude, Cursor, etc.).
Tool | Description |
| List deals with filters (pipeline, stage, assignee, status) |
| Get deal details by ID |
| Create a new deal |
| Update an existing deal |
| Delete a deal |
| List all sales pipelines |
| List pipeline stages |
Tool | Description |
| List tasks with filters (responsible, status, type, module binding) |
| Get task details by ID |
| Create a new task |
| Update an existing task |
| Delete a task |
| List all task workflows |
| List workflow stages |
Tool | Description |
| Search users by name (returns |
| Get user details by ID |
Related MCP server: aspro-mcp
Node.js 18+
Aspro Cloud account with API access
API key from your Aspro Cloud settings
Two environment variables are required:
Variable | Description | Example |
| Your company subdomain |
|
| API key from Aspro Cloud settings |
|
Your company subdomain is the part before .aspro.cloud in your workspace URL.
Add to your Cursor MCP configuration (~/.cursor/mcp.json or .cursor/mcp.json in your project):
{
"mcpServers": {
"aspro-cloud": {
"command": "npx",
"args": ["-y", "github:kazan-project-manufactory/aspo-cloud-mcp"],
"env": {
"ASPRO_COMPANY": "your_company",
"ASPRO_API_KEY": "your_api_key"
}
}
}
}git clone https://github.com/kazan-project-manufactory/aspo-cloud-mcp.git
cd aspo-cloud-mcp
npm install{
"mcpServers": {
"aspro-cloud": {
"command": "node",
"args": ["/path/to/aspo-cloud-mcp/dist/index.js"],
"env": {
"ASPRO_COMPANY": "your_company",
"ASPRO_API_KEY": "your_api_key"
}
}
}
}Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS):
{
"mcpServers": {
"aspro-cloud": {
"command": "npx",
"args": ["-y", "github:kazan-project-manufactory/aspo-cloud-mcp"],
"env": {
"ASPRO_COMPANY": "your_company",
"ASPRO_API_KEY": "your_api_key"
}
}
}
}Find user Ivan Petrov and assign him a task to prepare the contract by FridayShow me all open deals in the "New Clients" pipelineCreate a deal "Website Redesign" for client Vasily Sidorov with budget 150000List all tasks assigned to me that are in progressnpm run build # compile TypeScript
npm run dev # watch modeMIT
Create a new CRM deal (lead)
Inputs: name (required), budget, deadline, assignee_id, +7 more.
Create a new task
Inputs: name (required), type, model, module, +12 more.
Delete a CRM deal (lead) by ID
Inputs: id (required).
Delete a task by ID
Inputs: id (required).
Get a CRM deal (lead) by ID
Inputs: id (required).
Get a task by ID
Inputs: id (required).
Get detailed information about a user by ID
Inputs: id (required).
List CRM deals (leads) with optional filters
Inputs: page, active, assignee_id, pipeline_id, +1 more.
List all CRM sales pipelines
Inputs: no named parameters.
List pipeline stages, optionally filtered by pipeline
Inputs: pipeline_id.
List tasks with optional filters.
By default returns only NON-ARCHIVED tasks (archive_status=0). "Active tasks" and "tasks" always means non-archived. To get archived tasks, pass archive_status=10.
Status values (use 'status' param): 1 = New (created but not started — most tasks accumulate here as backlog) 3 = In Progress (actively being worked on right now) 4 = Waiting Review (done by assignee, pending verification) 5 = Done (completed but not yet archived)
To find tasks truly in progress use status=3. To find all incomplete tasks use status=1, 3, or 4.
Type values: 0=Task, 1=Inbox, 20=Event, 30=Template
Inputs: page, type, model, module, +6 more.
List all task workflows
Inputs: no named parameters.
List workflow stages, optionally filtered by workflow
Inputs: workflow_id.
Search users by name or email. Returns id, name and username (email) — use id as responsible_id for tasks or assignee_id for deals
Inputs: query (required).
Update an existing CRM deal (lead)
Inputs: id (required), name, active, budget, +11 more.
Update an existing task
Inputs: id (required), name, rating, report, +8 more.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 16 tools
Tools cleanly separate into leads, tasks, workflow/pipeline configuration, and users. Each tool targets a unique resource-action pair, such as list_pipelines versus list_pipeline_stages, so there is no real ambiguity.
All tool names follow a consistent verb_noun pattern in snake_case (list_*, get_*, create_*, update_*, delete_*, search_*). This makes the toolset predictable and easy to navigate.
At 16 tools, the server is slightly above the ideal 3-15 range but still well-scoped. The count is justified by covering two major domains (leads and tasks) plus user lookup, with minimal redundancy.
Both leads and tasks have full CRUD coverage, complemented by pipeline/stage and workflow/stage listing. Minor gaps exist, such as no user listing (only search) and no CRUD for pipelines/workflows, but these are typically configuration-level and do not block core workflows.
Operate Obriym CRM from your AI assistant: leads, deals, orders, catalog, stock, marketplaces.
Operate the Plixana CRM from any AI: contacts, deals, quotes, WhatsApp and metrics.
Read deals, persons, organizations, activities and pipelines; create and update CRM records.
Connect AI to your Attio CRM. Manage contacts, companies, deals, and sales pipelines. Create tasks…
