Cavyro - Agentic CRM
Cavyro is an agentic CRM, wired into the place your customers already message you.
What it can do
- Describe Resource: Introspect the CRM. Call with no resource to list all resources and global actions. Call with a resource slug to learn its filters, sort fields, supported operations, and related pe
- Query Resources: List records of a resource with optional filters, sort, pagination, and custom field filters. Call describe_resource first to learn valid filter and sort keys. limit defaults to 10 pe
- Get Resource: Fetch a single record of a resource by its numeric ID.
What data it sees
Do you need an account
An API key from the service settings is required
Cavyro is an agentic CRM, wired into the place your customers already message you. Telegram.
Pipelines, deals, meetings, automations and reporting. Your team runs it from the app or from Telegram. Your agents run it headless over MCP.
How to connect
How to connect Cavyro - Agentic CRM to Claude
The server address to paste into Claude settings:
https://cavyro--cavyro.run.tools
- Open Claude (claude.ai or the desktop app).
- Go to Settings → Connectors.
- Click Add custom connector.
- Paste the server address copied below into Remote MCP server URL and click Add.
- In a chat, click + → Connectors and switch the new connector on.
Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.
Authorization
After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.
How to connect Cavyro - Agentic CRM to ChatGPT
The server address to paste into ChatGPT settings:
https://cavyro--cavyro.run.tools
- Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
- Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
- Open Settings → Connectors and click Create.
- Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
- Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
- In a new chat open + → Apps/Connectors and enable the connector.
OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.
Authorization
On first use ChatGPT opens the service's sign-in window. Sign in and approve access.
How to connect Cavyro - Agentic CRM to Cursor
The server address to paste into Cursor settings:
https://cavyro--cavyro.run.tools
Fastest: click Open in Cursor below and confirm the prompt.
Manually:
- In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
- Paste the JSON copied below into
~/.cursor/mcp.json(per project:.cursor/mcp.jsonin the repo root). - Save the file. The server appears in the MCP list; authorize it there if asked.
Authorization
If the service needs sign-in, an authorize button appears next to the server in the MCP list.
Server tool list (9)
Raw names from tools/list. Only developers need these.
| describe_resource | Introspect the CRM. Call with no resource to list all resources and global actions. Call with a resource slug to learn its filters, sort fields, supported operations, and related perform_action slugs. Describe a resource before querying or mutating it when unsure of its fields, filters, or actions. |
| query_resources | List records of a resource with optional filters, sort, pagination, and custom field filters. Call describe_resource first to learn valid filter and sort keys. limit defaults to 10 per page (max 100). |
| get_resource | Fetch a single record of a resource by its numeric ID. |
| create_resource | Create a record of a resource. attributes is an object of field values. To set custom fields, nest a `custom_fields` object keyed by numeric definition id inside attributes (e.g. { custom_fields: { "12": "Low" } }); discover ids and required fields by querying the custom_field_definition resource filtered by entity (Deal | Contact | Company). |
| update_resource | Update a record of a resource by ID. attributes contains only the fields to change. To set custom fields, nest a `custom_fields` object keyed by numeric definition id inside attributes (e.g. { custom_fields: { "12": "Low" } }). |
| delete_resource | Archive, restore, or permanently delete a record. mode=discard archives (soft delete), restore un-archives, destroy permanently deletes. |
| search | Omnibox search across deals, contacts, companies, teams, groups, members, and saved reports. Returns top matches per type. |
| perform_action | Execute a specialized (non-CRUD) action by slug, such as move_deal, link_contact_company, bulk operations, comments, membership changes, reports, or global reads. Discover available actions and their params via describe_resource. |
| load_guidance | Load step-by-step workflow guidance for one or more topics (ids come from a resource's related_guidance or describe_resource's guidance list). Covers create flows, required custom fields, activity feed vs calendar, multi-turn continuation, and which features exist only in the web app (topic 'product-surface'). Call it before composing a create/update you are unsure about, or before telling the user something is impossible. |