Capsule MCP Server
First-party Model Context Protocol server for Capsule CRM, published by Zestia Ltd (the company that operates Capsule - the capsulecrm.com CAA record names caa-iodef@zestia.com, and the repository is Apache-2.0 under github.com/zestia). Announced on the Capsule developer changelog on 15 April 2026 as a private beta. It is a LOCAL server: an AI assistant runs it as a Docker container over stdio on the operator's own machine, and it calls the Capsule v2 REST API directly with a personal API token. There is no hosted/remote MCP endpoint an agent can POST to.
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Documentation
Documentation link · transport
Tools
list_contacts— Retrieve Contacts with comprehensive filtering abilityget_contact— Get Contact by IDlist_opportunities— Retrieve Opportunities with comprehensive filtering abilityget_opportunity— Get Opportunity by IDcalculate_value_of_opportunities— Retrieves Total & Projected Values for Opportunities with comprehensive filtering abilitylist_projects— Retrieve Projects with comprehensive filtering abilitylist_contact_custom_fields— Retrieves Custom Fields defined for Contactslist_opportunity_custom_fields— Retrieves Custom Fields defined for Opportunitieslist_project_custom_fields— Retrieves Custom Fields defined for Projectsget_contact_custom_field— Get Contact Custom Field Definition by IDget_opportunity_custom_field— Get Opportunity Custom Field Definition by IDget_project_custom_field— Get Project Custom Field Definition by IDlist_custom_fields_for_contact_data_tag— List Custom Fields defined for a Contact DataTaglist_custom_fields_for_opportunity_data_tag— List Custom Fields defined for an Opportunity DataTaglist_custom_fields_for_project_data_tag— List Custom Fields defined for a Project DataTaglist_pipelines— Retrieves Sales Pipelines defined for Opportunities with optional searching by nameget_pipeline— Get Pipeline by IDlist_milestones— Retrieves Milestones defined across all Sales Pipelineslist_milestones_by_pipeline— Retrieves Milestones for a given Sales Pipelineget_milestone— Get Milestone by IDlist_lost_reasons— Retrieves Lost Reasons with optional searching by nameget_lost_reason— Get Lost Reason by IDlist_boards— Retrieves Project Boards with optional searching by nameget_board— Get Project Board by IDlist_stages— Retrieves Stages defined across all Project Boardsget_stage— Get Project Stagelist_stages_by_board— Retrieves Stages for a given Project Boardlist_contact_tags— Retrieves Tags defined for Contactslist_opportunity_tags— Retrieves Tags defined for Opportunitieslist_project_tags— Retrieves Tags defined for Projectsget_contact_tag— Get Contact Tag Definition by IDget_opportunity_tag— Get Opportunity Tag Definition by IDget_project_tag— Get Project Tag Definition by IDlist_users— Retrieves all Usersget_user— Get User by IDget_current_user— Get current Userlist_teams— Retrieves all Teams and Team membersget_team— Get Team by IDlist_tasks— Retrieve Tasks with basic filtering abilityget_task— Get Task by IDget_track— Get Track by IDlist_tracks_for_contact— List Tracks for specified Contactlist_tracks_for_opportunity— List Tracks for specified Opportunitylist_tracks_for_project— List Tracks for specified Projectlist_activity— Retrieve Activity with basic filtering abilitylist_entries_for_contact— Retrieve Entries for specified Contactlist_entries_for_project— Retrieve Entries for specified Projectlist_entries_for_opportunity— Retrieve Entries for specified Opportunityget_entry— Get Entry by ID
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.