ClosedLoop AI MCP Server
First-party hosted MCP server over Streamable HTTP with OAuth 2.1. Two regional deployments (US and EU). Exposes product-intelligence tools over the same data the /v1 REST API reads, plus one MCP prompt. Documented for Claude Code, Claude Desktop/web/Cowork, Cursor, LiteLLM and any MCP HTTP client; machine-to-machine access uses OAuth client_credentials with private_key_jwt or a shared secret.
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.
Descriptor
Candidate descriptor · transport
Tools
get_overview— High-level summary of the product-intelligence landscape. Documented as the starting point.get_facets— Aggregated counts by dimension; top 20 values with counts per dimension.get_trends— Time-bucketed counts for trend analysis, with unique customers and average frustration per period.search_customers— Find customers by name, industry, country or engagement metrics; every result carries revenue context.get_customer— Full customer profile -- CRM data, deals, contacts, intelligence summary, strategic context.search_insights— Hybrid (keyword + semantic) search across product insights; returns 300-character content previews and a customers_mentioned summary.get_insight— Full detail for one insight -- verbatim content, pain point, workaround, use case, business outcomes, kano category, reporter details.search_signals— Search strategic context -- satisfaction, churn reasons, competitor mentions, buying behavior.get_signal— Full detail for one context record, including source URL back to the original conversation.get_competitors— Configured competitors with mention counts, products, and whether each is a direct competitor. No parameters.search_opportunities— Biggest Themes ranked by business impact. Tool name retains the legacy "opportunities" identifier for compatibility.get_opportunity— Full Theme detail -- top 50 quotes, customer list with IDs and deal values, total_won_deal_value, and associated Features.
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.