--- title: "Unwrap MCP server" url: "https://martechdb.com/vendors/unwrap" markdown_url: "https://martechdb.com/vendors/unwrap.md" api_url: "https://martechdb.com/api/v1/vendors/unwrap.ai" updated: "2026-10-27" --- # Unwrap MCP server Yes. Unwrap publishes an official MCP server at https://nlp.api.production.unwrap.ai/mcp. It's hosted. It offers 16 tools. We last checked it on 5 Nov 2026. MartechDB lists only servers the vendor publishes itself, never community servers. **Key facts:** As of 5 Nov 2026, Unwrap's official MCP server scores 65/100 (provisional) on MartechDB's Agent Readiness Index (v1.1). It answered 9 of our 9 checks in the last 90 days and has 16 tools named in its documentation. - Website: [unwrap.ai](https://unwrap.ai) - Categories: [User & market research](https://martechdb.com/categories/user-market-research.md) ## Review Unwrap's Unwrap MCP scores 65/100 on MartechDB's Agent Readiness Index: easy to connect an AI agent to, with a few gaps. The good: - Hosted by Unwrap: connect by URL, with nothing to install - Documented, with 16 tools known - Answered 100% of our checks in the last 90 days Not checked yet: how you sign in; what agent access costs. ## Agent Readiness Index: 65/100 (provisional) How friendly Unwrap is to AI agents, from its best official MCP server. Anything not yet researched scores nothing, so this score may rise once it is. Methodology v1.1: https://martechdb.com/methodology. - Official MCP server: 30/30 (Published by the vendor) - Hosted by the vendor: 25/25 (Connect by URL, nothing to install) - OAuth sign-in: pending (Sign-in: see vendor docs) - Documented tools: 10/10 (A docs page, and its tools are known) - Free to start, pay as you go: 0/15 (Not stated by the vendor) ## Unwrap MCP - Address: https://nlp.api.production.unwrap.ai/mcp - Runs: Hosted - Sign-in: Sign-in: see vendor docs (`unknown`) - Official MCP Registry: not listed - Documentation: https://docs.unwrap.ai/articles/6412771011-unwrap-mcp - How we know it's official: Documented on Unwrap's own site, at docs.unwrap.ai - First seen: 2026-10-27 - Last checked: 2026-11-05 - Recent checks: 7 of the last 7 reachable - Uptime: 100% (9 of 9 checks reachable since 2026-10-28) ### Tools (16) The server needs sign-in before it lists its tools, so these are as the vendor's documentation names them ([source](https://docs.unwrap.ai/articles/6412771011-unwrap-mcp)), read on 2026-11-05. They may be out of date. - `list_views`: Lists the authenticated org's available views, including view\_id, view\_name, and org\_name. - `leave_feedback`: Leave feedback on the MCP directly to the Unwrap team - `get_started`: Call this first when using Unwrap. Returns the core usage guide, including the data model and recommended workflows. - `list_feedback_integrations`: Lists the feedback integrations connected to a view and summarizes source coverage. - `search_segments`: Semantically searches segment fields and values relevant to a question. - `list_segment_field_values`: Lists the exact allowed values for a segment field so filters use the correct spelling. - `discover_filter_schema`: Returns all available filter fields for a view so clients can discover valid filtering options up front. - `search_groups`: Semantically searches taxonomy groups to find issues or themes relevant to a query. Supports optional filtering. - `search_actionable_groups`: Returns the most actionable groups for a question, with optional filtering and numeric segment sorting. - `plot_chart`: Generates charts or tables over time or by breakdown for trends, rankings, share comparisons, and other visual analyses. - `sample_feedback_entries`: Creates a named sample of feedback entries, either as a representative random sample or a targeted semantic sample. - `analyze_entry_text`: Runs a custom instruction or question across all entries in a saved sample and returns prevalence statistics plus example results. - `classify_feedback_entries`: Classifies entries in a saved sample into predefined labels and creates sub-samples for each resulting label. - `search_documentation`: Searches Unwrap's official product docs (public help center) and returns a ranked list of matching article titles and URLs - `read_documentation_article`: Reads one or more Unwrap docs articles and returns them as markdown. - `query_feedback_tool`: Allows users to query for Unwrap data and statistics using Unwraps query syntax ### Connect it Claude Code: ```sh claude mcp add --transport http unwrap https://nlp.api.production.unwrap.ai/mcp ``` - Add to Cursor: - Add to VS Code: - Claude.ai and Claude Desktop: Customize, Connectors, "+", Add custom connector, then paste https://nlp.api.production.unwrap.ai/mcp - ChatGPT: Settings, Apps, Advanced settings, turn on Developer mode, Create, then paste https://nlp.api.production.unwrap.ai/mcp (this usually works only with servers that use self-serve sign-in or none) JSON for Cursor, Windsurf and other clients that connect to hosted servers: ```json { "mcpServers": { "unwrap": { "type": "http", "url": "https://nlp.api.production.unwrap.ai/mcp" } } } ``` ## Questions ### Does Unwrap have an official MCP server? Yes. Unwrap publishes its MCP server itself. Unwrap's own documentation describes it. MartechDB only lists servers a vendor publishes, never community copies. ### What is the Unwrap MCP server URL? The address is https://nlp.api.production.unwrap.ai/mcp. ### How do I connect Unwrap MCP to Claude, ChatGPT or Cursor? In Claude, add https://nlp.api.production.unwrap.ai/mcp as a custom connector (Customize, Connectors, Add custom connector). In Cursor, use the Add to Cursor link on MartechDB's page, or paste the JSON settings into your mcp.json. In Claude Code, run: claude mcp add --transport http unwrap https://nlp.api.production.unwrap.ai/mcp ### What can the Unwrap MCP server do? It offers 16 tools, including list\_views, leave\_feedback, get\_started, list\_feedback\_integrations and search\_segments (as its documentation names them, read on 5 Nov 2026). ### Is the Unwrap MCP server in the official MCP Registry? No. Unwrap hasn't published it to the official MCP Registry. ### Is the Unwrap MCP server working? Yes. It answered our most recent check. We last checked it on 5 Nov 2026. ### What are the alternatives to Unwrap's MCP server? In User & market research, the most agent-friendly alternatives with an official MCP server are Condens Supercharge (91/100), CB Insights (85/100), Mintel (85/100), Dovetail (85/100) and Rally (85/100). Unwrap scores 65/100 on the same index. ## Change history - 2026-10-27: Added to MartechDB with Unwrap MCP ## Alternatives to Unwrap's MCP server In User & market research, the most agent-friendly first: - [Condens Supercharge](https://martechdb.com/vendors/condens-supercharge.md) (condens.io), Agent Readiness Index 91/100 - [CB Insights](https://martechdb.com/vendors/cb-insights.md) (cbinsights.com), Agent Readiness Index 85/100 - [Mintel](https://martechdb.com/vendors/mintel.md) (mintel.com), Agent Readiness Index 85/100 - [Dovetail](https://martechdb.com/vendors/dovetail.md) (dovetail.com), Agent Readiness Index 85/100 - [Rally](https://martechdb.com/vendors/rally.md) (rallyuxr.com), Agent Readiness Index 85/100 ## Get this data - API: `curl https://martechdb.com/api/v1/vendors/unwrap.ai` - MCP: `claude mcp add --transport http martechdb https://martechdb.com/mcp`, then ask about Unwrap. - Web page: https://martechdb.com/vendors/unwrap