adobe-analytics-mcp
Adobe publishes an official, Adobe-hosted (remote) Model Context Protocol server for Adobe Analytics. It lets MCP clients (Claude, ChatGPT, Cursor) discover components (report suites, dimensions, metrics, segments, date ranges, projects) and run ranked/trended reports in natural language. Requests run under the authenticated user's identity and enforce existing Adobe Analytics permissions; the user's product profile must carry the "MCP Access" permission item.
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.
Endpoint
Hosted endpoint · transport http
Connect
This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):
For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:
If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:
Tools
describeAa— Starting point for learning how to use the Adobe Analytics MCP tools.setSessionDefaults— Sets the default report suite ID and global company ID for the session.getDefaultSessionReportSuiteId— Returns the current default report suite ID.clearDefaultSessionReportSuiteId— Clears the default report suite ID.findCompanies— Lists all companies accessible to the current user.findReportSuites— Finds report suites accessible within a specific company.findDimensions— Discovers dimensions available for a given report suite.findMetrics— Identifies metrics available for the given report suite.findSegments— Locates segments accessible to the user.findDateRanges— Finds saved date range components available to the user.findProjects— Discovers workspace projects accessible to the user.runReport— Primary tool for pulling analytics data (ranked report, one dimension + one or more metrics over a date range).searchDimensionItems— Retrieves the top dimension items for a given dimension.describeSegment— Returns metadata for a given segment.describeCalculatedMetric— Shows the metric formula and base metrics used by a calculated metric.describeProject— Shows details about a workspace project.listComponentUsage— Lists the most-used components ranked by frequency.listFrequentlyUsedWith— Lists components frequently used together in reports.listSimilarTo— Lists components similar to a specified component.upsertSegment— Creates a new segment or updates an existing one.upsertCalculatedMetric— Creates or updates a calculated metric.createDateRange— Creates a new reusable date range component.upsertProject— Creates a new workspace project or updates an existing one.
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.