Skip to main content

​
Overview

Use this page when you want to connect an MCP-compatible client to Cevoid and explore analytics or edit your BrandKit. The Cevoid MCP server is Cevoid’s hosted MCP server for connecting AI clients to your Cevoid workspaces. You can use it to give tools like Claude, Cursor, and ChatGPT secure access to Cevoid context through a single MCP endpoint. You can query UGC, Loyalty, and Profiles analytics; manage reports and dashboards; and edit the BrandKit used by reviews and emails. BrandKit tools manage styling, color schemes, fonts, and custom SVG icons. If you need direct REST integrations from your own application code, use the API Reference instead.

​
When to use MCP

Use MCP when you want an AI client to query analytics, set up reports and dashboards, or update your brand styling without building your own API layer first. Use the API Reference instead when you want direct REST integrations from your own application code.

​
Connect

Use https://mcp.cevoid.com/mcp as the MCP server URL. Use a client that supports MCP over streamable HTTP and OAuth-based authentication, such as Claude, Cursor, or ChatGPT.

​
Quickstart

  1. Open an MCP-compatible client such as Claude, Cursor, or ChatGPT.
  2. Point it at https://mcp.cevoid.com/mcp.
  3. Complete the OAuth flow and choose which workspaces and permissions to grant.
  4. Ask your client to list your workspaces with list-workspaces and discover the tools you need with tool-search.
  5. The client uses execute-tool to call a discovered tool with its returned schema. Independent reads can use execute-batch; writes must run individually.

​
Verify the connection

Start by asking your client to list the workspaces and tools available to your connection. Try a prompt like:
If the connection works, your MCP client should return your authorized workspaces and tool categories instead of a generic model-only answer.

​
Authentication

The Cevoid MCP server uses OAuth 2.1 for authentication. Access tokens are short-lived, resource-bound to the Cevoid MCP endpoint, and carry both principal and authorized workspace identity. Clients can maintain sessions with rotating refresh tokens.
  • Access is scoped to the workspace or workspaces selected during authorization.
  • Analytics reads require analytics:read. This includes entity and profile labels used in analytics dimensions and intentional filter searches. Report and dashboard writes require analytics:write.
  • BrandKit reads, font discovery, and icon discovery require brandkit:read. Styling changes, color-scheme changes, font uploads/imports, and icon overrides require brandkit:write.
  • The connect page lets you choose which permissions to grant. Discovery only returns tools permitted by your connection. Reconnect an existing client to grant BrandKit permissions.
  • Clients should use the advertised Protected Resource Metadata and include the Cevoid MCP endpoint as the OAuth resource.
  • Clients can identify themselves with OAuth Client ID Metadata Documents or Dynamic Client Registration.

​
Client implementer details

Use the discovery documents instead of hard-coding OAuth endpoints where your client supports discovery.
  • MCP endpoint: https://mcp.cevoid.com/mcp
  • OAuth resource: https://mcp.cevoid.com/mcp
  • OAuth scopes: analytics:read, analytics:write, brandkit:read, and brandkit:write. Request only the permissions your client needs.
  • Protected Resource Metadata: https://mcp.cevoid.com/.well-known/oauth-protected-resource/mcp
  • Authorization Server Metadata: https://mcp.cevoid.com/.well-known/oauth-authorization-server
  • Client identification: OAuth Client ID Metadata Documents are supported. Dynamic Client Registration is available as a fallback.
  • Token revocation: supported through the advertised OAuth revocation endpoint.
Access tokens expire after 15 minutes. Refresh tokens rotate on every use and expire 30 days after the latest refresh. If a connection is not used before the refresh token expires, the client needs to reconnect through OAuth.

​
Rate limits

Tool calls are rate limited per authenticated principal and tool.
  • Analytics queries, report execution, and all analytics/BrandKit writes: 20 requests per minute.
  • Other analytics reads, BrandKit reads, and the four discovery/execution tools: 60 requests per minute.
Calls through execute-tool or execute-batch also count toward the invoked tool’s own limit.

​
Available tools

Your client discovers domain tools through tool-search, then calls their canonical IDs through execute-tool. Search without a query to browse categories. The table lists both the discovery/execution tools and the domain tools they expose.
CategoryToolDescription
Workspacelist-workspacesList the workspaces this MCP session can access.
Discovery and executiontool-searchDiscover authorized tools and their input schemas.
execute-toolRun a discovered tool using its canonical ID.
execute-batchRun independent read-only calls together. Writes are not accepted.
Analyticsanalytics.list-reportsList saved analytics reports and curated presets for an authorized workspace.
analytics.run-queryQuery Cevoid analytics directly with a schema-first query object.
analytics.get-query-schemaInspect the supported analytics query schema for a module.
analytics.get-reportGet metadata for a saved analytics report by report ID.
analytics.run-reportExecute a saved analytics report by report ID and date range.
analytics.list-dimensionsList the currently available analytics dimensions and metadata for a module.
analytics.get-filter-valuesGet valid values for a specific analytics filter.
analytics.create-reportValidate and create a custom analytics report.
analytics.update-reportValidate and update a custom analytics report.
Dashboardanalytics.list-dashboardsList analytics dashboards in a workspace.
analytics.get-dashboardGet a dashboard and its report panels.
analytics.create-dashboardCreate a dashboard with validated or automatically placed panels.
analytics.update-dashboardUpdate a custom dashboard and its panel layout.
BrandKitbrandkit.getRead your live BrandKit settings and revision.
brandkit.updateUpdate styling, typography, and font or icon-pack assignments.
brandkit.create-color-schemeCreate a named color scheme, optionally copying an existing scheme.
brandkit.rename-color-schemeRename a color scheme and update its references.
brandkit.delete-color-schemeDelete a color scheme and return review/email assignments to defaults. At least one scheme must remain; change any popup assignment first.
brandkit.list-fontsBrowse default and workspace fonts.
brandkit.prepare-font-uploadPrepare an upload for a local font file.
brandkit.complete-font-uploadValidate and register an uploaded font.
brandkit.import-font-from-urlImport a font from a public file URL.
brandkit.list-icon-packsBrowse available icon packs.
brandkit.list-iconsInspect editable icon slots and their current SVGs.
brandkit.set-iconsReplace existing icon slots with custom SVGs.
brandkit.reset-iconsRestore selected icons to their icon-pack or bundled defaults.
Workspace IDs are returned by list-workspaces; reuse them unchanged. Report IDs use the public rpt_… format and dashboard IDs use dsh_…. Treat these IDs as opaque and reuse returned values for later get, run, update, and dashboard-panel operations. Analytics filter values are a separate contract. A returned value is an opaque token valid for that filter and authorized workspace; its format may vary. Reuse it unchanged and do not treat it as a resource ID. Profile filter discovery requires at least two search characters and returns no more than 20 minimal label/token pairs. Analytics list tools return compact selection summaries; matching get tools return complete public definitions. Result counts use returnedRowCount, meaning rows actually returned after limits. analytics.run-report.executedQuery records the effective execution settings needed to interpret saved-report results. BrandKit changes save live and update open previews. Incoming changes replace unsaved BrandKit edits in an open editor. There is no draft or publish step. Settings, scheme, and icon writes do not require a revision; later writes can overwrite earlier values. Omitted settings stay unchanged, and null resets a setting to its default or inherited value. Dimensions use pixels, line height is a multiplier, and letter spacing uses em. For a local font, prepare the upload, send the file to the returned URL, then complete registration. You can also import a public WOFF2, WOFF, TTF, or OTF file up to 10 MB; URL redirects are rejected. Assign the returned font ID to typography or buttons with brandkit.update. Custom icons replace existing editable slots. Supply a complete monochrome SVG with a viewBox, up to 16 KiB per icon. Active content and external resources are rejected. Icons inherit the theme color; rating stars use the BrandKit star design setting. Reuse font and icon-pack IDs returned by discovery unchanged. Available analytics resources (require analytics:read):
  • cevoid://analytics/query-schema
  • cevoid://analytics/dimensions
  • cevoid://analytics/filters
  • cevoid://analytics/filter-values
  • cevoid://analytics/reports
  • cevoid://analytics/capabilities

​
Example prompts

  • “What reports do I already have for UGC performance?” Starts with analytics.list-reports.
  • “Show me the top performing posts for the last 30 days.” Routes to analytics.run-query.
  • “What types of analytics queries can you run for UGC?” Uses analytics.get-query-schema.
  • “Which workspaces can I access in this MCP session?” Uses list-workspaces.
  • “Create a monthly performance report and add it to a dashboard.” Uses the report and dashboard write tools after write-scope consent.
  • “Set my BrandKit accent color to green and make buttons rounder.” Uses brandkit.get and brandkit.update after BrandKit write-scope consent.
  • “Import this font file and use it for headings.” Uses the BrandKit font tools, then assigns the returned font with brandkit.update.
  • “Generate a simple close icon and apply it to my BrandKit.” Inspects brandkit.list-icons, then applies the SVG with brandkit.set-icons.