Xenmark MCP server
OfficialClick on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Xenmark MCP server Anything new for me in Xenmark today?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Xenmark MCP server
An MCP server that lets AI assistants — Claude, Cursor, VS Code and others — read your Xenmark drawing-review data: projects, drawings, revisions, comments, replies and your notification inbox. Read-only, runs on your own machine, uses a token you create inside Xenmark.
Status: released. On npm as xenmark-mcp and in the official MCP Registry as io.github.Xenmark/xenmark-mcp.
What you can ask
"Anything new for me in Xenmark?" / "Who mentioned me today?"
"Which projects am I on, and what's my role?"
"What's still open on drawing 1001-300, Rev. B?"
"List the unresolved comments on that revision and who raised them."
"What did Greta reply on comment #7?"
Every answer carries a link straight into Xenmark.
Related MCP server: mooteam-mcp
What it never does
It never writes to Xenmark, never sees your password, never returns e-mail addresses, files, billing or account roles, and never reaches projects you are not a member of. It talks to exactly one server: https://api.xenmark.app, the official read-only Integration API (contract).
Get a token
In Xenmark: profile → Account & Security → Connected apps → Connect an app → "Personal API token (Postman, GitHub)" → Generate. The token is shown once; keep it in the assistant's config only. Revoke it any time from Connected apps.
Install
Requires Node.js 18 or newer. The server runs with npx -y xenmark-mcp — nothing to clone or build. (To run from a source checkout instead: npm install && npm run build, then point your assistant at dist/index.js.)
Claude Desktop — edit claude_desktop_config.json (Settings → Developer → Edit Config) and add:
{
"mcpServers": {
"xenmark": {
"command": "npx",
"args": ["-y", "xenmark-mcp"],
"env": { "XENMARK_TOKEN": "xmk_live_YOUR_TOKEN_HERE" }
}
}
}Restart Claude Desktop; the Xenmark tools appear under the tools icon.
Cursor — Settings → MCP → Add new server, same command, args and env.
VS Code (Copilot agent mode) — add the same entry under "servers" in .vscode/mcp.json or your user mcp.json.
From a source checkout, replace the command with node and the args with the full path to dist/index.js.
Support
support@xenmark.app · Security: see SECURITY.md. Never post a token anywhere public.
Available Tools
9 toolsxenmark_find_drawingARead-onlyIdempotent
Find drawings by drawing number or name fragment across the user's projects (or within one project) and return their ids, project, revision_count and web_url. Use this when the user names a drawing rather than an id. Walks at most 20 projects and says so if truncated.
Inputs: query (required), project_id.
xenmark_list_commentsCRead-onlyIdempotent
Comments on one revision: id, comment_number (quote this to people), title, description, status, author_display_name, page, reply_count, annotation_count, web_url, plus a replies_preview of up to 3 replies and replies_truncated.
Inputs: revision_id (required), cursor, include_replies_preview.
xenmark_list_drawingsARead-onlyIdempotent
Drawings in one project: id, drawing_number, name, revision_count, created_at, web_url. Needs the project id from xenmark_list_projects or xenmark_find_drawing.
Inputs: project_id (required), cursor.
xenmark_list_projectsCRead-onlyIdempotent
Projects the user owns or is a member of: id, name, description, company_name, status (active/archived), my_role, created_at, updated_at, web_url.
Inputs: cursor.
xenmark_list_repliesARead-onlyIdempotent
All replies on one comment, paginated: id, author_display_name, body, created_at, edited_at.
Inputs: comment_id (required), cursor.
xenmark_list_revisionsARead-onlyIdempotent
Revisions of one drawing: id, revision_label, original_filename, size_bytes, content_type, created_at, web_url. Files themselves are never available.
Inputs: drawing_id (required), cursor.
xenmark_recent_activityARead-onlyIdempotent
The user's Xenmark notification inbox, newest first: new comments, replies, mentions and status changes on drawings the user is part of. Each row has actor_name, project_name, drawing_number, revision_label, comment_number, title, preview, mention_labels, old_status/new_status (status changes), read, created_at and a web_url deep link into Xenmark. Use web_url for links - never build Xenmark URLs.
Inputs: limit, unread_only.
xenmark_review_summaryARead-onlyIdempotent
Comment-status rollup for one or more revisions (up to 100): total_comments, open_count, progress_count, closed_count, last_activity_at per revision. Revisions the user cannot access are silently omitted.
Inputs: revision_ids (required).
xenmark_whoamiARead-onlyIdempotent
Identify the Xenmark account behind the configured token: user_id, display_name, company. Never returns e-mail, plan, billing or role.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 9 tools
Each tool targets a distinct resource or action: identity, notifications, projects, drawings, revisions, comment rollup, comments, replies, and drawing search. The only potential overlap (list_drawings vs. find_drawing) is explicitly clarified by descriptions, so an agent can reliably choose the right tool.
All names use a consistent snake_case style with a uniform 'xenmark_' prefix, which makes them predictable and readable. However, the semantic pattern is slightly mixed: most follow list_<noun>, but there are also find_drawing, review_summary, recent_activity, and whoami, so it is not a strict verb_noun convention throughout.
Nine tools is well-scoped for a read-only data-access server covering projects, drawings, revisions, comments, and activity. Each tool earns its place without redundancy, and the set avoids the bloat that would come from exposing every possible field or operation separately.
The read surface is thorough: identity, activity, projects, drawings, revisions, comments, replies, and a review summary are all covered. However, write operations that are central to a review workflow—posting comments/replies, changing comment status, or marking activity read—are entirely absent, creating a notable lifecycle gap.
Maintenance
Related MCP Connectors
Read-only access to Cogram projects, meetings, email, RFIs and drawings for architects and engineers
Read-only access to your VeloCapture leads, RFPs, contacts and drafts from an AI assistant.
Ask your AI about construction and ad-platform data. Read-only on your systems, never writes to them
Read-only AI access to HAVN properties, leads, tasks, files, media, and analytics.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables read-only file-management operations from AI assistants, including health checks, connection and folder listings, search, share-link resolution, metadata retrieval, and on-demand document reading.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants to read Moo.team task context directly through the HTTPS API, including descriptions, attributed comments, and file attachments. It is read-only and requires no browser automation.7 npmMIT
- AlicenseBqualityBmaintenanceOpen-source MCP server for Autodesk Revit 2022 to 2027: read, audit and edit live models with 89 tools, one Undo entry per change, and a workstation read-only lock.8917MIT
- AlicenseAqualityBmaintenanceEnables AI assistants such as Claude to read fields, boundaries, field operations, equipment, machine health, products, operators, guidance lines, and work plans from a John Deere Operations Center account on the user's own computer. It is read-only and cannot change anything in Operations Center.22MIT