TheDeskMonitor MCP server
Which servers in the official MCP registry are TheDeskMonitor's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-20
- Registry namecom.thedeskmonitor/mcpverified in the MCP registry
The registry name sits under thedeskmonitor.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-20
- Tools24
- Server calls itselfDeskMonitor MCP Server
- Server version1.6.0
- Protocol version2025-06-18
On 2026-10-20 the server answered initialize and tools/list without a sign-in. First answer in 594 ms.
- Its tools do none of the product's use cases we checked: calculate payroll cost per team member from rate cards; track project budget burn rate in real time.
- Checked on 2 of the 7 days it takes to judge reliability.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
- What an agent can do with it0 of 2 use cases
- Answeredmeasuring2 of the 7 daily checks it takes to print a share
- Median first answer539 ms
- Space in an agent's context≈ 4,144 tokensthe definitions of all its tools (24), which an agent carries on every turn
- Tool definitionsA · 98 of 100
- Typed results24 of 24 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 3 of 24
What an agent can do with it
- not sure · log hours and idle time automatically into timesheets
- cannot · calculate payroll cost per team member from rate cards
- cannot · track project budget burn rate in real time
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
get_started_guideReturns a role-scoped welcome message and curated sample questions to help you get started with DeskMonitor AI. Use when a new user asks 'what can I do?', 'what can I ask?', or 'how do I get started?' Call this first when connecting. Do…
get_data_dictionaryReturns the schema of queryable data — what fields exist, their meaning, and which tools expose them. Includes the RetentionPolicy entity — how long screenshots and monitoring data are kept per plan. Use when the user asks 'what data…
switch_to_demoSwitches to DeskMonitor demo mode with synthetic data. Returns demo tenant info and suggested queries. Use when the user wants to explore without a real account. Use a dm_demo_* API key to call data tools in demo mode.
switch_to_productionSwitches back to production mode and confirms your real tenant context from your auth token. Use when the user wants to see their real company data after exploring demo mode.
get_demo_scenariosReturns 5 guided scenario walkthroughs using the demo tenant's synthetic data. Use when the user wants to see example queries or guided tours of DeskMonitor capabilities.
get_dashboard_summaryReturns the dashboard KPIs for the current user — hours worked today, team productivity score, pending approvals, active headcount. Use when the user asks 'how is my team today?', 'am I clocked in?', 'what's my summary?'. Do NOT use for…
list_employeesLists employees visible to the current user based on their role. Supports pagination and name search. Use when the user asks 'who is on my team?', 'list all employees', or wants a roster. Use get_employee_details for information about ONE…
get_employee_detailsReturns the full profile for a specific employee including role, team, clock-in status, and recent activity. Use when the user asks about ONE specific person. Use list_employees for multiple people. Use 'me' as employee_id for the…
list_my_timesheetReturns the authenticated user's time log entries for a date range. Use when the user asks 'how many hours have I worked?', 'show me my timesheet', or 'what did I work on yesterday?'. Cannot query another person's timesheet — use…
summarize_team_hoursAggregates hours worked by the manager's team for a given period. Requires Manager role or above. Use when the manager asks 'how many hours did my team work this week?', 'show me team hours', or 'who worked the most hours?'. Do NOT use…
list_pending_approvalsReturns timesheets pending approval in the manager's team. Requires Manager role or above. Use when the manager asks 'show me pending approvals', 'who needs sign-off?', or 'any outstanding timesheets?'. Read-only -- this tool LISTS…
list_recent_activityReturns a daily aggregate activity feed scoped to the authenticated user, including clock events, timesheet submissions, and approval actions. Use when the user asks 'show me recent activity', 'what happened today?', or 'what did I do…
get_workload_alertsReturns workload alerts — team members with unusual hours, employees not yet clocked in, timesheet gaps. Use when the manager asks 'who needs attention?', 'any anomalies today?', 'any warnings?', or 'are there any issues?'.
get_productivity_overviewReturns productivity scores and active/idle time ratios for an employee or team. Use when the user asks 'what\'s my productivity score?', 'how productive was the team?', or 'show me active vs idle time'. Employee sees own data only…
clock_inClock the authenticated user in to start a new work session. Creates a TimeLog entry in DeskMonitor. Use when the user says 'clock me in', 'start my shift', 'I am starting work', or any attendance start phrase. Supports optional GPS…
clock_outClock the authenticated user out to end their current work session. Finalises the TimeLog and generates gap-fill blocks. Use when the user says 'clock me out', 'end my shift', 'I am done for the day', or any attendance end phrase…
invite_staffInvite a staff member to join your DeskMonitor workspace by email. Use when the user asks to 'add an employee', 'invite a team member', 'send a team invite', 'onboard someone new', or 'invite [name] to my workspace'. The invite is sent by…
get_capabilitiesReturns a structured list of DeskMonitor AI capabilities grouped by user role AND plan entitlements. Includes MCP / AI assistant plan entitlements (Community=No MCP; Starter/Professional/Business/Enterprise=Yes MCP). Use when a new user…
get_pricing_and_plansReturns DeskMonitor pricing plans and subscription details including MCP / AI access entitlement per plan, and per-plan retention periods for screenshots and monitoring data. Plans: Community (free, no MCP), Starter ($14/mo, MCP…
start_free_trialReturns the DeskMonitor free trial sign-up URL and onboarding instructions. Use when the user says 'I want to sign up', 'start a free trial', 'how do I get started?', 'create an account', 'I want to use DeskMonitor'. This is an…
ask_workforceUse when the user asks a free-form, open-ended question about their workforce that you are not sure which other tool answers — for example: 'Which team has the highest cost-to-output?', 'How is my team performing?', 'Who should I talk to…
get_analytics_questionsReturns demand intelligence captured from ask_workforce calls: recent verbatim admin questions, top question themes with counts, and the most-requested 'period' argument values across all tools. Use when the admin asks: 'What questions…
get_analytics_overviewReturns platform-level DeskMonitor analytics — AI/MCP queries served (from the internal McpAuditLogs table), web sessions, active unique visitors (1-day, 7-day, 28-day windows) and top referring sources (from Cloudflare Web Analytics when…
get_analytics_feature_usageReturns a breakdown of which DeskMonitor MCP tools users are calling most — sourced from the internal McpAuditLogs table, grouped by ToolName (top-N tool call counts for the period). Use when the user asks: 'which MCP tools are most…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"thedeskmonitor": {
"type": "http",
"url": "https://api.thedeskmonitor.com/api/mcp/v1"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http thedeskmonitor https://api.thedeskmonitor.com/api/mcp/v1claude.ai, ChatGPT and other clients: add https://api.thedeskmonitor.com/api/mcp/v1 as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.