// MCP TOKEN COST

The OneUptime MCP server costs 226,700 tokens before the first call.

Every request your agent makes carries every tool definition this server exposes — context your code, documents and conversation can't use, mostly for tools the agent never calls. You don't need them all in the window, and you don't have to pay for them.

QUICK ANSWER The OneUptime MCP server's 223 tool definitions consume 226,700 tokens — 113% of a 200k context window, and 130× the median MCP server (1,746 tokens). A scoped grant exposing only the tools you use cuts that roughly in proportion.

MEASURED FROM SCHEMAS tiktoken o200k_base · rank #8 of 15,192 measured servers · refreshed every build Method →

// CONTEXT WINDOW SHARE

What that costs before your agent starts working.

Tool definitions are overhead: they occupy context on every request and compete with your code, documents and conversation history for the same window.

200K WINDOW 113%

1M WINDOW 23%

Corpus context: OneUptime ranks #8 of 15,192 measured MCP servers by definition cost. The median is 1,746 tokens, p90 is 12,772, and the heaviest (AstroWay Astrology API (full catalogue)) is 547,756 — 274% of a 200k window on its own. New to this? See MCP token cost and context window in the glossary.

Token cost is one axis. See the risk picture across your whole stack →

// PER-TOOL BREAKDOWN

Where the 226,700 tokens go.

Each row is one tool definition as a tools/list entry — name, description and input schema — counted with o200k_base. Average: 1,017 tokens per tool.

Tool	Category	Tokens	% of server
list_status_pages	Read	8,168	3.6%
list_incidents	Read	7,091	3.1%
count_status_pages	Read	5,648	2.5%
count_incidents	Read	5,437	2.4%
list_monitors	Read	5,413	2.4%
list_security_cases	Read	5,029	2.2%
list_alerts	Read	4,935	2.2%
list_scheduled_maintenance_events	Read	4,459	2.0%
count_monitors	Read	4,084	1.8%
count_alerts	Read	3,912	1.7%
count_security_cases	Read	3,637	1.6%
count_scheduled_maintenance_events	Read	3,364	1.5%
create_status_page	Write	3,292	1.5%
list_spans	Read	3,266	1.4%
update_status_page	Write	3,262	1.4%
list_security_detections	Read	2,863	1.3%
list_kubernetes_cost_allocations	Read	2,778	1.2%
list_security_events	Read	2,708	1.2%
list_security_case_priorities	Read	2,511	1.1%
create_incident	Write	2,446	1.1%
list_incident_public_notes	Read	2,413	1.1%
list_metrics	Read	2,393	1.1%
update_incident	Write	2,378	1.0%
list_status_page_announcements	Read	2,343	1.0%
list_on_call_duty_policies	Read	2,269	1.0%
list_security_case_statuses	Read	2,209	1.0%
list_scheduled_maintenance_states	Read	2,208	1.0%
list_postmortem_statuses	Read	2,130	0.9%
list_incident_state_timelines	Read	2,124	0.9%
create_monitor	Write	2,119	0.9%
list_incident_states	Read	2,118	0.9%
list_security_case_evidence	Read	2,069	0.9%
list_monitor_statuses	Read	2,057	0.9%
list_alert_states	Read	2,034	0.9%
count_security_detections	Read	2,033	0.9%
list_security_playbooks	Read	2,026	0.9%
list_scheduled_maintenance_state_timelines	Read	2,021	0.9%
list_exception_instances	Read	2,007	0.9%
list_labels	Read	1,879	0.8%
list_incident_severities	Read	1,866	0.8%
list_alert_severities	Read	1,865	0.8%
list_teams	Read	1,851	0.8%
list_alert_state_timelines	Read	1,830	0.8%
list_monitor_status_events	Read	1,827	0.8%
list_logs	Read	1,819	0.8%
create_alert	Write	1,793	0.8%
list_incident_internal_notes	Read	1,771	0.8%
list_security_case_tasks	Read	1,771	0.8%
list_alert_internal_notes	Read	1,770	0.8%
update_alert	Write	1,759	0.8%
count_security_case_priorities	Read	1,746	0.8%
update_monitor	Write	1,743	0.8%
count_incident_public_notes	Read	1,663	0.7%
count_status_page_announcements	Read	1,648	0.7%
create_scheduled_maintenance_event	Write	1,628	0.7%
count_on_call_duty_policies	Read	1,589	0.7%
count_security_case_statuses	Read	1,540	0.7%
count_scheduled_maintenance_states	Read	1,539	0.7%
count_postmortem_statuses	Read	1,489	0.7%
count_incident_states	Read	1,481	0.7%
count_incident_state_timelines	Read	1,479	0.7%
update_scheduled_maintenance_event	Write	1,479	0.7%
count_security_playbooks	Read	1,429	0.6%
count_monitor_statuses	Read	1,426	0.6%
count_security_case_evidence	Read	1,425	0.6%
count_alert_states	Read	1,423	0.6%
list_incident_alerts	Read	1,376	0.6%
count_scheduled_maintenance_state_timelines	Read	1,374	0.6%
list_security_case_notes	Read	1,348	0.6%
count_incident_severities	Read	1,321	0.6%
count_alert_severities	Read	1,320	0.6%
count_labels	Read	1,306	0.6%
count_alert_state_timelines	Read	1,290	0.6%
count_monitor_status_events	Read	1,287	0.6%
count_teams	Read	1,256	0.6%
count_incident_internal_notes	Read	1,254	0.6%
count_alert_internal_notes	Read	1,253	0.6%
list_threat_intel_indicators	Read	1,247	0.6%
count_security_case_tasks	Read	1,216	0.5%
oneuptime_help	Destructive	1,056	0.5%
list_change_events	Read	1,048	0.5%
count_spans	Read	1,026	0.5%
count_incident_alerts	Read	943	0.4%
count_security_case_notes	Read	939	0.4%
count_kubernetes_cost_allocations	Read	857	0.4%
count_security_events	Read	840	0.4%
list_monitor_logs	Read	816	0.4%
count_metrics	Read	790	0.3%
create_security_case	Write	697	0.3%
create_security_case_priority	Write	692	0.3%
update_security_case	Write	671	0.3%
update_security_case_priority	Write	665	0.3%
count_exception_instances	Read	640	0.3%
count_logs	Read	594	0.3%
create_security_case_status	Write	570	0.3%
create_postmortem_status	Write	554	0.2%
update_security_case_status	Write	543	0.2%
update_postmortem_status	Write	524	0.2%
create_security_playbook	Write	508	0.2%
create_scheduled_maintenance_state	Write	484	0.2%
update_security_playbook	Write	482	0.2%
create_on_call_policy	Write	471	0.2%
create_status_page_announcement	Write	468	0.2%
create_incident_state	Write	467	0.2%
create_alert_state	Write	465	0.2%
update_scheduled_maintenance_state	Write	457	0.2%
update_on_call_policy	Write	443	0.2%
update_incident_state	Write	437	0.2%
create_security_case_evidence	Write	433	0.2%
update_alert_state	Write	433	0.2%
create_monitor_status	Write	428	0.2%
count_threat_intel_indicators	Read	423	0.2%
create_incident_public_note	Write	417	0.2%
create_incident_state_timeline	Write	405	0.2%
update_status_page_announcement	Write	403	0.2%
update_monitor_status	Write	396	0.2%
create_incident_internal_note	Write	385	0.2%
create_alert_internal_note	Write	384	0.2%
create_scheduled_maintenance_state_timeline	Write	375	0.2%
create_alert_state_timeline	Write	372	0.2%
count_change_events	Read	358	0.2%
create_incident_severity	Write	351	0.2%
create_alert_severity	Write	350	0.2%
create_monitor_status_event	Write	346	0.2%
update_incident_severity	Write	323	0.1%
update_alert_severity	Write	320	0.1%
create_security_case_task	Write	303	0.1%
count_monitor_logs	Read	290	0.1%
get_public_status_page_scheduled_maintenance	Read	258	0.1%
create_label	Write	255	0.1%
get_public_status_page_overview	Read	253	0.1%
update_incident_internal_note	Write	249	0.1%
get_public_status_page_incidents	Read	248	0.1%
update_alert_internal_note	Write	246	0.1%
update_scheduled_maintenance_state_timeline	Write	230	0.1%
update_security_case_task	Write	229	0.1%
get_public_status_page_announcements	Read	227	0.1%
create_incident_alert	Write	223	0.1%
update_security_case_evidence	Write	223	0.1%
update_incident_public_note	Write	222	0.1%
update_incident_state_timeline	Write	222	0.1%
update_label	Write	222	0.1%
update_alert_state_timeline	Write	219	0.1%
create_team	Write	209	0.1%
create_security_case_note	Write	204	0.1%
get_incident	Read	194	0.1%
get_status_page	Read	193	0.1%
get_incident_public_note	Read	184	0.1%
get_scheduled_maintenance_event	Read	184	0.1%
get_scheduled_maintenance_state_timeline	Read	180	0.1%
get_status_page_announcement	Read	179	0.1%
update_team	Write	179	0.1%
get_incident_state_timeline	Read	177	0.1%
get_security_detection	Read	176	0.1%
get_monitor	Read	173	0.1%
get_on_call_policy	Read	173	0.1%
get_alert	Read	171	0.1%
get_incident_internal_note	Read	171	0.1%
get_security_case	Read	171	0.1%
get_alert_state_timeline	Read	170	0.1%
get_security_playbook	Read	170	0.1%
get_alert_internal_note	Read	169	0.1%
get_monitor_status_event	Read	168	0.1%
get_security_case_evidence	Read	168	0.1%
get_postmortem_status	Read	159	0.1%
get_team	Read	158	0.1%
get_scheduled_maintenance_state	Read	157	0.1%
get_security_case_priority	Read	154	0.1%
get_security_case_status	Read	154	0.1%
get_incident_severity	Read	153	0.1%
get_security_case_note	Read	153	0.1%
get_security_case_task	Read	153	0.1%
get_alert_severity	Read	151	0.1%
get_incident_alert	Read	151	0.1%
get_incident_state	Read	150	0.1%
update_monitor_status_event	Write	150	0.1%
get_monitor_status	Read	149	0.1%
get_alert_state	Read	148	0.1%
add_incident_note	Write	146	0.1%
get_label	Read	143	0.1%
update_security_case_note	Write	130	0.1%
acknowledge_incident	Read	125	0.1%
acknowledge_alert	Read	109	0.0%
update_incident_alert	Write	101	0.0%
update_security_detection	Write	99	0.0%
delete_scheduled_maintenance_state_timeline	Destructive	91	0.0%
oneuptime_whoami	Write	89	0.0%
delete_postmortem_status	Destructive	88	0.0%
delete_incident_state_timeline	Destructive	87	0.0%
delete_on_call_policy	Destructive	87	0.0%
delete_scheduled_maintenance_event	Destructive	87	0.0%
delete_scheduled_maintenance_state	Destructive	87	0.0%
delete_alert_state_timeline	Destructive	86	0.0%
delete_incident_internal_note	Destructive	86	0.0%
delete_incident_public_note	Destructive	86	0.0%
delete_security_case_evidence	Destructive	86	0.0%
delete_status_page_announcement	Destructive	86	0.0%
delete_alert_internal_note	Destructive	85	0.0%
delete_monitor_status_event	Destructive	85	0.0%
delete_security_case_note	Destructive	85	0.0%
delete_security_case_priority	Destructive	85	0.0%
delete_security_case_status	Destructive	85	0.0%
delete_security_case_task	Destructive	85	0.0%
delete_security_playbook	Destructive	85	0.0%
delete_incident_severity	Destructive	84	0.0%
delete_alert_severity	Destructive	83	0.0%
delete_incident_alert	Destructive	83	0.0%
delete_incident_state	Destructive	83	0.0%
add_alert_note	Write	83	0.0%
delete_alert_state	Destructive	82	0.0%
delete_monitor_status	Destructive	82	0.0%
delete_security_case	Destructive	82	0.0%
delete_security_detection	Destructive	82	0.0%
delete_status_page	Destructive	82	0.0%
resolve_incident	Write	82	0.0%
delete_incident	Destructive	80	0.0%
create_security_detection	Write	80	0.0%
delete_alert	Destructive	79	0.0%
delete_label	Destructive	79	0.0%
delete_monitor	Destructive	79	0.0%
delete_team	Destructive	79	0.0%
resolve_alert	Write	68	0.0%
oneuptime_list_resources	Read	53	0.0%

// CUT THE COST

Your agent uses a handful of these tools. It pays for all 223.

You don't need all 223 of those definitions in the window. PolicyLayer is an MCP gateway that sits in front of OneUptime: only the tools you grant are exposed to the agent, the rest never load. A smaller window means a sharper agent — less noise when it picks a tool — and every request costs less:

Grant scope	Definition cost	Reduction
All 223 tools (no gateway)	226,700 tokens	—
3 granted tools	~3,050 tokens	−99%
5 granted tools	~5,083 tokens	−98%
10 granted tools	~10,166 tokens	−96%

The risk dividend: 33 of these 223 tools are critical-risk (destructive or financial) and cost 3,747 tokens (2% of the definition load). Block them — the recommended starter policy — and you reclaim that context before tuning anything else.

Create a free account and register OneUptime — nothing to install.
Grant only the tools you use — ungranted definitions never enter the context window.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CUT ONEUPTIME TOKEN COST →

Instant setup, no code required.

Model your own stack in the token-cost calculator, or see the OneUptime policy for what a sensible grant looks like.

//FAQ

OneUptime token-cost questions.

How many tokens does the OneUptime MCP server use?+

Its 223 tool definitions total 226,700 tokens — 113% of a 200k context window — measured with tiktoken o200k_base over the serialised tools/list payload. Exact counts vary slightly by client and model.

Why does OneUptime consume tokens before I send a message?+

MCP clients load every connected server's tool definitions — name, description, and input schema — into the model's context so it knows what it can call. That payload is charged against your context window on every request, whether or not a tool is used.

How do I reduce OneUptime's token usage?+

Expose fewer tools. A PolicyLayer grant scopes OneUptime to only the tools you allow — ungranted definitions are filtered out of the tool list, so they never enter the context window. A grant of 3 typical tools costs roughly 3,050 tokens, a 99% reduction.

Does deferred tool loading fix this?+

Partially, in some clients. Claude Code defers MCP tool schemas behind a tool-search step by default, and VS Code has experimental grouping — but you still pay tokens per search and reload, and Cursor, Windsurf and Gemini CLI load definitions upfront. Reducing the exposed tool set cuts the cost in every client.

// METHOD & REVIEW

How these numbers were measured.

01

Serialisation

Each tool is serialised as a tools/list entry — name, description, input schema — from the schemas in the PolicyLayer scan database. Clients differ slightly in framing, so treat counts as close estimates.

02

Tokeniser

tiktoken o200k_base (GPT-4o/o-series). Anthropic's current tokeniser isn't published, so Claude's exact counts will differ; for English text and JSON schemas the totals are close enough to treat these as estimates.

03

Deferred loading

Some clients now defer schema loading (Claude Code's tool search; VS Code experimental grouping). You still pay per search and reload — and Cursor, Windsurf and Gemini CLI load everything upfront.

Computed 04-11-2026 from the PolicyLayer scan database over all 223 catalogued OneUptime tools. Counts refresh with every site build.