// MCP TOKEN COST

The Acronis Platform MCP server costs 70,609 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 Acronis Platform MCP server's 156 tool definitions consume 70,609 tokens — 35% of a 200k context window, and 37× the median MCP server (1,919 tokens). A scoped grant exposing only the tools you use cuts that roughly in proportion.

MEASURED FROM SCHEMAS tiktoken o200k_base · rank #17 of 7,978 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 35%

1M WINDOW 7.1%

Corpus context: Acronis Platform ranks #17 of 7,978 measured MCP servers by definition cost. The median is 1,919 tokens, p90 is 12,349, and the heaviest (Ainumbers Mcp Apps) is 325,967 — 163% 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 70,609 tokens go.

Each row is one tool definition as a tools/list entry — name, description and input schema — counted with o200k_base. Average: 453 tokens per tool.

Tool	Category	Tokens	% of server
create_a_policy	Write	4,141	5.9%
create_a_protection_policy_draft	Write	4,114	5.8%
update_a_policy	Write	4,092	5.8%
add_or_update_a_policy_in_a_draft	Write	2,697	3.8%
create_a_resource	Write	2,306	3.3%
post_multiple_resources_in_one_request_from_a_single_agent	Write	2,306	3.3%
create_an_alert	Write	1,574	2.2%
commit_or_cancel_a_protection_policy_draft	Write	1,570	2.2%
fetch_all_alerts	Read	1,514	2.1%
apply_a_policy	Write	1,484	2.1%
fetch_alerts_grouped_per_customer	Read	1,355	1.9%
dismiss_the_alerts_by_filter	Read	1,347	1.9%
fetch_partner_s_customer_alerts_count	Read	1,332	1.9%
fetch_incidents	Read	1,323	1.9%
set_a_draft_s_resource_context	Write	1,318	1.9%
create_tenant	Write	1,261	1.8%
initiate_response_action	Read	1,042	1.5%
bulk_update_investigation_state	Write	999	1.4%
update_tenant	Write	989	1.4%
modify_custom_branding	Write	945	1.3%
fetch_a_list_of_all_resources	Read	930	1.3%
create_user	Write	900	1.3%
fetch_a_list_of_policy_applications	Read	896	1.3%
update_user	Write	856	1.2%
fetch_a_list_of_policies	Read	836	1.2%
fetch_a_count_of_all_resources_that_match_filter_parameters	Read	827	1.2%
fetch_users_batch	Read	819	1.2%
update_user_access_policies	Write	813	1.2%
update_investigation_state	Write	789	1.1%
fetch_agents	Read	782	1.1%
fetch_tenants_batch	Read	770	1.1%
fetch_application_statuses_by_policy	Read	646	0.9%
create_report	Write	553	0.8%
register_new_alert_type	Write	536	0.8%
execute_a_protection_policy	Execute	495	0.7%
set_tenant_offering_items	Write	495	0.7%
fetch_incident	Read	472	0.7%
fetch_the_protection_status_of_resources	Read	449	0.6%
fetch_tenant_offering_items	Read	415	0.6%
update_infrastructure	Write	401	0.6%
fetch_a_resource_by_id	Read	384	0.5%
fetch_response_action_status	Read	374	0.5%
register_infrastructure	Write	363	0.5%
update_tenants_usages	Write	363	0.5%
fetch_tenant_offering_items_batch	Read	357	0.5%
update_report	Write	339	0.5%
update_tenant_offering_items_prices	Write	329	0.5%
update_tenant_application_setting	Write	326	0.5%
fetch_tenant_users	Read	323	0.5%
remove_policy_applications	Destructive	300	0.4%
fetch_tenant_children	Read	298	0.4%
fetch_a_policy	Read	260	0.4%
create_registration_token	Write	249	0.4%
update_tenant_default_idp_id	Write	247	0.3%
fetch_alert_counters	Read	241	0.3%
fetch_a_list_of_resource_s_attributes	Read	240	0.3%
update_tenant_pricing_settings	Write	233	0.3%
fetch_resources_containing_the_highest_severity_alerts	Read	231	0.3%
fetch_all_alert_types	Read	227	0.3%
update_client	Write	224	0.3%
request_one_time_token	Read	223	0.3%
revoke_token	Destructive	219	0.3%
create_client	Write	218	0.3%
switch_tenant_edition	Write	218	0.3%
fetch_one_time_token_login_page	Read	215	0.3%
enable_or_disable_policies_in_a_draft	Write	215	0.3%
fetch_offering_items_available_for_tenant_child	Read	214	0.3%
delete_tenant_application_setting	Destructive	213	0.3%
fetch_tenant_application_setting	Read	202	0.3%
restore_deleted_user	Write	194	0.3%
upload_tenant_brand_logo	Write	194	0.3%
fetch_tenants_usages_batch	Read	193	0.3%
update_a_draft_policy_s_settings	Write	191	0.3%
update_infrastructures_location	Write	191	0.3%
device_authorization_approval	Read	190	0.3%
unregister_infrastructure	Read	190	0.3%
search	Read	188	0.3%
request_tokens	Read	184	0.3%
fetch_clients_batch	Read	183	0.3%
set_a_draft_s_disabled_applications_context	Write	182	0.3%
fetch_available_tenant_applications	Read	181	0.3%
download_stored_report	Read	180	0.3%
fetch_applications_issue_statistics	Read	180	0.3%
turn_off_tenant_application	Read	180	0.3%
turn_on_tenant_application	Read	180	0.3%
restore_deleted_tenant	Write	179	0.3%
fetch_alerts_grouped_by_scope	Read	177	0.3%
fetch_tenant_usages	Read	177	0.3%
perform_tenant_edition_switch_check	Write	177	0.3%
manage_tenant_mfastatus	Write	175	0.2%
mark_alert_as_false_positive	Write	174	0.2%
fetch_an_alert_by_id	Read	173	0.2%
fetch_tenant	Read	172	0.2%
set_user_password	Write	172	0.2%
delete_policies	Destructive	171	0.2%
delete_resources	Destructive	168	0.2%
enable_custom_branding	Write	167	0.2%
manage_user_mfastatus	Write	162	0.2%
fetch_user_access_policies	Read	160	0.2%
delete_infrastructures_location	Destructive	157	0.2%
fetch_tenants_applications_batch	Read	156	0.2%
disable_custom_branding	Write	154	0.2%
fetch_custom_branding_options	Read	153	0.2%
delete_report	Destructive	151	0.2%
delete_tenant	Destructive	151	0.2%
delete_user	Destructive	150	0.2%
fetch_user	Read	149	0.2%
resolve_tenant_ids	Write	146	0.2%
create_infrastructures_location	Write	141	0.2%
dismiss_an_alert_by_id	Read	134	0.2%
set_a_draft_policy_s_type	Write	131	0.2%
delete_agents	Destructive	129	0.2%
fetch_tenant_mfastatus	Read	127	0.2%
fetch_tenant_offering_items_prices	Read	127	0.2%
fetch_location_infrastructures	Read	125	0.2%
fetch_tenant_infrastructure_locations	Read	124	0.2%
fetch_tenant_reports	Read	124	0.2%
enable_or_disable_a_policy_in_a_draft	Write	123	0.2%
fetch_infrastructures_location	Read	122	0.2%
fetch_stored_reports	Read	121	0.2%
fetch_tenant_pricing_settings	Read	120	0.2%
set_a_draft_policy_s_comment	Write	120	0.2%
set_a_protection_policy_draft_s_name	Write	120	0.2%
fetch_application	Read	118	0.2%
fetch_tenant_brand_logo	Read	118	0.2%
set_a_draft_policy_s_name	Write	118	0.2%
delete_registration_token	Destructive	117	0.2%
send_activation_email	Write	117	0.2%
fetch_client	Read	115	0.2%
fetch_infrastructure	Read	115	0.2%
fetch_report	Read	115	0.2%
delete_client	Destructive	114	0.2%
fetch_registration_tokens	Read	114	0.2%
modify_policies_favorite_order_and_properties	Write	102	0.1%
remove_a_policy_from_a_draft	Destructive	99	0.1%
log_in_with_one_time_token	Read	89	0.1%
fetch_a_protection_policy_draft	Read	87	0.1%
unregister_an_alert_type_by_id	Write	87	0.1%
cancel_a_protection_policy_draft	Destructive	83	0.1%
check_password	Read	83	0.1%
fetch_an_alert_type_by_id	Read	77	0.1%
fetch_infrastructures_locations_batch	Read	77	0.1%
check_login_name_availability	Read	76	0.1%
introspect_token	Read	75	0.1%
fetch_infrastructures_batch	Read	74	0.1%
fetch_agent	Read	73	0.1%
get_forgot_link	Read	73	0.1%
fetch_categories	Read	69	0.1%
delete_a_policy	Destructive	62	0.1%
fetch_open_idconfiguration	Read	58	0.1%
post_idp_device_authorization	Write	57	0.1%
get_count_of_active_alerts_and_last_modification_time	Read	44	0.1%
get_acronis_skill	Read	36	0.1%
fetch_current_user_info	Read	33	0.0%
fetch_applications	Read	32	0.0%
logout	Read	28	0.0%

// CUT THE COST

Your agent uses a handful of these tools. It pays for all 156.

You don't need all 156 of those definitions in the window. PolicyLayer is an MCP gateway that sits in front of Acronis Platform: 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 156 tools (no gateway)	70,609 tokens	—
3 granted tools	~1,358 tokens	−98%
5 granted tools	~2,263 tokens	−97%
10 granted tools	~4,526 tokens	−94%

The risk dividend: 15 of these 156 tools are critical-risk (destructive or financial) and cost 2,284 tokens (3% 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 Acronis Platform — 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 ACRONIS PLATFORM TOKEN COST →

Instant setup, no code required.

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

//FAQ

Acronis Platform token-cost questions.

How many tokens does the Acronis Platform MCP server use?+

Its 156 tool definitions total 70,609 tokens — 35% 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 Acronis Platform 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 Acronis Platform's token usage?+

Expose fewer tools. A PolicyLayer grant scopes Acronis Platform 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 1,358 tokens, a 98% 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 02-09-2026 from the PolicyLayer scan database over all 156 catalogued Acronis Platform tools. Counts refresh with every site build.