// MCP TOKEN COST

The Ezhi Scm Insights MCP server costs 32,967 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 Ezhi Scm Insights MCP server's 87 tool definitions consume 32,967 tokens — 16% of a 200k context window, and 16× the median MCP server (2,038 tokens). A scoped grant exposing only the tools you use cuts that roughly in proportion.

MEASURED FROM SCHEMAS tiktoken o200k_base · rank #62 of 6,689 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 16%

1M WINDOW 3.3%

Corpus context: Ezhi Scm Insights ranks #62 of 6,689 measured MCP servers by definition cost. The median is 2,038 tokens, p90 is 12,122, and the heaviest (Ainumbers Mcp Apps) is 269,012 — 135% 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 32,967 tokens go.

Each row is one tool definition as a tools/list entry — name, description and input schema — counted with o200k_base. Average: 379 tokens per tool.

Tool	Category	Tokens	% of server
scm_insights_export_users_agent_user_list	Write	457	1.4%
scm_insights_users_agent_user_list	Read	454	1.4%
scm_insights_user_monitored_user_count_histogram	Read	446	1.4%
scm_insights_users_monitored_user_experience_score	Read	445	1.3%
scm_insights_users_agent_connected_user_device_count_histogram	Read	443	1.3%
scm_insights_users_monitored_device_count_histogram	Read	443	1.3%
scm_insights_users_monitored_device_count	Read	441	1.3%
scm_insights_user_monitored_user_count	Read	440	1.3%
scm_insights_users_agent_connected_user_count_histogram	Read	440	1.3%
scm_insights_users_agent_current_connected_device_count	Read	436	1.3%
scm_insights_users_agent_current_connected_user_count	Read	436	1.3%
scm_insights_applications_internal_application_list	Read	434	1.3%
scm_insights_users_agent_device_list	Read	431	1.3%
scm_insights_users_agent_client_version_distribution	Read	418	1.3%
scm_insights_users_agent_session_list	Read	409	1.2%
scm_insights_applications_internal_total_data_transfer_by_destination	Read	408	1.2%
scm_insights_applications_internal_total_data_transfer_application	Read	406	1.2%
scm_insights_applications_internal_app_by_risk_score	Read	405	1.2%
scm_insights_users_all_user_list_all	Read	405	1.2%
scm_insights_applications_internal_app_by_tag	Read	401	1.2%
scm_insights_users_agent_connected_entity_count	Read	401	1.2%
scm_insights_users_agent_unique_device_connections_list	Read	398	1.2%
scm_insights_users_branch_connected_user_count	Read	398	1.2%
scm_insights_users_other_connected_entity_count	Read	395	1.2%
scm_insights_query	Read	391	1.2%
scm_insights_users_other_user_list	Read	389	1.2%
scm_insights_users_agentless_connected_user_count	Read	388	1.2%
scm_insights_applications_app_info	Read	386	1.2%
scm_insights_users_agent_connected_user_count	Read	385	1.2%
scm_insights_users_eb_connected_user_count	Read	385	1.2%
scm_insights_sites_bandwidth_consumption_histogram	Read	382	1.2%
scm_insights_export_users_branch_user_list	Write	381	1.2%
scm_insights_accelerated_applications_throughput_per_app_histogram	Read	380	1.2%
scm_insights_users_agentless_active_user_count	Read	380	1.2%
scm_insights_users_other_user_count_histogram	Read	380	1.2%
scm_insights_accelerated_applications_packet_loss_per_app_histogram	Read	379	1.1%
scm_insights_users_agentless_active_user_list	Read	379	1.1%
scm_insights_accelerated_applications_rtt_variance_histogram	Read	378	1.1%
scm_insights_applications_pab_access_events_breakdown_blocked_histogram	Read	378	1.1%
scm_insights_users_agentless_user_count_histogram	Read	378	1.1%
scm_insights_users_branch_user_list	Read	378	1.1%
scm_insights_users_other_active_user_list	Read	378	1.1%
scm_insights_agentless_risky_user_count	Read	377	1.1%
scm_insights_other_risky_user_count	Read	377	1.1%
scm_insights_sites_site_traffic	Read	377	1.1%
scm_insights_users_other_active_user_count	Read	377	1.1%
scm_insights_accelerated_applications_data_transfer_throughput_per_app	Read	376	1.1%
scm_insights_accelerated_applications_accelerated_application_list	Read	375	1.1%
scm_insights_accelerated_applications_better_response_time	Read	374	1.1%
scm_insights_users_agentless_session_list	Read	374	1.1%
scm_insights_users_other_session_list	Read	374	1.1%
scm_insights_accelerated_applications_total_data_transfer	Read	373	1.1%
scm_insights_accelerated_applications_performance_boost	Execute	372	1.1%
scm_insights_accelerated_applications_applications_count	Read	372	1.1%
scm_insights_pab_data_events_breakdown_blocked_histogram	Read	372	1.1%
scm_insights_pab_access_events_blocked_histogram	Read	369	1.1%
scm_insights_pab_access_events_breakdown_blocked	Read	369	1.1%
scm_insights_pab_access_events_breakdown_histogram	Read	369	1.1%
scm_insights_pab_data_events_blocked_histogram	Read	369	1.1%
scm_insights_users_agentless_users	Read	369	1.1%
scm_insights_users_eb_user_count_histogram	Read	369	1.1%
scm_insights_accelerated_applications_users_count	Read	368	1.1%
scm_insights_applications_pab_access_events_breakdown	Read	368	1.1%
scm_insights_pab_data_events_breakdown_blocked	Read	368	1.1%
scm_insights_pab_data_events_breakdown_histogram	Read	368	1.1%
scm_insights_users_eb_active_user_count	Read	366	1.1%
scm_insights_pab_data_events_blocked	Read	365	1.1%
scm_insights_pab_access_events_blocked	Read	364	1.1%
scm_insights_pab_access_events_histogram	Read	364	1.1%
scm_insights_users_eb_user_list	Read	364	1.1%
scm_insights_app_details_bw_info_histogram	Read	363	1.1%
scm_insights_applications_pab_access_events	Read	363	1.1%
scm_insights_applications_pab_data_events	Read	363	1.1%
scm_insights_pab_data_events_breakdown	Read	363	1.1%
scm_insights_pab_data_events_histogram	Read	363	1.1%
scm_insights_users_branch_connected_entity_count	Read	363	1.1%
scm_insights_users_branch_user_count_histogram	Read	362	1.1%
scm_insights_users_branch_active_user_count	Read	361	1.1%
scm_insights_users_branch_active_user_list	Read	361	1.1%
scm_insights_branch_risky_user_count	Read	360	1.1%
scm_insights_users_agent_risky_user_count	Read	360	1.1%
scm_insights_users_branch_session_list	Read	358	1.1%
scm_insights_sites_session_count	Read	351	1.1%
scm_insights_sites_site_location_search_contains	Read	351	1.1%
scm_insights_sites_site_count	Read	348	1.1%
scm_insights_api_catalog	Read	96	0.3%
scm_insights_auth_test	Read	37	0.1%

// CUT THE COST

Your agent uses a handful of these tools. It pays for all 87.

You don't need all 87 of those definitions in the window. PolicyLayer is an MCP gateway that sits in front of Ezhi Scm Insights: 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 87 tools (no gateway)	32,967 tokens	—
3 granted tools	~1,137 tokens	−97%
5 granted tools	~1,895 tokens	−94%
10 granted tools	~3,789 tokens	−89%

Create a free account and register Ezhi Scm Insights — 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 EZHI SCM INSIGHTS TOKEN COST →

Instant setup, no code required.

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

//FAQ

Ezhi Scm Insights token-cost questions.

How many tokens does the Ezhi Scm Insights MCP server use?+

Its 87 tool definitions total 32,967 tokens — 16% 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 Ezhi Scm Insights 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 Ezhi Scm Insights's token usage?+

Expose fewer tools. A PolicyLayer grant scopes Ezhi Scm Insights 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 1,137 tokens, a 97% 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.

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.

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.

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 17-08-2026 from the PolicyLayer scan database over all 87 catalogued Ezhi Scm Insights tools. Counts refresh with every site build.