// MCP TOKEN COST

The Calcgrid MCP server costs 140,850 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 Calcgrid MCP server's 253 tool definitions consume 140,850 tokens — 70% of a 200k context window, and 76× the median MCP server (1,862 tokens). A scoped grant exposing only the tools you use cuts that roughly in proportion.

MEASURED FROM SCHEMAS tiktoken o200k_base · rank #9 of 12,722 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 70%

1M WINDOW 14%

Corpus context: Calcgrid ranks #9 of 12,722 measured MCP servers by definition cost. The median is 1,862 tokens, p90 is 13,674, and the heaviest (Ainumbers Mcp Apps) is 442,047 — 221% 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 140,850 tokens go.

Each row is one tool definition as a tools/list entry — name, description and input schema — counted with o200k_base. Average: 557 tokens per tool.

Tool	Category	Tokens	% of server
calculate_t_test	Read	2,043	1.5%
calculate_business_deadline	Write	1,486	1.1%
cast_plum_blossom_hexagram	Read	1,287	0.9%
count_global_working_days	Read	1,188	0.8%
calculate_bazi_four_pillars	Execute	1,186	0.8%
count_global_reference_working_days	Read	1,139	0.8%
add_global_working_days	Write	1,110	0.8%
estimate_ev_charging_time	Read	1,087	0.8%
check_global_working_day	Read	1,055	0.7%
add_global_reference_working_days	Write	1,051	0.7%
compare_loans	Read	1,046	0.7%
check_global_reference_working_day	Read	1,036	0.7%
price_black_scholes_option	Read	1,032	0.7%
check_lv_working_day	Read	1,021	0.7%
calculate_amortization_schedule	Write	993	0.7%
lookup_iching_hexagram	Read	968	0.7%
count_lv_working_days	Read	941	0.7%
calculate_mortgage_payment	Read	887	0.6%
calculate_depth_of_field	Read	883	0.6%
convert_time_zone	Write	881	0.6%
check_lt_working_day	Read	873	0.6%
calculate_ab_test_significance	Read	871	0.6%
add_lv_working_days	Write	861	0.6%
calculate_loan_payment	Read	820	0.6%
count_ro_working_days	Read	820	0.6%
count_lt_working_days	Read	815	0.6%
count_pe_working_days	Read	791	0.6%
count_uk_working_days	Read	790	0.6%
check_ro_working_day	Read	786	0.6%
calculate_haversine_distance	Read	784	0.6%
count_mt_working_days	Read	759	0.5%
calculate_compound_interest	Read	757	0.5%
add_ro_working_days	Write	749	0.5%
convert_lunar_to_solar	Write	740	0.5%
add_lt_working_days	Write	738	0.5%
find_chinese_zodiac	Read	728	0.5%
count_lu_working_days	Read	722	0.5%
add_pe_working_days	Write	719	0.5%
count_ee_working_days	Read	717	0.5%
count_global_public_holiday_working_days	Read	709	0.5%
check_pe_working_day	Read	695	0.5%
count_hu_working_days	Read	691	0.5%
check_mt_working_day	Read	683	0.5%
count_bg_working_days	Read	679	0.5%
convert_solar_to_lunar	Write	675	0.5%
add_mt_working_days	Write	674	0.5%
count_cz_working_days	Read	668	0.5%
solve_ohms_law	Read	665	0.5%
count_hr_working_days	Read	662	0.5%
add_uk_working_days	Write	662	0.5%
check_lu_working_day	Read	661	0.5%
calculate_bmr	Read	658	0.5%
check_ee_working_day	Read	654	0.5%
resolve_local_time	Write	654	0.5%
add_lu_working_days	Write	650	0.5%
count_si_working_days	Read	649	0.5%
add_ee_working_days	Write	647	0.5%
count_china_working_days	Read	641	0.5%
count_my_working_days	Read	641	0.5%
calculate_running_pace	Read	634	0.5%
check_hu_working_day	Read	632	0.4%
add_hu_working_days	Write	632	0.4%
count_india_central_working_days	Read	631	0.4%
calculate_tdee	Read	625	0.4%
check_bg_working_day	Read	625	0.4%
add_bg_working_days	Write	620	0.4%
add_global_public_holiday_working_days	Write	620	0.4%
convert_betting_odds	Write	616	0.4%
check_cz_working_day	Read	614	0.4%
check_hr_working_day	Read	610	0.4%
add_cz_working_days	Write	610	0.4%
calculate_descriptive_statistics	Write	608	0.4%
add_hr_working_days	Write	603	0.4%
calculate_date_difference	Write	603	0.4%
count_australia_working_days	Read	601	0.4%
calculate_fraction_arithmetic	Write	601	0.4%
count_sk_working_days	Read	598	0.4%
check_si_working_day	Read	595	0.4%
count_kz_working_days	Read	591	0.4%
add_si_working_days	Write	590	0.4%
check_global_public_holiday_working_day	Read	585	0.4%
count_ke_working_days	Read	585	0.4%
count_lk_working_days	Read	583	0.4%
list_time_zone_transitions	Read	579	0.4%
count_uzbekistan_working_days	Read	576	0.4%
count_gh_working_days	Read	574	0.4%
count_ng_working_days	Read	567	0.4%
list_solar_terms	Read	566	0.4%
add_china_working_days	Write	565	0.4%
calculate_age	Read	558	0.4%
count_gr_working_days	Read	556	0.4%
check_uk_working_day	Read	555	0.4%
add_my_working_days	Write	551	0.4%
count_eg_working_days	Read	550	0.4%
count_cl_working_days	Read	547	0.4%
calculate_subnet	Read	546	0.4%
count_pk_working_days	Read	542	0.4%
count_ru_working_days	Read	541	0.4%
check_india_central_working_day	Read	540	0.4%
count_bd_working_days	Read	540	0.4%
add_sk_working_days	Write	538	0.4%
count_no_working_days	Read	537	0.4%
add_india_central_working_days	Write	536	0.4%
count_sa_working_days	Read	535	0.4%
calculate_kinetic_energy	Read	534	0.4%
count_hk_working_days	Read	534	0.4%
count_co_working_days	Read	530	0.4%
count_fi_working_days	Read	530	0.4%
convert_temperature	Write	529	0.4%
count_vn_working_days	Read	525	0.4%
calculate_percentage	Read	521	0.4%
count_canada_federal_working_days	Read	521	0.4%
count_us_federal_working_days	Read	521	0.4%
count_turkey_working_days	Read	520	0.4%
count_uae_federal_working_days	Read	520	0.4%
count_tw_working_days	Read	519	0.4%
count_singapore_working_days	Read	518	0.4%
count_th_working_days	Read	518	0.4%
count_dk_working_days	Read	516	0.4%
count_se_working_days	Read	515	0.4%
count_nl_working_days	Read	514	0.4%
count_kr_working_days	Read	512	0.4%
count_ch_working_days	Read	509	0.4%
count_japan_national_working_days	Read	509	0.4%
add_kz_working_days	Write	509	0.4%
add_australia_working_days	Write	508	0.4%
count_id_working_days	Read	506	0.4%
count_at_working_days	Read	505	0.4%
check_sk_working_day	Read	503	0.4%
add_ke_working_days	Write	503	0.4%
count_be_working_days	Read	502	0.4%
add_lk_working_days	Write	502	0.4%
check_my_working_day	Read	501	0.4%
count_ph_working_days	Read	501	0.4%
count_mx_working_days	Read	500	0.4%
count_it_working_days	Read	494	0.4%
count_pl_working_days	Read	494	0.4%
count_pt_working_days	Read	492	0.3%
add_gh_working_days	Write	492	0.3%
calculate_circle_properties	Read	491	0.3%
count_ar_working_days	Read	491	0.3%
count_de_working_days	Read	491	0.3%
count_es_working_days	Read	491	0.3%
check_lk_working_day	Read	490	0.3%
count_ireland_working_days	Read	487	0.3%
count_south_africa_working_days	Read	487	0.3%
count_br_working_days	Read	486	0.3%
solve_quadratic_equation	Read	485	0.3%
add_ng_working_days	Write	485	0.3%
count_new_zealand_working_days	Read	482	0.3%
count_fr_working_days	Read	481	0.3%
add_uzbekistan_working_days	Write	477	0.3%
calculate_tip	Write	477	0.3%
check_ke_working_day	Read	476	0.3%
add_gr_working_days	Write	474	0.3%
check_kz_working_day	Read	473	0.3%
check_uzbekistan_working_day	Read	471	0.3%
check_china_working_day	Read	470	0.3%
add_eg_working_days	Write	468	0.3%
add_cl_working_days	Write	467	0.3%
check_gh_working_day	Read	465	0.3%
add_ru_working_days	Write	461	0.3%
add_pk_working_days	Write	460	0.3%
add_bd_working_days	Write	458	0.3%
check_ng_working_day	Read	457	0.3%
check_australia_working_day	Read	456	0.3%
add_hk_working_days	Write	456	0.3%
add_sa_working_days	Write	456	0.3%
add_no_working_days	Write	455	0.3%
check_eg_working_day	Read	450	0.3%
add_co_working_days	Write	450	0.3%
check_ru_working_day	Read	449	0.3%
calculate_molar_mass	Read	448	0.3%
add_fi_working_days	Write	448	0.3%
check_cl_working_day	Read	444	0.3%
add_vn_working_days	Write	443	0.3%
check_gr_working_day	Read	439	0.3%
add_tw_working_days	Write	439	0.3%
check_pk_working_day	Read	437	0.3%
add_th_working_days	Write	436	0.3%
add_dk_working_days	Write	434	0.3%
add_se_working_days	Write	433	0.3%
add_nl_working_days	Write	432	0.3%
add_canada_federal_working_days	Write	431	0.3%
add_kr_working_days	Write	431	0.3%
check_bd_working_day	Read	429	0.3%
check_co_working_day	Read	429	0.3%
calculate_bmi	Read	428	0.3%
add_ch_working_days	Write	427	0.3%
add_singapore_working_days	Write	427	0.3%
add_id_working_days	Write	424	0.3%
add_turkey_working_days	Write	424	0.3%
add_at_working_days	Write	423	0.3%
add_be_working_days	Write	420	0.3%
check_sa_working_day	Read	419	0.3%
add_ph_working_days	Write	419	0.3%
check_hk_working_day	Read	418	0.3%
add_uae_federal_working_days	Write	418	0.3%
add_japan_national_working_days	Write	417	0.3%
add_us_federal_working_days	Write	417	0.3%
add_mx_working_days	Write	416	0.3%
add_it_working_days	Write	412	0.3%
add_pl_working_days	Write	412	0.3%
add_pt_working_days	Write	410	0.3%
add_de_working_days	Write	409	0.3%
add_es_working_days	Write	409	0.3%
check_no_working_day	Read	408	0.3%
check_tw_working_day	Read	408	0.3%
check_vn_working_day	Read	408	0.3%
add_ar_working_days	Write	407	0.3%
check_fi_working_day	Read	405	0.3%
list_working_day_calendars	Read	405	0.3%
add_br_working_days	Write	402	0.3%
check_th_working_day	Read	397	0.3%
add_fr_working_days	Write	397	0.3%
check_nl_working_day	Read	395	0.3%
calculate_percentage_change	Read	392	0.3%
add_south_africa_working_days	Write	392	0.3%
add_ireland_working_days	Write	391	0.3%
add_new_zealand_working_days	Write	388	0.3%
check_dk_working_day	Read	387	0.3%
check_kr_working_day	Read	386	0.3%
check_se_working_day	Read	386	0.3%
check_id_working_day	Read	381	0.3%
check_ch_working_day	Read	380	0.3%
check_at_working_day	Read	376	0.3%
check_singapore_working_day	Read	376	0.3%
check_be_working_day	Read	375	0.3%
check_turkey_working_day	Read	371	0.3%
check_ireland_working_day	Read	366	0.3%
check_ph_working_day	Read	366	0.3%
check_it_working_day	Read	365	0.3%
check_pl_working_day	Read	365	0.3%
check_es_working_day	Read	363	0.3%
check_pt_working_day	Read	363	0.3%
check_canada_federal_working_day	Read	362	0.3%
check_uae_federal_working_day	Read	361	0.3%
check_de_working_day	Read	359	0.3%
check_us_federal_working_day	Read	351	0.2%
check_mx_working_day	Read	347	0.2%
check_south_africa_working_day	Read	347	0.2%
check_ar_working_day	Read	345	0.2%
check_br_working_day	Read	335	0.2%
check_japan_national_working_day	Read	335	0.2%
check_new_zealand_working_day	Read	330	0.2%
check_fr_working_day	Read	326	0.2%
search_calculators	Read	273	0.2%
run_calculator	Execute	220	0.2%
list_calculators	Read	197	0.1%
convert_units	Write	197	0.1%
get_calculator_schema	Read	141	0.1%
list_units	Read	77	0.1%
list_calculator_categories	Read	55	0.0%

// CUT THE COST

Your agent uses a handful of these tools. It pays for all 253.

You don't need all 253 of those definitions in the window. PolicyLayer is an MCP gateway that sits in front of Calcgrid: 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 253 tools (no gateway)	140,850 tokens	—
3 granted tools	~1,670 tokens	−99%
5 granted tools	~2,784 tokens	−98%
10 granted tools	~5,567 tokens	−96%

Create a free account and register Calcgrid — 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 CALCGRID TOKEN COST →

Instant setup, no code required.

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

//FAQ

Calcgrid token-cost questions.

How many tokens does the Calcgrid MCP server use?+

Its 253 tool definitions total 140,850 tokens — 70% 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 Calcgrid 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 Calcgrid's token usage?+

Expose fewer tools. A PolicyLayer grant scopes Calcgrid 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 1,670 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 20-10-2026 from the PolicyLayer scan database over all 253 catalogued Calcgrid tools. Counts refresh with every site build.