// MCP TOKEN COST

The Ready APIs MCP server costs 13,721 tokens before the first call.

Connect Ready APIs and its 129 tool definitions are loaded into the model's context on every request — 6.9% of a 200k window spent before your agent does anything.

QUICK ANSWER The Ready APIs MCP server's tool definitions consume 13,721 tokens — 7.2× the median MCP server (1,905 tokens). A scoped grant exposing only the tools you use cuts that roughly in proportion.

MEASURED FROM SCHEMAS 129 tools · 13,721 tokens · 6.9% of 200k · 1.4% of 1M Method →

// CONTEXT WINDOW SHARE

What that buys 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 6.9%

1M WINDOW 1.4%

Corpus context: Ready APIs ranks #110 of 3,213 measured MCP servers by definition cost. The median is 1,905 tokens, p90 is 7,952, and the heaviest (Fusionauth) is 183,337 — 92% of a 200k window on its own.

// PER-TOOL BREAKDOWN

Where the 13,721 tokens go.

Each row is one tool definition as a tools/list entry — name, description and input schema — counted with o200k_base. Average: 106 tokens per tool.

Tool	Category	Tokens	% of server
sanctions_search	Read	247	1.8%
hiring_signal	Read	241	1.8%
company_signal	Read	234	1.7%
fred_series	Read	224	1.6%
company_change	Read	221	1.6%
funding_signal	Read	221	1.6%
weather_best_window	Read	216	1.6%
location_score	Read	214	1.6%
remote_hire_cost	Read	214	1.6%
weather_route	Read	214	1.6%
compliance_signal	Read	212	1.5%
counterparty_risk	Read	200	1.5%
tax_calculate	Read	195	1.4%
company_changes	Read	192	1.4%
company_insights	Read	183	1.3%
company_stats	Read	183	1.3%
cyber_risk	Read	175	1.3%
phone_validate	Read	169	1.2%
bin_lookup	Read	165	1.2%
weather_marine	Read	162	1.2%
dns_history	Read	157	1.1%
vin_decode	Read	151	1.1%
dns_compare	Write	148	1.1%
company_registration	Read	146	1.1%
weather_hourly	Read	146	1.1%
intel_rank	Read	142	1.0%
site_risk	Read	142	1.0%
weather_normals	Read	141	1.0%
weather_air_quality	Read	139	1.0%
equities_fundamentals	Read	137	1.0%
email_smtp_probe	Read	136	1.0%
equities_filings	Read	136	1.0%
company_peer_comparison	Write	136	1.0%
weather_compare	Read	135	1.0%
company_network	Read	130	0.9%
weather_historical	Read	129	0.9%
fx_volatility_leaders	Read	127	0.9%
weather_forecast	Read	127	0.9%
weather_degree_days	Read	122	0.9%
flight_reliability	Read	121	0.9%
company_lookup_batch	Read	119	0.9%
jobs_skill_graph	Read	116	0.8%
equities_concept	Read	115	0.8%
fx_movers	Read	115	0.8%
company_lookup_auto	Read	114	0.8%
tech_stack	Read	113	0.8%
geo_zip_batch	Read	112	0.8%
geo_nearby	Read	107	0.8%
fx_strength	Read	106	0.8%
dns_certificates	Read	105	0.8%
dns_tls	Read	105	0.8%
fx_correlation	Read	105	0.8%
company_cik	Read	101	0.7%
fred_search	Read	101	0.7%
jobs_concentration	Read	101	0.7%
company_timeline	Read	98	0.7%
company_domains_batch	Read	97	0.7%
fx_pair	Read	97	0.7%
fx_timeseries	Read	97	0.7%
dns_profile	Read	96	0.7%
flight_cancellation_risk	Read	96	0.7%
tax_state_brackets	Read	95	0.7%
flight_route_summary	Read	93	0.7%
fx_historical	Read	92	0.7%
fx_convert	Write	92	0.7%
email_validate	Read	91	0.7%
geo_ip	Read	91	0.7%
geo_zip_lookup	Read	90	0.7%
dns_lookup	Read	87	0.6%
dns_reputation	Read	86	0.6%
tax_summary	Read	85	0.6%
jobs_companies_hiring	Read	84	0.6%
weather_alerts	Read	84	0.6%
weather_current	Read	84	0.6%
address_validate	Read	83	0.6%
address_validate_batch	Read	82	0.6%
jobs_skill_trends	Read	82	0.6%
geo_city_search	Read	81	0.6%
jobs_momentum	Read	81	0.6%
jobs_profile	Read	79	0.6%
address_enrich	Read	78	0.6%
tax_federal_brackets	Read	78	0.6%
jobs_related_skills	Read	77	0.6%
jobs_role_skills	Read	76	0.6%
company_nonprofit_search	Read	75	0.5%
equities_ticker	Read	74	0.5%
phone_region	Read	73	0.5%
geo_county_lookup	Read	72	0.5%
jobs_salary_signals	Read	72	0.5%
tax_standard_deduction	Read	72	0.5%
weather_zip	Read	72	0.5%
intel_role_profiles	Read	71	0.5%
company_enrich	Read	70	0.5%
geo_enrich	Read	70	0.5%
jobs_scarcity	Read	69	0.5%
geo_timezone	Read	68	0.5%
dns_whois	Read	67	0.5%
calendar_business_days_add	Write	67	0.5%
company_search	Read	66	0.5%
flight_route_best_times	Read	66	0.5%
flight_airport_delay_profile	Read	65	0.5%
flight_airline_reliability	Read	64	0.5%
fx_rates	Read	64	0.5%
calendar_is_business_day	Read	63	0.5%
email_disposable	Read	62	0.5%
email_free_provider	Read	62	0.5%
company_nonprofit_ein	Read	61	0.4%
fred_popular	Read	60	0.4%
geo_asn	Read	60	0.4%
meta_dataset	Read	60	0.4%
company_classify	Write	60	0.4%
company_industry	Read	59	0.4%
jobs_remote_trends	Read	57	0.4%
company_domain	Read	56	0.4%
company_ticker	Read	56	0.4%
tax_mileage_rates	Read	56	0.4%
tax_retirement_limits	Read	56	0.4%
meta_catalog	Read	55	0.4%
tax_deadlines	Read	55	0.4%
calendar_holidays	Read	54	0.4%
intel_risk_profiles	Read	51	0.4%
intel_buyer_profiles	Read	49	0.4%
intel_site_profiles	Read	49	0.4%
intel_cyber_profiles	Read	46	0.3%
fx_currencies	Read	45	0.3%
intel_compliance_profiles	Read	45	0.3%
intel_funding_profiles	Read	45	0.3%
intel_hiring_profiles	Read	43	0.3%
intel_change_profiles	Read	42	0.3%

// SCOPED GRANT

Most agents use a handful of these tools. They pay for all 129.

A PolicyLayer grant exposes only the tools you allow — ungranted definitions are filtered out of the tool list, so they never enter the context window. Estimates below assume typical-weight tools (106 tokens each).

Grant scope	Definition cost	Reduction
All 129 tools (no gateway)	13,721 tokens	—
3 granted tools	~319 tokens	−98%
5 granted tools	~532 tokens	−96%
10 granted tools	~1,064 tokens	−92%

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

//FAQ

Ready APIs token-cost questions.

How many tokens does the Ready APIs MCP server use?+

Its 129 tool definitions total 13,721 tokens — 6.9% 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 Ready APIs 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 Ready APIs's token usage?+

Expose fewer tools. A PolicyLayer grant scopes Ready APIs 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 319 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 07-06-2026 from the PolicyLayer scan database over all 129 catalogued Ready APIs tools. Counts refresh with every site build.