// MCP TOKEN COST

The Mcp Reunion MCP server costs 11,927 tokens before the first call.

Connect Mcp Reunion and its 99 tool definitions are loaded into the model's context on every request — 6.0% of a 200k window spent before your agent does anything.

QUICK ANSWER The Mcp Reunion MCP server's tool definitions consume 11,927 tokens — 6.3× the median MCP server (1,905 tokens). A scoped grant exposing only the tools you use cuts that roughly in proportion.

MEASURED FROM SCHEMAS 99 tools · 11,927 tokens · 6.0% of 200k · 1.2% 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 6.0%

1M WINDOW 1.2%

Corpus context: Mcp Reunion ranks #135 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 11,927 tokens go.

Each row is one tool definition as a tools/list entry — name, description and input schema — counted with o200k_base. Average: 120 tokens per tool.

Tool	Category	Tokens	% of server
reunion_query_dataset	Read	217	1.8%
reunion_search_catalog	Read	172	1.4%
reunion_get_pathology_prevalence	Read	171	1.4%
reunion_search_sirene_establishments	Read	169	1.4%
reunion_get_weather_observations	Read	162	1.4%
reunion_search_real_estate_transactions	Read	159	1.3%
reunion_search_road_accidents	Read	158	1.3%
reunion_search_schools	Read	158	1.3%
reunion_search_classified_accommodations	Read	157	1.3%
reunion_possession_search_procurement	Read	154	1.3%
reunion_get_higher_education_enrollment	Read	153	1.3%
reunion_search_tourism_establishments	Read	153	1.3%
reunion_search_public_facilities	Read	150	1.3%
reunion_get_air_quality	Read	147	1.2%
reunion_get_legislative_2022_round2	Read	147	1.2%
reunion_get_legislative_2022_round1	Read	145	1.2%
reunion_get_presidential_2022_round1	Read	145	1.2%
reunion_get_caf_beneficiaries	Read	144	1.2%
reunion_list_5g_sites	Read	143	1.2%
reunion_search_ban_addresses	Read	143	1.2%
reunion_search_local_elected_officials	Read	143	1.2%
reunion_search_car_jaune_stops	Read	142	1.2%
reunion_get_lycee_ips	Read	141	1.2%
reunion_search_finess_establishments	Read	141	1.2%
reunion_search_sport_facilities	Read	141	1.2%
reunion_search_health_professionals	Read	140	1.2%
reunion_get_college_ips	Read	139	1.2%
reunion_search_baby_names	Read	139	1.2%
reunion_get_consumer_price_index	Read	138	1.2%
reunion_search_feder_beneficiaries	Read	138	1.2%
reunion_list_land_potential	Read	137	1.1%
reunion_search_plu_zones	Read	137	1.1%
reunion_possession_search_association_grants	Read	136	1.1%
reunion_search_admin_directory	Read	136	1.1%
reunion_search_building_permits	Read	136	1.1%
reunion_search_parcoursup_formations	Read	135	1.1%
reunion_search_joconde_collections	Read	134	1.1%
reunion_search_residential_permits	Read	134	1.1%
reunion_get_road_traffic	Read	133	1.1%
reunion_search_boamp	Read	133	1.1%
reunion_list_priority_education_schools	Read	131	1.1%
reunion_search_rge_companies	Read	130	1.1%
reunion_get_covid_emergency_stats	Read	129	1.1%
reunion_get_jobseekers_by_age_sex	Read	129	1.1%
reunion_list_childcare_facilities	Read	128	1.1%
reunion_search_training_organizations	Read	128	1.1%
reunion_compare_communes	Read	127	1.1%
reunion_list_hiking_circuits	Read	126	1.1%
reunion_search_possession_health_pros	Read	126	1.1%
reunion_list_water_management_points	Read	124	1.0%
reunion_get_income_poverty_by_iris	Read	123	1.0%
reunion_lookup_postal_codes	Read	123	1.0%
reunion_get_legislative_2024_round1	Read	122	1.0%
reunion_get_legislative_2024_round2	Read	122	1.0%
reunion_search_associations	Read	121	1.0%
reunion_list_swimming_pools	Read	119	1.0%
reunion_list_landmarks	Read	118	1.0%
reunion_get_waste_tonnage	Read	117	1.0%
reunion_list_festivals	Read	117	1.0%
reunion_list_gen2024_schools	Read	115	1.0%
reunion_search_vehicle_inspection_prices	Read	115	1.0%
reunion_get_covid_hospital_stats	Read	114	1.0%
reunion_get_tourism_frequentation	Read	113	0.9%
reunion_get_commune_population	Read	112	0.9%
reunion_get_caf_amounts	Read	109	0.9%
reunion_get_housing_overview	Read	109	0.9%
reunion_get_jobseekers_by_commune	Read	109	0.9%
reunion_get_museum_attendance	Read	108	0.9%
reunion_commune_profile	Read	107	0.9%
reunion_get_cycle_network	Read	107	0.9%
reunion_get_east_coastal_trail	Read	105	0.9%
reunion_inspect_dataset	Read	104	0.9%
reunion_iris_profile	Read	104	0.9%
reunion_find_commune	Read	103	0.9%
reunion_get_road_classification	Read	103	0.9%
reunion_get_social_housing_costs	Read	103	0.9%
reunion_list_communes	Read	103	0.9%
reunion_get_petroleum_consumption	Read	101	0.8%
reunion_get_speed_limits	Read	101	0.8%
reunion_search_bal_possession	Read	101	0.8%
reunion_list_iris	Read	98	0.8%
reunion_list_priority_neighborhoods	Read	98	0.8%
reunion_list_canyons	Read	96	0.8%
reunion_list_cultural_leisure_pois	Read	95	0.8%
reunion_list_znieff	Read	91	0.8%
reunion_get_road_daily_flow	Read	90	0.8%
reunion_list_coworking_spaces	Read	89	0.7%
reunion_get_european_2024	Read	84	0.7%
reunion_list_libraries	Read	84	0.7%
reunion_list_family_trails	Read	77	0.6%
reunion_list_cantons	Read	67	0.6%
reunion_list_epci	Read	61	0.5%
reunion_get_ftth_coverage	Read	60	0.5%
reunion_list_national_park_perimeters	Read	60	0.5%
reunion_list_saint_denis_quarters	Read	60	0.5%
reunion_list_car_jaune_routes	Read	56	0.5%
reunion_list_weather_stations	Read	53	0.4%
reunion_list_museums	Read	52	0.4%
reunion_list_ecolodge_locations	Read	50	0.4%

// SCOPED GRANT

Most agents use a handful of these tools. They pay for all 99.

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 (120 tokens each).

Grant scope	Definition cost	Reduction
All 99 tools (no gateway)	11,927 tokens	—
3 granted tools	~361 tokens	−97%
5 granted tools	~602 tokens	−95%
10 granted tools	~1,205 tokens	−90%

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

//FAQ

Mcp Reunion token-cost questions.

How many tokens does the Mcp Reunion MCP server use?+

Its 99 tool definitions total 11,927 tokens — 6.0% 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 Mcp Reunion 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 Mcp Reunion's token usage?+

Expose fewer tools. A PolicyLayer grant scopes Mcp Reunion 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 361 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 07-06-2026 from the PolicyLayer scan database over all 99 catalogued Mcp Reunion tools. Counts refresh with every site build.

Expose only the tools you use — the rest never enter your context.

A PolicyLayer grant scopes Mcp Reunion to the tools you actually allow. Ungranted definitions never load, and every call that does run is checked against policy first.

SCOPE YOUR GRANT →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.