// MCP TOKEN COST

The PoolParty Main Stage Airtime MCP server costs 15,925 tokens before the first call.

Connect PoolParty Main Stage Airtime and its 71 tool definitions are loaded into the model's context on every request — 8.0% of a 200k window spent before your agent does anything.

QUICK ANSWER The PoolParty Main Stage Airtime MCP server's tool definitions consume 15,925 tokens — 8.4× the median MCP server (1,905 tokens). A scoped grant exposing only the tools you use cuts that roughly in proportion.

MEASURED FROM SCHEMAS 71 tools · 15,925 tokens · 8.0% of 200k · 1.6% 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 8.0%

1M WINDOW 1.6%

Corpus context: PoolParty Main Stage Airtime ranks #85 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 15,925 tokens go.

Each row is one tool definition as a tools/list entry — name, description and input schema — counted with o200k_base. Average: 224 tokens per tool.

Tool	Category	Tokens	% of server
revise_slide_block	Read	808	5.1%
admit_programming_candidates	Write	765	4.8%
preview_slide_block	Read	639	4.0%
draft_slide_block_from_project	Read	534	3.4%
inspect_programming_discovery_inventory	Read	492	3.1%
quote_sponsor_reservation	Read	453	2.8%
submit_media_block	Write	417	2.6%
configure_open_call	Write	392	2.5%
prepare_block_mint	Read	382	2.4%
complete_sim_pool_back	Write	372	2.3%
request_pilot_key	Read	367	2.3%
complete_media_upload	Write	367	2.3%
request_media_upload_url	Write	340	2.1%
pool_block	Read	328	2.1%
prepare_superblock_purchase	Read	311	2.0%
withdraw_pool_support	Read	298	1.9%
draft_program_queue	Write	294	1.8%
browse_channels	Read	280	1.8%
finalize_pool_support	Read	279	1.8%
finalize_block_mint	Financial	277	1.7%
create_channel_from_template	Write	276	1.7%
list_programming_candidates	Read	271	1.7%
get_channel_feed	Read	267	1.7%
attach_wallet_to_session	Write	262	1.6%
quote_superblock_reservation	Write	244	1.5%
update_channel_settings	Write	243	1.5%
settle_paid_action	Read	235	1.5%
claim_test_pol	Read	201	1.3%
claim_test_collateral	Read	196	1.2%
get_distribution_report	Read	196	1.2%
simulate_program_queue_publish	Write	192	1.2%
get_block_mint_status	Read	176	1.1%
get_pooling_receipt	Read	175	1.1%
get_channel_stream	Read	173	1.1%
publish_program_queue	Write	170	1.1%
create_program_item	Write	167	1.0%
get_wallet_pooling_state	Read	166	1.0%
set_programming_bucket	Write	164	1.0%
get_sim_signer_access	Read	162	1.0%
get_channel_metrics	Read	153	1.0%
get_block_economics	Read	151	0.9%
get_paid_action_receipt	Read	147	0.9%
reorder_program_queue	Write	145	0.9%
accept_programming_proposal	Write	139	0.9%
get_collateral_opportunity	Read	134	0.8%
insert_live_next	Write	130	0.8%
remove_live_queue_item	Destructive	128	0.8%
propose_program_order	Read	128	0.8%
preview_channel_template	Execute	127	0.8%
create_join_session	Write	127	0.8%
resolve_channel	Write	125	0.8%
get_airtime_opportunity	Read	121	0.8%
list_block_types	Read	118	0.7%
check_key_request_status	Read	113	0.7%
get_block_type_schema	Read	113	0.7%
preview_programming_candidate	Read	113	0.7%
get_open_submission_calls	Read	112	0.7%
get_program_mode_manifest	Read	112	0.7%
skip_current_live_item	Read	110	0.7%
list_channel_templates	Read	102	0.6%
list_programming_scope_profiles	Read	97	0.6%
list_program_modes	Read	94	0.6%
list_programming_buckets	Read	92	0.6%
get_sponsor_opportunities	Read	90	0.6%
inspect_channel_programming_policy	Read	89	0.6%
get_superblock_offerings	Read	86	0.5%
get_key_info	Read	84	0.5%
get_reward_opportunities	Read	84	0.5%
list_live_queue	Read	81	0.5%
list_program_queue	Read	80	0.5%
get_platform_pulse	Read	69	0.4%

// SCOPED GRANT

Most agents use a handful of these tools. They pay for all 71.

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 (224 tokens each).

Grant scope	Definition cost	Reduction
All 71 tools (no gateway)	15,925 tokens	—
3 granted tools	~673 tokens	−96%
5 granted tools	~1,121 tokens	−93%
10 granted tools	~2,243 tokens	−86%

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

//FAQ

PoolParty Main Stage Airtime token-cost questions.

How many tokens does the PoolParty Main Stage Airtime MCP server use?+

Its 71 tool definitions total 15,925 tokens — 8.0% 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 PoolParty Main Stage Airtime 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 PoolParty Main Stage Airtime's token usage?+

Expose fewer tools. A PolicyLayer grant scopes PoolParty Main Stage Airtime 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 673 tokens, a 96% 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 71 catalogued PoolParty Main Stage Airtime tools. Counts refresh with every site build.

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

A PolicyLayer grant scopes PoolParty Main Stage Airtime 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.