Home / Token cost / Space0

The Space0 MCP server costs 15,184 tokens before the first call.

Connect Space0 and its 60 tool definitions are loaded into the model's context on every request — 7.6% of a 200k window spent before your agent does anything.

QUICK ANSWER The Space0 MCP server's tool definitions consume 15,184 tokens — 8.0× the median MCP server (1,905 tokens). A scoped grant exposing only the tools you use cuts that roughly in proportion.

MEASURED FROM SCHEMAS 60 tools · 15,184 tokens · 7.6% of 200k · 1.5% of 1M Method →

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 7.6%
1M WINDOW 1.5%

Corpus context: Space0 ranks #91 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.

Where the 15,184 tokens go.

Each row is one tool definition as a tools/list entry — name, description and input schema — counted with o200k_base. Average: 253 tokens per tool.

ToolCategoryTokens% of server
plan_build Write 710 4.7%
create_memory_post Write 688 4.5%
build Execute 658 4.3%
append_memory Read 653 4.3%
place_block Destructive 541 3.6%
label_region Execute 526 3.5%
survey_site Destructive 479 3.2%
recall_nearby_memories Execute 475 3.1%
get_material_palette Read 465 3.1%
set_soul Write 418 2.8%
look_at Read 403 2.7%
cognitive_boot Write 400 2.6%
look_around Destructive 362 2.4%
find_clear_region Read 357 2.4%
move_to Write 357 2.4%
mark_memories_used Write 356 2.3%
ingest_post_media Write 349 2.3%
set_goal Write 295 1.9%
scan Read 289 1.9%
inspect_region Read 287 1.9%
create_commitment Write 270 1.8%
recall_nearby_posts Execute 242 1.6%
my_recent_brushes Read 233 1.5%
compose_card_preview Read 217 1.4%
link_to_owner Execute 214 1.4%
delete_memory_post Destructive 212 1.4%
say Write 211 1.4%
undo_last_brushes Destructive 203 1.3%
save_skill Write 203 1.3%
list_surfaces Read 202 1.3%
supersede_memory Read 198 1.3%
record_drives_drift Read 194 1.3%
enter_space Execute 184 1.2%
assert_coverage Execute 178 1.2%
list_spaces Read 170 1.1%
poll_events Read 168 1.1%
save_brain_state Write 167 1.1%
invoke_skill Execute 161 1.1%
search_memories Read 155 1.0%
record_skill_outcome Read 153 1.0%
search_skills Read 149 1.0%
coverage_of Execute 148 1.0%
list_my_skills Read 143 0.9%
complete_goal Write 141 0.9%
get_cell Read 131 0.9%
inspect_region_provenance Read 131 0.9%
list_regions Read 131 0.9%
update_commitment Write 126 0.8%
extend_commitment Read 115 0.8%
commitment_sweep Read 105 0.7%
list_soul_revisions Read 102 0.7%
list_sticker_presets Read 96 0.6%
recent_memory Read 96 0.6%
get_soul Read 94 0.6%
touch_commitment Read 89 0.6%
list_commitments Read 87 0.6%
get_build_info Read 86 0.6%
who_is_here Read 74 0.5%
load_brain_state Destructive 69 0.5%
leave_space Destructive 68 0.4%

Most agents use a handful of these tools. They pay for all 60.

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 (253 tokens each).

Grant scopeDefinition costReduction
All 60 tools (no gateway) 15,184 tokens
3 granted tools ~759 tokens −95%
5 granted tools ~1,265 tokens −92%
10 granted tools ~2,531 tokens −83%

Space0 token-cost questions.

How many tokens does the Space0 MCP server use?+

Its 60 tool definitions total 15,184 tokens — 7.6% 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 Space0 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 Space0's token usage?+

Expose fewer tools. A PolicyLayer grant scopes Space0 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 759 tokens, a 95% 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.

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 60 catalogued Space0 tools. Counts refresh with every site build.

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

A PolicyLayer grant scopes Space0 to the tools you actually allow. Ungranted definitions never load, and every call that does run is checked against policy first.

Free to start. No card required.

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

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.