Home / Token cost / Rhombus Node

The Rhombus Node MCP server costs 44,100 tokens before the first call.

Connect Rhombus Node and its 31 tool definitions are loaded into the model's context on every request — 22% of a 200k window spent before your agent does anything.

QUICK ANSWER The Rhombus Node MCP server's tool definitions consume 44,100 tokens — 41× the median MCP server (1,075 tokens). A scoped grant exposing only the tools you use cuts that roughly in proportion.

MEASURED FROM SCHEMAS 31 tools · 44,100 tokens · 22% of 200k · 4.4% 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 22%
1M WINDOW 4.4%

Corpus context: Rhombus Node ranks #8 of 1,659 measured MCP servers by definition cost. The median is 1,075 tokens, p90 is 6,119, and the heaviest (Fusionauth) is 183,337 — 92% of a 200k window on its own.

Where the 44,100 tokens go.

Each row is one tool definition as a tools/list entry — name, description and input schema — counted with o200k_base. Average: 1,423 tokens per tool.

ToolCategoryTokens% of server
report-tool Read 7,546 17.1%
events-tool Execute 3,820 8.7%
door-schedule-exception-tool Write 3,009 6.8%
faces-tool Read 2,797 6.3%
policy-alerts-tool Execute 2,444 5.5%
clips-tool Execute 2,412 5.5%
lpr-tool Execute 2,287 5.2%
automated-prompts-tool Destructive 1,954 4.4%
camera-tool Write 1,634 3.7%
analytics-tool Read 1,590 3.6%
search-tool Read 1,490 3.4%
update-tool Write 1,336 3.0%
access-control-tool Read 1,102 2.5%
user-tool Read 989 2.2%
video-walls-tool Read 916 2.1%
user-access-trail-tool Read 838 1.9%
door-tool Write 827 1.9%
user-audit-tool Read 804 1.8%
rules-tool Destructive 785 1.8%
alarm-monitoring-tool Read 781 1.8%
guest-management-tool Read 767 1.7%
entity-lookup-tool Read 758 1.7%
camera-uptime-tool Read 742 1.7%
get-entity-tool Read 714 1.6%
create-camera-policy-tool Write 707 1.6%
location-tool Write 281 0.6%
time-tool Read 276 0.6%
time-conversion-tool Read 156 0.4%
count-tool Read 143 0.3%
reboot-cameras Read 138 0.3%
get-org-information Read 57 0.1%

Most agents use a handful of these tools. They pay for all 31.

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 (1,423 tokens each).

Grant scopeDefinition costReduction
All 31 tools (no gateway) 44,100 tokens
3 granted tools ~4,268 tokens −90%
5 granted tools ~7,113 tokens −84%
10 granted tools ~14,226 tokens −68%

Rhombus Node token-cost questions.

How many tokens does the Rhombus Node MCP server use?+

Its 31 tool definitions total 44,100 tokens — 22% 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 Rhombus Node 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 Rhombus Node's token usage?+

Expose fewer tools. A PolicyLayer grant scopes Rhombus Node 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 4,268 tokens, a 90% 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 05-06-2026 from the PolicyLayer scan database over all 31 catalogued Rhombus Node tools. Counts refresh with every site build.

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

A PolicyLayer grant scopes Rhombus Node 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.