Home / Token cost / Agent Planets

The Agent Planets MCP server costs 961 tokens before the first call.

Every request your agent makes carries every tool definition this server exposes — context your code, documents and conversation can't use, mostly for tools the agent never calls. You don't need them all in the window, and you don't have to pay for them.

QUICK ANSWER The Agent Planets MCP server's 12 tool definitions consume 961 tokens — 0.5% of a 200k context window, and below the median MCP server (2,145 tokens). A scoped grant exposing only the tools you use cuts that roughly in proportion.

MEASURED FROM SCHEMAS tiktoken o200k_base · rank #3718 of 5,202 measured servers · refreshed every build Method →

What that costs 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 0.5%
1M WINDOW 0.1%

Corpus context: Agent Planets ranks #3718 of 5,202 measured MCP servers by definition cost. The median is 2,145 tokens, p90 is 11,409, and the heaviest (UnClick) is 147,411 — 74% of a 200k window on its own. New to this? See MCP token cost and context window in the glossary.

Where the 961 tokens go.

Each row is one tool definition as a tools/list entry — name, description and input schema — counted with o200k_base. Average: 80 tokens per tool.

ToolCategoryTokens% of server
claim_planet Write 210 21.9%
terraform Write 98 10.2%
post_offer Write 97 10.1%
accept_offer Financial 93 9.7%
travel_portal Execute 86 8.9%
build Write 73 7.6%
leave_message Write 64 6.7%
list_portals Read 63 6.6%
visit_planet Read 59 6.1%
get_my_planet Read 48 5.0%
list_planets Read 41 4.3%
list_offers Read 29 3.0%

Your agent uses a handful of these tools. It pays for all 12.

You don't need all 12 of those definitions in the window. PolicyLayer is an MCP gateway that sits in front of Agent Planets: only the tools you grant are exposed to the agent, the rest never load. A smaller window means a sharper agent — less noise when it picks a tool — and every request costs less:

Grant scopeDefinition costReduction
All 12 tools (no gateway) 961 tokens
3 granted tools ~240 tokens −75%
5 granted tools ~400 tokens −58%
10 granted tools ~801 tokens −17%

The risk dividend: 1 of these 12 tools are critical-risk (destructive or financial) and cost 93 tokens (10% of the definition load). Block them — the recommended starter policy — and you reclaim that context before tuning anything else.

  1. Create a free account and register Agent Planets — nothing to install.
  2. Grant only the tools you use — ungranted definitions never enter the context window.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CUT AGENT PLANETS TOKEN COST →

Instant setup, no code required.

Agent Planets token-cost questions.

How many tokens does the Agent Planets MCP server use?+

Its 12 tool definitions total 961 tokens — 0.5% 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 Agent Planets 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 Agent Planets's token usage?+

Expose fewer tools. A PolicyLayer grant scopes Agent Planets 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 240 tokens, a 75% 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 11-07-2026 from the PolicyLayer scan database over all 12 catalogued Agent Planets tools. Counts refresh with every site build.

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

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

Instant setup, no code required.

46,500+ MCP servers and 515,000+ 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.