Home / Token cost / Raras

The Raras MCP server costs 2,175 tokens before the first call.

Connect Raras and its 21 tool definitions are loaded into the model's context on every request — 1.1% of a 200k window spent before your agent does anything.

QUICK ANSWER The Raras MCP server's tool definitions consume 2,175 tokens — around the median MCP server (1,905 tokens). A scoped grant exposing only the tools you use cuts that roughly in proportion.

MEASURED FROM SCHEMAS 21 tools · 2,175 tokens · 1.1% of 200k · 0.2% 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 1.1%
1M WINDOW 0.2%

Corpus context: Raras ranks #1519 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 2,175 tokens go.

Each row is one tool definition as a tools/list entry — name, description and input schema — counted with o200k_base. Average: 104 tokens per tool.

ToolCategoryTokens% of server
explain_relation Read 198 9.1%
get_literature_relations Read 144 6.6%
get_hypotheses Read 126 5.8%
find_phenotypically_similar Read 123 5.7%
analyze_clinical_case Read 117 5.4%
find_papers_for_disease Read 117 5.4%
get_recent_updates Read 117 5.4%
search_papers_semantic Read 114 5.2%
get_research_log Read 112 5.1%
search_diseases Read 109 5.0%
find_diseases_by_phenotypes Read 108 5.0%
get_evidence Read 103 4.7%
find_reference_centers Read 96 4.4%
find_active_trials Read 94 4.3%
find_communities Read 84 3.9%
find_similar_diseases Read 84 3.9%
search_phenotypes Read 83 3.8%
get_disease_detail Read 75 3.4%
get_sus_coverage Read 73 3.4%
get_schema Read 54 2.5%
get_graph_stats Read 44 2.0%

Most agents use a handful of these tools. They pay for all 21.

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 (104 tokens each).

Grant scopeDefinition costReduction
All 21 tools (no gateway) 2,175 tokens
3 granted tools ~311 tokens −86%
5 granted tools ~518 tokens −76%
10 granted tools ~1,036 tokens −52%

Raras token-cost questions.

How many tokens does the Raras MCP server use?+

Its 21 tool definitions total 2,175 tokens — 1.1% 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 Raras 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 Raras's token usage?+

Expose fewer tools. A PolicyLayer grant scopes Raras 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 311 tokens, a 86% 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 21 catalogued Raras tools. Counts refresh with every site build.

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

A PolicyLayer grant scopes Raras 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.