mcp-context-cost

pandoc — context cost

1,425 tokens across 1 tools — light (1–5K). Measured 2026-08-16 under methodology v1.0.

   
server (self-reported) mcp-pandoc v0.11.1
status measured
tokenizer tiktoken / o200k_base
launch command uvx mcp-pandoc
isolation docker · ghcr.io/astral-sh/uv:python3.12-bookworm-slim · network bridge · network enabled for package fetch; clean FS, no host credentials
env vars supplied none
canonical SHA-256 4d8f9de25d7aa74f0fb5e0c828a904d74b3934e62cb1032bc6cf0fada1f0d952
category community
source https://github.com/vivekVells/mcp-pandoc

Where the tokens are

tool tokens share description schema
convert-contents 1,423 99.9% 996 361

Each tool is tokenized on its own, so the parts do not sum exactly to the whole: the array adds its own brackets and commas, and the tokenizer merges tokens across object boundaries. The badge number is always the count of the whole array, never a sum of parts.

Re-derive it

npx -y mcp-context-cost verify results/pandoc/measurement.json

That re-tokenizes the published capture and checks the count and the hash. If it disagrees with the badge, the badge is wrong — open an issue and it gets corrected.

Badge JSON · All servers · Leaderboard · Methodology