Add context-cost badge (transparency for the default toolset's schema size) - #3083
Open
athakur3 wants to merge 1 commit into
Open
Add context-cost badge (transparency for the default toolset's schema size)#3083athakur3 wants to merge 1 commit into
athakur3 wants to merge 1 commit into
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
One line: a shields.io badge showing what the server's tool schemas cost in context tokens — currently 54,422 tokens across 44 tools for the default Docker toolset (measured 2026-08-16). This is transparency users repeatedly ask for when budgeting context windows, and the number is already widely discussed in the ecosystem — a badge makes it accurate, versioned, and linked to a reproducible method instead of folklore.
Framing note: this is not a judgment — a full-platform server can be worth every token, and toolset filtering exists precisely for cost control. The per-tool breakdown may be independently useful: the top 5 tools (
issue_write1,890,list_issues1,783,pull_request_read1,737,pull_request_review_write1,681,search_issues1,678) carry a large share, mostly in inputSchema depth — results/github/measurement.json has the full capture.The badge JSON lives in our repo and refreshes weekly; the number links to the methodology — raw
tools/listcapture + pinnedo200k_basetokenizer, re-derivable in five lines from the published measurement. Numbers you can refute beat numbers people quote.If you'd rather not carry this, close freely — no hard feelings. To own the number in your own CI instead: sd2k/mcp-tokens-action (badge support proposed in sd2k/mcp-tokens-action#5).