ctxcap
naeha-s/ctxcap
Offline context-budget MCP server for AI coding agents.
- GitHub stars
- 2
- tools
- 4
- transport
- STDIO
- last updated
- Nov 13, 2026
Tools
4 toolsPublic tool metadata for what this MCP can expose to an agent.
measure_contextReturns the full JSON report for the current working directory
Returns the full JSON report for the current working directory
No parameter schema in public metadata yet.
context_budget_planReturns a deterministic ranked splice plan with safety classifications and preserve spans
Returns a deterministic ranked splice plan with safety classifications and preserve spans
No parameter schema in public metadata yet.
context_budget_verifyReports missed edits and preserve-span violations after applying a plan
Reports missed edits and preserve-span violations after applying a plan
No parameter schema in public metadata yet.
trim_to_budgetDeprecated alias for `context_budget_plan`; always returns `apply: false`
Deprecated alias for `context_budget_plan`; always returns `apply: false`
No parameter schema in public metadata yet.
Sponsors
Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthly
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any language
Agent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any languageReadme
ctxcap
Offline token-budget linter for agent context files. It measures CLAUDE.md,
AGENTS.md, prompts/**, and .cursor/rules/**, finds references that no
longer resolve, and hands your agent a ranked, verifiable plan to get back
under budget.
No config, API key, network, or telemetry. Node >= 20. Two runtime
dependencies: fast-glob and gpt-tokenizer.
npx ctxcap --json
The loop
Context files get trimmed by agents badly: the agent rewrites the file from
memory, drops the ## Never rules, hits the budget, and ships a worse file.
ctxcap closes that loop with line ranges, safety flags, and verification.
npx ctxcap --plan --budget 40000 # ranked plan, JSON
npx ctxcap --plan --budget 40000 --apply # splice atomically
npx ctxcap --verify <planId> # catch drift and violations
Three rules for the agent:
- Splice by
startLine/endLine. Never rewrite a file from scratch. - Never cut a span listed in
preserve. - If
satisfiableis false, reportminAchievableand stop.
Where plans live
Details
- Repository
- github.com/naeha-s/ctxcap
- Website
- github.com/Naeha-S/ctxcap
- Package
ctxcap-mcp- Transport
- STDIO
- Registry
- MCP registry, active