
TokenSafe
Reduce your AI bills by up to 99% locally: focused code, warm prompt caches & zero secret leaks.
- GitHub stars
- 33
- tools
- 2
- auth
- Secret needed
- transport
- STDIO, HTTP
- last updated
- Nov 13, 2026
Tools
2 toolsPublic tool metadata for what this MCP can expose to an agent.
tokensafe:smart_read_fileReturns the target function plus its 1-hop dependencies instead of the whole file, for 10+ languages, with CSS design tokens preserved.
Returns the target function plus its 1-hop dependencies instead of the whole file, for 10+ languages, with CSS design tokens preserved.
No parameter schema in public metadata yet.
tokensafe:graphMaps architectural hotspots and dependency topology in under 250 tokens instead of a full repository crawl.
Maps architectural hotspots and dependency topology in under 250 tokens instead of a full repository crawl.
No parameter schema in public metadata yet.
Sponsors
Readme
TokenSafe Logo
TokenSafe
Local-First Context Control, Prompt Caching & Secret Guardrails for Coding Agents
Reduce your AI bills by up to 99%. Let your team ship clean code faster and cheaper.
Your coding agents read only the code each task needs and keep prompt caches intact across turns. Everything runs locally on your machine, so your team fixes fewer broken edits and keeps secrets out of git.
Works with Cursor, Claude Code, Codex, Windsurf, Google Antigravity, Gemini CLI, and ChatGPT.
Details
- Repository
- github.com/tokensafe-dev/tokensafe
- Website
- tokensafe.dev
- Category
- AI & LLM Tools
- Package
tokensafe- Transport
- STDIO, HTTP
- Auth
- Required
- Registry
- MCP registry, active