Navigate codebases by symbol and retain memory across sessions.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "io.github.Mibayy/token-savior" MCP server from askskill: Run: claude mcp add 'io-github-mibayy-token-savior' -- npx -y token-savior-recall
Developers working in unfamiliar or complex codebases can navigate by symbol instead of manually browsing files, speeding up code understanding.
When code investigation spans multiple sessions, users can rely on persistent memory to continue from prior context instead of rebuilding it from scratch.
Researchers or technical leads can trace module relationships around key symbols to organize code structure and responsibility boundaries more efficiently.
This is a structural MCP tool for codebases. It lets you navigate code by symbol and preserves memory across sessions for ongoing analysis.
Based on the description, it focuses on structured symbol-based navigation rather than simple keyword matching, and it also provides cross-session memory. For more specifics, see the source repository.
The provided materials do not include installation steps, runtime details, or key requirements. Please see the source repository for prerequisites.
Index repositories into a persistent graph for fast code search and understanding.
Build a persistent code cache for fast semantic lookup and lower token usage.
Build persistent, semantically searchable memory for codebases via natural language queries.
Build persistent code memory for cross-session analysis, search, and documentation.
Analyze multi-language codebases with semantic search and static analysis.
Build local codebase memory for AI agents with search and architecture inspection.