TokenScope
TokenScope is a token-aware directory explorer for Large Language Models that enables intelligent codebase analysis while respecting token limitations. Built by Carlos Gaete-Morales, this Python-based MCP server provides tools for scanning directory structures, extracting file contents, analyzing token usage statistics, and generating comprehensive reports. It features security validation to restrict operations to specified base directories, intelligent file prioritization based on importance, and automatic handling of common file formats like JSON. The implementation respects .gitignore files and includes default ignore patterns for common non-source directories, making it valuable for developers who need to help LLMs understand codebases efficiently without exceeding token limits.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/cdgaete/token-scope-mcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve TokenScope from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.