CodeGraphContext
This MCP server provides AI-powered code analysis by indexing local Python codebases into a Neo4j graph database, enabling sophisticated relationship queries and context discovery for development workflows. Built by Shashank Shekhar Singh using Python with Neo4j, watchdog for file monitoring, and Typer for CLI interaction, it offers 12 specialized tools including code indexing with background job processing, real-time file watching for active projects, function call relationship analysis, class hierarchy exploration, dead code detection, and direct Cypher query execution. The implementation features cyclomatic complexity calculation, full-text search across code elements, import dependency tracking, and an interactive setup wizard that supports both local Neo4j installations and hosted AuraDB connections, making it valuable for developers who need programmatic access to code structure and relationships for refactoring, impact analysis, and codebase understanding tasks.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- database
- Source
- PulseMCP
- Repository
- github.com/codegraphcontext/codegraphcontext
- Author type
- human
- Updated
- 2026-05-27
Use via MCP
Resolve CodeGraphContext 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.