Repository Search
This MCP server implementation provides a file search functionality for text content within a specified repository. Developed with TypeScript and utilizing the Model Context Protocol SDK, it offers efficient searching capabilities while respecting ignore patterns defined in a .reposearchignore file. The server is designed to work in Node.js environments and includes features for file traversal, content matching, and result filtering. It's particularly useful for AI applications or development tools that require quick and accurate text searches across codebases or document repositories. The implementation focuses on performance and configurability, making it suitable for both small-scale projects and larger, more complex file systems.
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 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- search
- Source
- PulseMCP
- Repository
- github.com/astricaelus/mcp-server-reposearch
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Repository Search 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.