octocode-mcp and srclight
These are **competitors** — both provide semantic code search and indexing capabilities for MCP servers, but OctoCode emphasizes real-time LLM-based search across public/private repositories while Srclight focuses on local deep indexing with hybrid FTS5+embedding search and advanced analysis tools like call graphs and git blame.
About octocode-mcp
bgauryy/octocode-mcp
MCP server for semantic code research and context generation on real-time using LLM patterns | Search naturally across public & private repos based on your permissions | Transform any accessible codebase/s into AI-optimized knowledge on simple and complex flows | Find real implementations and live docs from anywhere
Implements MCP (Model Context Protocol) with LSP-powered code intelligence (Go to Definition, Find References, Call Hierarchy) across GitHub, GitLab, and local codebases, enabling compiler-level understanding without parsing. Provides modular Agent Skills—including multi-phase research with session persistence, AST-driven code analysis, dependency graphing, and PR review across seven domains—composable via CLI or direct integration into Claude/Cursor.
About srclight
srclight/srclight
Deep code indexing MCP server for AI agents. 25 tools: hybrid FTS5 + embedding search, call graphs, git blame/hotspots, build system analysis. Multi-repo workspaces, GPU-accelerated semantic search, 10 languages via tree-sitter. Fully local, zero cloud dependencies.
Implements a filesystem-watched SQLite + tree-sitter indexing layer that increments on git changes via post-commit hooks, with optional Ollama embeddings cached as `.npy` matrices for GPU-accelerated cosine similarity in ~3ms. Operates as a stdio or SSE MCP transport server compatible with Claude Code and Cursor, supporting multi-repo workspaces through SQLite ATTACH and RRF-ranked hybrid search across keyword (FTS5/trigram) and semantic results.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work