# forloopcodes/contextplus

Semantic Intelligence for Large-Scale Engineering. Context+ is an MCP server designed for developers who demand 99% accuracy. By combining RAG, Tree-sitter AST, Spectral Clustering, and Obsidian-style linking, Context+ turns a massive codebase into a searchable, hierarchical feature graph.

Repository: https://github.com/forloopcodes/contextplus
Canonical: https://ross.abutalabs.com/products/contextplus
Homepage: https://contextplus.vercel.app
Language: TypeScript
License: MIT
License Family: permissive
Topics: mcp-server
Last push: 2026-07-13T09:40:42+00:00

## Health v2 (maintenance only)
Score: 56/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 92, release rhythm 35, longevity 13
- inputs: {"age_days": 187, "days_push": 51, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1976, forks 165 (observed 2026-08-28T04:06:01.391232+00:00)

## What it is
Context+ is an MCP server that gives AI coding agents semantic understanding of large codebases by combining RAG embeddings, Tree-sitter AST parsing, and spectral clustering into a searchable hierarchical feature graph. It exposes tools for semantic code search, blast-radius analysis, static analysis, and validated code writes via stdio to IDEs like Claude Code, Cursor, and VS Code.

## Use cases
- give my AI coding agent accurate context about a large codebase
- search code by meaning instead of exact text
- find every file and line affected by changing a function
- map features to code files in a massive repository
- reduce token usage when agents explore a codebase
- run semantic navigation over a monorepo with an MCP server

## When to choose
- you use MCP-compatible IDEs or agents (Claude Code, Cursor, Windsurf, VS Code) on large codebases
- you want semantic retrieval plus AST-accurate symbol and line-level results
- you can run Ollama locally or via cloud for embeddings and chat models

## When to avoid
- you need a standalone code search tool without an MCP client
- you cannot run Ollama or provide an Ollama API key
- your project is small enough that plain grep or IDE search suffices

## Facets
- artifact type: service
- maturity: active
- function: mcp, rag, search-engine, parser, static-site-generator
- domain: developer-tools, large-language-models
- platform: cli, cross-platform
- tags: mcp-server, code-search, tree-sitter, spectral-clustering, semantic-code-navigation, ollama, codebase-understanding, typescript, ai-agents, search, nodejs

## Member repositories
- forloopcodes/contextplus (main) score 56

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:01.391232+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:04:49.730032+00:00, confidence not recorded.
  - readme: https://github.com/forloopcodes/contextplus (fetched 2026-08-28T04:06:01.391232+00:00, sha 3eedb3832817)
  - homepage: https://contextplus.vercel.app (fetched 2026-08-29T10:44:15.820583+00:00, sha cf51566cb9cb)
- Data as of 2026-08-30T08:39:29.467469+00:00.