# ctx++

> Use this tool when you need to analyze and search large codebases across multiple programming languages, or when you want to identify related code snippets and understand call relationships. It solves problems such as finding relevant code, understanding feature implementations, and analyzing the impact of code changes. The tool takes in source files as input and provides outputs such as symbol extracts, call graphs, and search results, making it ideal for use cases like code discovery, dependency analysis, and refactoring.

Canonical page: https://skillsregistry.net/skills/cavenine-ctxpp  
JSON: https://api.skillsregistry.net/v1/skills/cavenine-ctxpp

## Description

A codebase intelligence MCP server that parses source files across 13+ languages using tree-sitter parsers to extract symbols, call graphs, and documentation. Indexes everything in SQLite with both full-text and vector search through Ollama or AWS Bedrock embeddings. Features hybrid ranking that combines BM25 scoring with call-graph connectivity analysis, enabling queries that find not just matching code but all code involved in a feature by walking real call relationships. Provides tools for indexing, semantic search, file skeletons, dependency traversal, and blast radius analysis of code changes.

## Trust

- **Trust score (0–1):** 0.75
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/cavenine-ctxpp)
- **Repository:** <https://github.com/cavenine/ctxpp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "cavenine-ctxpp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/cavenine-ctxpp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/cavenine-ctxpp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt
