cctx-mcp 0.1.0

MCP server for AI agents — structured code analysis that cuts token usage by 87%

Cut AI agent token usage by 87%.
Structure-aware code analysis via the Model Context Protocol — returns symbol trees, dependencies, and docs instead of raw file contents.

---

Overview

CCTX-MCP — Code ConTeXt via Model Context Protocol. An MCP server that gives AI agents a structured view of source code without reading entire files.

Built for Claude, Cursor, OpenCode, and any MCP-compatible AI coding tool.

uvx cctx-mcp  ·  Tools  ·  Savings  ·  Install

---

Quick Start

uvx cctx-mcp

Add to your MCP client config:

{
  "mcpServers": {
    "cctx-mcp": {
      "command": "uvx",
      "args": ["cctx-mcp"]
    }
  }
}

---

Tools

Code Analysis

Tool	Returns	Replaces	Savings
smart_read	symbol hierarchy, deps, docs, line counts	cat + manual parsing	~87%
find_symbols	symbol locations by name or type	grep -r + file reads	~99%
get_dependencies	all imports of a file in one shot	grep ^import	~96%
trace_calls	every call site with file + line	grep across repo	~90%
get_symbol_summaries	AI semantic descriptions per symbol	reading implementation	~85%

Search & Navigation

Tool	Returns	Replaces	Savings
analyze_project	language breakdown, file counts, tree	find + wc	~98%
code_search	regex matches with context lines	grep + cat	~90%
semantic_search	natural language query over indexed codebase	reading everything	~96%
dir_summary	directory listing with sizes	ls -la	~80%
find_files	files matching name, extension, path	find	~80%

Git & Commits

Tool	Returns	Replaces	Savings
compact_change_intelligence	structured git diff with intent cues	git diff + git status	~75%
draft_commit	AI-generated conventional commit message	writing from scratch	~90%
approve_commit_draft	executes the commit after review	git add + git commit	—

Observability

get_config · get_health · get_metrics_report · get_metrics_events · get_metrics_daily_trend · get_metrics_slowest · get_version

---

Token Savings

Operation	Native	With CCTX-MCP	Savings
Read 500-line file	~1,500 tokens	~200 tokens	87%
Find function across project	~5,000 tokens	~50 tokens	99%
Understand imports	~800 tokens	~30 tokens	96%
Semantic query across codebase	~8,000 tokens	~300 tokens	96%
Analyze project structure	~10,000 tokens	~150 tokens	98%
Git change summary	~3,000 tokens	~750 tokens	75%

Typical session: 80%+ aggregate savings.

---

Supported Languages

Powered by tree-sitter AST — each language has a dedicated parser.

---

Install

uvx (recommended)

{
  "mcpServers": {
    "cctx-mcp": {
      "command": "uvx",
      "args": ["cctx-mcp"]
    }
  }
}

pip

pip install cctx-mcp

{
  "mcpServers": {
    "cctx-mcp": {
      "command": "python",
      "args": ["-m", "code_context.server"]
    }
  }
}

source

git clone https://github.com/nikondrat/cctx-mcp.git
cd cctx-mcp
uv sync
uv run python -m code_context.server --skip-index

---

Configuration

Variable	Default	Description
CC_OLLAMA_URL	http://localhost:11434	Ollama server address
CC_OPENROUTER_API_KEY	—	Remote inference key
CC_LLM_ROUTER	local-first	local-first, local-only, remote-first, remote-only
CC_COMMIT_MODEL	gemma4:latest	Local model for commit drafting
CC_EMBED_MODEL	nomic-embed-text	Local model for embeddings
CC_SEMANTIC_SUMMARIES	1	Enable AI symbol summaries

---

Development

uv sync
uv run pytest tests/ -v

PRs welcome. Open issues.

---

License

MIT — free for any use.