code-context MCP server
Commit Oct 25, 2026Provides AST-based codebase intelligence, symbol extraction, and cyclomatic complexity analysis to improve AI coding agent context efficiency.
Also known as jitendrakumar-ai/code-context-mcp
- Stars
- 1
- Tools
- 5
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Oct 25, 2026
- License
- MIT
What is code-context MCP?
code-context provides AST-based codebase intelligence, symbol extraction, and cyclomatic complexity analysis to improve AI coding agent context efficiency. It exposes 5 tools, such as summarize_repository_architecture, extract_python_ast_symbols, analyze_cyclomatic_complexity.
Summary generated from the project's README
About code-context MCP server
Providing surgical code context to AI coding agents is what this server enables by replacing raw file dumping with structured intelligence. It helps developers using tools like Claude Code, Cursor, Windsurf, or Codex to reduce token usage by extracting only the necessary structural information from Python codebases. Instead of sending entire files, the server provides an Abstract Syntax Tree representation to keep context windows efficient.
Users run this server locally via stdio, meaning it works entirely offline with no external API keys or telemetry required. It functions through a three-layer workflow that starts with a high-level repository summary and moves into detailed symbol extraction and complexity analysis. By using specific tools like extract_python_ast_symbols and analyze_cyclomatic_complexity, an AI agent can understand class definitions, method signatures, and refactoring needs without consuming excessive tokens.
What you can do with it
- 1Map repository structureAsk the AI to provide a high-level overview of the file tree and module entry points.
- 2Extract specific code symbolsRequest a detailed outline of classes, methods, and docstrings for a specific Python file.
- 3Identify refactoring targetsFind functions that have high cyclomatic complexity and need to be modularized.
Written from the project's README. Every use case is checked against a quote from it.
code-context MCP tools 5
Detected from the READMEsummarize_repository_architectureextract_python_ast_symbolsanalyze_cyclomatic_complexityget_refactoring_contextsearch_code_todos_and_hotspots
| summarize_repository_architecture | — | |
| extract_python_ast_symbols | — | |
| analyze_cyclomatic_complexity | — | |
| get_refactoring_context | — | |
| search_code_todos_and_hotspots | — |
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablejitendrakumar-ai/code-context-mcp is public and reachablegithub.com/jitendrakumar-ai/code-context-mcp ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-10-25github.com/jitendrakumar-ai/code-context-mcp ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model5 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHub<
AST Codebase Intelligence, Symbol Extraction, Cyclomatic Complexity & Refactoring Analysis for LLMs & AI Coding Agents.
💡 Why This Exists & Token Efficiency
Traditional AI coding assistants dump entire raw source files into context windows, wasting tens of thousands of tokens on boilerplate, imports, and irrelevant functions. code-context-mcp introduces a claude-mem style 3-layer workflow that provides surgical code context before editing.
🚀 Quick Start
Multi-IDE Quick Start
Claude Code
Add to your ~/.claude.json:
{
"mcpServers": {
"code-context-mcp": {
"command": "python3",
"args": ["/path/to/code_context_mcp.py"]
}
}
}
Cursor
Go to Settings > Features > MCP and add:
- Name:
code-context-mcp - Type:
stdio - Command:
python3 /path/to/code_context_mcp.py
Codex
Add to codex.config.toml:
[mcp.servers.code-context-mcp]
command = "python3"
args = ["/path/to/code_context_mcp.py"]
Antigravity
Add to .antigravity/mcp_config.json:
{
"mcpServers": {
"code-context-mcp": {
"command": "python3",
"args": ["/path/to/code_context_mcp.py"]
}
}
}
OpenCode
Add to opencode.json:
{
"mcpServers": {
"code-context-mcp": {
"command": "python3",
"args": ["/path/to/code_context_mcp.py"]
}
}
}
Windsurf
Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"code-context-mcp": {
"command": "python3",
"args": ["/path/to/code_context_mcp.py"]
}
}
}
🛠️ How It Works
code-context-mcp runs as a standard Model Context Protocol (MCP) server communicating over stdio. It builds an Abstract Syntax Tree (AST) representation of Python source code locally and computes function metrics without sending data externally.
🧬 3-Layer Workflow
Layer 1: Repository Architecture Summary
# Call tool: summarize_repository_architecture
response = summarize_repository_architecture(root_dir=".")
print(response)
# Returns file tree, line counts, extension distribution, and module entry points.
Layer 2: AST Symbol Outline
# Call tool: extract_python_ast_symbols
response = extract_python_ast_symbols(file_path="code_context_mcp.py")
print(response)
# Returns class definitions, method signatures, decorator usages, and docstrings.
Layer 3: Cyclomatic Complexity & Refactoring Insights
# Call tool: analyze_cyclomatic_complexity
response = analyze_cyclomatic_complexity(file_path="code_context_mcp.py", threshold=10)
print(response)
# Identifies high-complexity methods and recommends specific modular refactorings.
🔧 MCP Tools
| Tool | Parameters | Description |
|---|---|---|
summarize_repository_architecture |
root_dir (str) |
High-level repository structure & file metrics. |
extract_python_ast_symbols |
file_path (str) |
AST symbol tree (Classes, Functions, Imports). |
analyze_cyclomatic_complexity |
file_path (str), threshold (int) |
Complexity metrics & actionable refactoring prompts. |
get_refactoring_context |
file_path (str), symbol_name (str) |
Targeted code extraction for surgical AI code edits. |
🏗️ Architecture
+-------------------------------------------------------+
| AI Coding Agent |
| (Claude Code / Cursor / Codex / Antigravity / etc.) |
+---------------------------+---------------------------+
| MCP (stdio)
v
+-------------------------------------------------------+
| code-context-mcp |
| |
| +--------------------+ +--------------------+ |
| | AST Parser Engine | | Cyclomatic Engine | |
| +--------------------+ +--------------------+ |
| | Symbol Extractor | | Refactor Context | |
| +--------------------+ +--------------------+ |
+-------------------------------------------------------+
🛡️ Security
code-context-mcp works 100% offline and locally. Zero telemetry, zero external API requests. See SECURITY.md for vulnerability disclosure policy.
📄 License
Distributed under the MIT License. See LICENSE for more details.--26-7928CA?style=for-the-badge" alt="MCP Spec" />
AST Codebase Intelligence, Symbol Extraction, Cyclomatic Complexity & Refactoring Analysis for LLMs & AI Coding Agents.
💡 Why This Exists & Token Efficiency
Traditional AI coding assistants dump entire raw source files into context windows, wasting tens of thousands of tokens on boilerplate, imports, and irrelevant functions. code-context-mcp introduces a claude-mem style 3-layer workflow that provides surgical code context before editing.
⚡ 3-Layer Context Workflow
- Layer 1: Structural Scan (
summarize_repository_architecture) — High-level file structure, line counts, and extensions map. - Layer 2: AST Symbol Outline (
extract_python_ast_symbols) — Class definitions, method signatures, docstrings, and line ranges without dumping raw code. - Layer 3: Targeted Analysis (
analyze_cyclomatic_complexity&search_code_todos_and_hotspots) — Cyclomatic complexity scores and TODO/FIXME hotspot discovery to pinpoint refactoring targets.
📊 Token Savings Comparison
| Approach | Context Injected | Token Usage | Accuracy | Savings |
|---|---|---|---|---|
| Naive Raw File Dumping | Entire source files | ~45,000 tokens | Moderate | 0% |
| Naive Grep Search | Raw line matches | ~18,000 tokens | Low | ~60% |
code-context-mcp AST Workflow |
Exact AST symbols & complexity | ~6,500 tokens | High | ~85% Savings 🚀 |
🏗️ Architecture Diagram
flowchart TD
A[AI Coding Agent / LLM] -->|1. Request Repo Summary| B[summarize_repository_architecture]
A -->|2. Extract AST Symbols| C[extract_python_ast_symbols]
A -->|3. Analyze Complexity| D[analyze_cyclomatic_complexity]
A -->|4. Scan Hotspots| E[search_code_todos_and_hotspots]
subgraph MCP Server Engine: code-context-mcp
B --> F[AST & Static Code Parser]
C --> F
D --> F
E --> F
end
F -->|Compact Structural Context| A
🛠️ Tools Included
summarize_repository_architecture: Scans directory paths, generates file structure breakdown by extension, and computes total lines of code.extract_python_ast_symbols: Parses Python files into Abstract Syntax Trees (AST) to extract classes, base classes, methods, docstrings, function signatures, and line markers.analyze_cyclomatic_complexity: Calculates cyclomatic complexity scores for all functions/methods to identify refactoring candidates and branch depth.search_code_todos_and_hotspots: Detects code comments containingTODO,FIXME,HACK, andXXXacross the codebase with exact file and line references.
🚀 Quick Start (1-Click & 1-Command Setup)
1. Claude Code CLI
claude mcp add code-context-mcp -- python -m code_context_mcp
2. Cursor (.cursor/mcp.json)
{
"mcpServers": {
"code-context-mcp": {
"command": "python",
"args": ["-m", "code_context_mcp"]
}
}
}
3. OpenAI Codex CLI (~/.codex/config.toml)
[mcp_servers.code-context-mcp]
command = "python"
args = ["-m", "code_context_mcp"]
4. Google Antigravity IDE (mcp_config.json)
{
"mcpServers": {
"code-context-mcp": {
"command": "python",
"args": ["-m", "code_context_mcp"]
}
}
}
5. Windsurf / Cline
{
"mcpServers": {
"code-context-mcp": {
"command": "python",
"args": ["-m", "code_context_mcp"]
}
}
}
code-context MCP questions
What tools does code-context MCP provide?
It exposes 5 tools, including summarize_repository_architecture, extract_python_ast_symbols, analyze_cyclomatic_complexity, get_refactoring_context, search_code_todos_and_hotspots.
Does this server require any API keys?
No, the server operates without the need for any external API keys.
Is my code sent to external servers?
No, the server works entirely offline and locally with zero telemetry or external API requests.
How does it improve token efficiency?
Instead of dumping entire files, it uses a 3-layer workflow to provide surgical context like AST symbols and complexity metrics, saving up to 85% in tokens.