Skip to main content
Glama
RaheesAhmed

code-context-mcp

Code Context MCP Server

License: MIT Python 3.10+

Make any LLM a codebase expert instantly. This MCP server provides deep code intelligence through semantic search, architecture mapping, security analysis, and smart context that fits perfectly in token windows. 90% more efficient than sending raw files. Perfect for Claude, GPT, and any LLM-powered IDE.

Installation

git clone https://github.com/RaheesAhmed/code-context-mcp.git
cd code-context-mcp
uv sync

Related MCP server: Portable MCP Toolkit

Usage

# Development mode with inspector
uv run mcp dev src/server.py

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "code-context": {
      "command": "uv",
      "args": ["run", "--directory", "/path/to/code-context-mcp", "mcp", "run", "src/server.py"]
    }
  }
}

Tools (16 Total)

Core Tools

Tool

Description

get_repo_map

Condensed map of all symbols in entire codebase

get_file_context

File content with related imports

search_symbols

Find function/class definitions

get_dependencies

Import relationships for a file

get_project_stats

File count, lines, language breakdown

read_file

Read file with optional line range

Tool

Description

find_usages

Find ALL places where a symbol is used

smart_context

Auto-find relevant files for a question

semantic_search

Search code by meaning, not keywords

Deep Analysis

Tool

Description

get_call_graph

Trace callers/callees with Mermaid diagram

get_architecture

Auto-generate project layer diagram

analyze_patterns

Detect security, performance, quality issues

Optimization

Tool

Description

get_compressed_context

Token-efficient multi-file context

analyze_change_impact

What breaks when you change a file

get_recent_changes

Git history - recently modified files

trace_code_flow

Step-by-step execution path tracing

Examples

# See entire codebase structure
get_repo_map(project_path="/path/to/project")

# Find all usages of a function
find_usages(project_path="/path/to/project", symbol="authenticate")

# Auto-find relevant code for a question
smart_context(project_path="/path/to/project", question="how does auth work?")

# Build call graph with visualization
get_call_graph(project_path="/path/to/project", function_name="main")

# Analyze before making changes
analyze_change_impact(project_path="/path/to/project", file_path="src/core.py")

# Trace execution flow
trace_code_flow(project_path="/path/to/project", entry_point="handleRequest")

Requirements

  • Python 3.10+

  • uv

License

MIT License - see LICENSE

Author

Rahees Ahmed

A
license - permissive license
-
quality - not tested
D
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/RaheesAhmed/code-context-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server