What distinguishes Project Scope from naive pattern-based scanners?
Project Scope uses context-sensitive scanning that parses source code rather than pattern-matching, eliminating false positives on legitimate code.
Project Scope MCP Server
@adityasasidhar
Basic information
About Project Scope MCP Server
A production-ready MCP server that gives AI agents deep codebase understanding. Features AST-based semantic analysis, context-aware security scanning (zero false positives on source code), safe refactoring tools with previews, and comprehensive Git operations.
Project Scope MCP Server config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"project-scope": {
"command": "npx",
"args": [
"-y",
"@adityasasidhar/project-scope-mcp"
]
}
}
}Project Scope MCP Server tools
Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
Overview
What is Project Scope?
Project Scope is a production-grade MCP server for semantic code intelligence and safe repository control. It gives AI agents deep, structural understanding of codebases and the ability to modify them safely through AST analysis, context-aware security scanning, refactoring tools, and Git operations.
How to use Project Scope?
To use Project Scope, configure your AI agent’s MCP client to connect to this server. You can then invoke its tools, such as get_repo_structure for repository analysis, scan_repo_for_threats for security scanning, refactor_rename for refactoring, and git_status for Git operations.
Key features of Project Scope
- Semantic repository analysis using Tree-sitter AST parsing
- Context-aware security scanning with zero false positives
- Safe refactoring tools with mandatory preview before apply
- Git-native operations for status, history, and comparison
- Defense-in-depth security with prompt injection detection
- Fully local execution with no external dependencies
Use cases of Project Scope
- Large codebase understanding for AI agents
- Safe autonomous refactoring with syntax guarantees
- Secure agent-driven code changes with context scanning
- Repository audits and change impact analysis
- AI-assisted code reviews with semantic understanding
Frequently asked questions
Does Project Scope run locally?
Yes, Project Scope is fully local execution, built with TypeScript, Node.js, and Tree-sitter.
What security measures does Project Scope include?
It includes prompt injection detection, regex and heuristic guards, optional integration with Meta Llama Prompt Guard 2, and file access and execution boundaries.
Can Project Scope perform refactoring safely?
Yes, it enforces mandatory preview before applying refactors and uses AST analysis to guarantee syntax correctness.
What Git operations are supported?
Project Scope supports repository status, commit history, branch comparison, and initialization.
More Developer Tools MCP servers
offprompt
offpromptMCP server that lets Claude Code, Cursor or Codex ask you for API keys on a local page and write them to .env. The agent only ever sees key names.
2
CircleCI MCP Server
CircleCIManage CI/CD pipelines, debug failed builds, and optimize test suites directly from your AI agents - no terminal required. The CircleCI MCP Server is a remote server hosted by CircleCI that connects AI tools and agents
Vibgrate MCP
VibgrateQuery your team's drift, vulnerability, and migration data from any AI assistant. Vibgrate MCP connects Cursor, Claude, ChatGPT, Windsurf, or VS Code to Vibgrate Cloud: 51 tools for DriftScores, CVEs and EOL runtimes, up
3
Meticulous
Meticulous
Reelier
Maxime HouleAgents make claims. Reelier writes receipts — record an agent's tool-call workflow once, replay it deterministically at 0 tokens, and diff runs to catch drift.
Comments