Code AnalysisSAFE
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A Model Context Protocol (MCP) server that enables AI models to understand and analyze codebases through natural language conversations.
✨ Highlights
- Natural Code Exploration: Ask high-level questions about your codebase
"What are all the different payment providers integrated in the system?"
- Deep Code Understanding: Extract insights about data models and system architecture
"How does the user authentication flow work from frontend to database?"
- Dynamic Analysis: Trace data flows and understand system relationships
"Show me all the places where we calculate transaction fees"
Limitations
This tool is a simpler alternative to more sophisticated code analysis tools / copilot like Aider. While it lacks the advanced code analysis capabilities and robustness of tools like Aider, it offers a lightweight solution for codebase exploration if you already have a Claude Pro subscription. The main advantages are:
- Cost-Effective: Using your existing Claude Pro subscription means no additional API costs, unlike tools that can get expensive when analyzing large codebases
- Simple Setup: Quick to get started with minimal configuration
- Basic Analysis: Good for high-level code understanding and exploration
Note that due to its simpler approach to code analysis, it may make more errors or provide less detailed insights compared to more specialized tools.
🚀 Quick Start
- Install the server:
git clone https://github.com/saiprashanths/code-analysis-mcp.git cd code-analysis-mcp
- Install Claude Desktop App. For more instructions on setting up an MCP Server with Claude Desktop app, see docs
- Configure the server in Claude Desktop's configuration file:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows: `%APPDATA%\Cla
6851215e41dbOBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add code-analysis-mcp -- uvx code-analysis-mcp
{
"mcpServers": {
"code-analysis-mcp": {
"command": "uvx",
"args": [
"code-analysis-mcp"
]
}
}
}Exposed tools (4)
4 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
get_repo_info | read | Get information about the currently initialized code repository. |
get_repo_structure | read | Get the structure of files and directories in the repository. |
initialize_repository | read | Initialize the repository path for future code analysis operations. |
read_file | read | Read and display the contents of a file from the repository. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (1)
Gates applied: no_behavioural_pass, no_license.
6851215e41dbfull audit observations/trust-audit/mcp-server/saiprashanths__code-analysis-1.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 6851215e41db | SAFE | B | 89 | first audit |
Questions
What tools does Code Analysis expose?
4 in total: 4 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Code Analysis safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Code Analysis need?
No credential environment variables were found in its source, so it appears to need none.
How does Code Analysis run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as code-analysis-mcp.
How current is this page?
The grade is for one exact copy of the source (6851215e41db), read on 2026-10-08. The repository is watched and re-audited when it changes.