Skip to main content
Glama
project-advisors-mcp
by ragubaran

Project Advisors MCP Server

An MCP (Model Context Protocol) server providing diagnostic tools to analyze software architecture, security, REST API compliance, and dependencies.

Supports: Python, Rust, Go, Node.js, Java, Swift (iOS), and Kotlin (Android).

Inspiration: The design and concept of these diagnostic advisors were heavily inspired by the BootUI platform.

Setup

npm install
npm run build

Related MCP server: arch-optimize

Running the Server

The server runs via stdio:

npm start

Available Tools

  • run_architecture_scan

  • run_rest_api_scan

  • run_security_scan

  • run_vulnerability_scan

  • run_pentest_scan

  • get_telemetry_stream

  • run_mcp_design_scan

Using the Agent Skill

This project includes a custom AI Agent Skill located at .agents/skills/project-advisor/SKILL.md. Agents like Antigravity will automatically use it when you ask them to "audit codebase" or "give project health score".

How to use this MCP Server

To use this library with your AI Coding Assistant, you need to configure the assistant to spawn this server via its stdio transport mechanism.

1. Claude Desktop Configuration

Add the following to your Claude Desktop config file (e.g. ~/Library/Application Support/Claude/claude_desktop_config.json on Mac):

{
  "mcpServers": {
    "project-advisors": {
      "command": "node",
      "args": ["/Users/ragu/Code/project-advisors/dist/index.js"]
    }
  }
}

Note: Make sure to run npm run build first so the dist/index.js file exists, and update the absolute path to point to your repository.

2. Cursor IDE Configuration

  1. Open Cursor Settings -> Features -> MCP.

  2. Click + Add new MCP server.

  3. Set the Name to project-advisors.

  4. Set the Type to command.

  5. Set the Command to node /absolute/path/to/project-advisors/dist/index.js.

  6. Click Save.

3. Example AI Prompts

Once connected, you can ask your AI Agent to run audits on your current workspace:

  • "Run an architecture scan on this project and tell me if there are any boundary violations."

  • "Check my REST APIs for compliance and security issues."

  • "Give me an overall health score for this project using the project advisor tools."

Available Tools

7 tools
get_telemetry_streamA

Retrieves live runtime activity (memory usage, unhandled exceptions, slow queries, leak traces) received from JVM or mobile sidecar streams.

Inputs: limit, severity.

run_architecture_scanB

Scans workspace source files for layer boundary violations, circular dependencies, and improper coupling. Supports Python, Rust, Go, Node.js, Java, Swift (iOS), and Kotlin (Android).

Inputs: pattern, projectRoot.

run_mcp_design_scanA

Verifies the design and implementation of MCP (Model Context Protocol) servers. Checks for proper tool definitions, schema validation, transport security, and proper error handling.

Inputs: strictMode, projectRoot.

run_pentest_scanA

Generates non-destructive exploit payloads (SQLi, XSS, JWT tampering) against configured dev environment endpoints to test input sanitization.

Inputs: targetUrl (required), payloadTypes.

run_rest_api_scanB

Evaluates REST endpoints/controllers for HTTP compliance, missing pagination, state-mutating GETs, raw stack traces, and unvalidated payloads.

Inputs: strictMode, includeRoutes.

run_security_scanB

Audits security configurations, hardcoded secrets/API keys, exposed management endpoints, missing CSRF tokens, and insecure permissions.

Inputs: scanConfig, scanSecrets.

run_vulnerability_scanB

Checks build dependency files (package.json, pom.xml, build.gradle, Cargo.toml, requirements.txt, etc.) against known CVE databases.

Inputs: manifestPath.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.6/5.0

    Scored across 7 tools

    Disambiguation4/5

    Each tool targets a distinct concern (dependencies, endpoints, runtime telemetry, MCP design, architecture, REST APIs, security config), but some overlap exists between security scan, vulnerability scan, and pentest scan. Descriptions clarify boundaries, so misselection is unlikely but possible.

    Naming Consistency4/5

    Six of seven tools follow the 'run_*_scan' pattern, which is predictable and consistent. The outlier 'get_telemetry_stream' uses a different verb and noun style, creating a minor deviation but not causing confusion.

    Tool Count5/5

    Seven tools is well within the ideal range for a specialized scanning server. Each tool covers a distinct aspect of project advisory, and the count feels neither sparse nor bloated.

    Completeness4/5

    The tool surface covers the main advisory domains: dependencies, security config, architecture, REST APIs, and runtime telemetry. Minor gaps like container scanning or infrastructure checks exist, but the core workflows are well covered.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      B
      quality
      D
      maintenance
      An MCP server that integrates SAST, DAST, and SCA security tools to enable AI-driven vulnerability scanning and automated security reporting. It allows AI assistants to execute and analyze results from tools like Semgrep, OWASP ZAP, and Trivy within a DevSecOps workflow.
      6
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      MCP server that provides tools for architecture analysis, risk diagnosis, quality metrics, and regression guarding to support AI-driven code review and incremental refactoring workflows.
      5
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      MCP server that provides audit and safety-check tools for enterprise SDLC code integrity, enabling AI agents to scan workspaces for lifecycle gaps, mock-theater tests, DRY violations, and language-specific issues in shell, JavaScript/HTML, and Python.
      4
      14 npm
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      MCP server that enables AI coding assistants to audit repositories against engineering rules, generating self-contained HTML reports with citations and optional GitHub issue filing.
      10
      2
      Apache 2.0