AgentSkillMesh
Enables OpenAI Codex and ChatGPT Pro agents to use MCP tools for static security scanning, AST symbol search, and safe execution contexts when working with code repositories.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
AgentSkillMesh
High-Performance Model Context Protocol (MCP) Tool Suite & Skill Runtime
Optimized for OpenAI Codex, ChatGPT Pro Workspace Agents, and Autonomous Coding Harnesses
Overview
AgentSkillMesh provides foundational tools for AI coding agents communicating via the Model Context Protocol (MCP). It equips OpenAI Codex, ChatGPT Pro, and coding harnesses with fast security static analysis, AST symbol indexing, and safe execution contexts.
Related MCP server: scanpay-mcp
Key Capabilities
Static Security Rule Engine: Instant linting for dynamic eval, secret leaks, and insecure regexes.
AST Symbol Grep: Sub-millisecond symbol search across large repositories without embedding overhead.
Zero External Bloat: Zero-dependency, pure ESM architecture designed for high-concurrency agent workflows.
Tools Exposed
AgentSkillMesh exposes two MCP tools that any MCP-compatible agent (OpenAI Codex, Claude, etc.) can call:
Tool | What it does |
| Scans source code for security hazards: dynamic |
| Fast AST-based symbol search across code — find definitions and references without embedding overhead. |
Demo
$ node dist/cli.js scan ./vuln_demo.js
Scan completed for ./vuln_demo.js. Findings: 2
- [CRITICAL] Line 1: High-entropy secret token literal detected. (SEC-003)
- [CRITICAL] Line 3: Dangerous dynamic code evaluation construct detected. (SEC-001)Quick Start
# Clone and build
git clone https://github.com/miriyaladhanwinn/agent-skill-mesh.git
cd agent-skill-mesh
npm install
npm run build
# Start MCP stdio server
node dist/cli.js serve
# Scan a source file
node dist/cli.js scan ./path/to/file.jsMCP Configuration
{
"mcpServers": {
"agent-mesh": {
"command": "node",
"args": ["/path/to/agent-skill-mesh/dist/cli.js", "serve"]
}
}
}License
Licensed under the Apache License, Version 2.0. Maintained by @miriyaladhanwinn.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Code intelligence for coding agents: semantic, AST, graph, and full-text search. 279+ languages.
Code intelligence platform for AI agents. 20 tools for architecture, security & impact analysis.
Zero-install security baseline for AI coding agents — OWASP/CWE-cited rules over MCP.
Pay-per-call cybersecurity for AI agents: vuln scans, threat intel, compliance, code security.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceFull-stack security for AI agents — static analysis + MCP runtime interception. 31 rules detect prompt injection, data exfiltration, backdoors, tool poisoning, and cross-file attack chains. Includes MCP proxy for real-time blocking, Python AST taint tracking, multi-language injection detection (8 languages), and AI-powered deep analysis. Free, offline, zero-config.49 npm17MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to scan code for security vulnerabilities before execution, supporting Python and JavaScript/TypeScript with deterministic AST-based analysis and optional Solana micropayments.4 npmMIT
- FlicenseBqualityCmaintenanceEnables AI agents to perform comprehensive, zero-infrastructure codebase analysis through 24 MCP tools, covering security, quality, architecture, type safety, git history, and dead code detection with high precision and local privacy.45-
- FlicenseNot gradedqualityBmaintenanceEnables AI agents and IDE assistants to run zero-config security audits, detect secrets and vulnerable dependencies, and apply adversarial verification to reduce false positives.2-