Skip to main content
Glama
miriyaladhanwinn

AgentSkillMesh

by miriyaladhanwinn
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

🕸️ AgentSkillMesh

High-Performance Model Context Protocol (MCP) Tool Suite & Skill Runtime

Optimized for OpenAI Codex, ChatGPT Pro Workspace Agents, and Autonomous Coding Harnesses

License Node.js MCP

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: vibecheck

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.

Quick Start

# Clone and build
git clone https://github.com/MRLDHANWINN/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.js

MCP 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 @MRLDHANWINN.

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • AgentShield

    elliotllliu
    A
    license
    Not graded
    quality
    C
    maintenance
    Full-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.
    421 npm
    15
    MIT

  • vibecheck

    ArisRhiannon
    A
    license
    A
    quality
    D
    maintenance
    Agent-native "safe to ship?" security gate for AI-generated code. Uses real parsers and inter-rocedural taint analysis (JS/TS, Python, Go) to flag the classes AI coding agents get wrong — secrets, SQL injection, SS, SSRF, path traversal, command injection, weak JWT/CORS — and ranks findings by confidence. Exposes a scan tool over MCP.
    1
    6 npm
    2
    MIT

  • llmsecurity-mcp

    afterdarksys
    A
    license
    B
    quality
    C
    maintenance
    Provides local, dependency-free security scanning tools for LLM configurations, prompts, RAG sources, and more, enabling AI coding agents to detect prompt injections and other vulnerabilities without external network access.
    8
    MIT