# AgentGuard MCP Server

> AgentGuard MCP Server — jahao-18-agent-guard. Use this tool when you need to secure and authorize MCP-based agents with policy-driven runtime evaluation, solving problems related to agent security and compliance. It provides inputs such as agent requests and policy definitions, and outputs authorized actions and audit logs. Ideal for use cases requiring robust security and auditing in MCP-based environments.

Canonical page: https://skillsregistry.net/skills/jahao-18-agent-guard  
JSON: https://api.skillsregistry.net/v1/skills/jahao-18-agent-guard

## Description

Provides policy-driven runtime authorization and security evaluation for MCP-based agents, including MCP streaming HTTP gateway, mock MCP servers, deterministic agent demos, and audited tool invocation with redacted PostgreSQL audit chains.

## Trust

- **Trust score (0–1):** 0.36
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/fpamo4h7m3)
- **Repository:** <https://github.com/jahao-18/Agent_Guard>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "jahao-18-agent-guard"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/jahao-18-agent-guard` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/jahao-18-agent-guard/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt