How do I install Diogenes Agent Guardrails & Sandbox MCP?

Copy the http config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.

Does Diogenes Agent Guardrails & Sandbox MCP need an API key?

No required environment variable is listed on this record.

What transport does Diogenes Agent Guardrails & Sandbox MCP use?

Diogenes Agent Guardrails & Sandbox MCP is reached over HTTP.

When was Diogenes Agent Guardrails & Sandbox MCP last checked?

Last checked 2026-10-27. Autonomous agent guardrails, bash sandboxing, MCP rugpull diffing & prompt firewalls.

Diogenes Agent Guardrails & Sandbox MCP server

Power your agent

Add this server

The publisher's own URL. Not a PlugMCP endpoint.

Add to Cursor Add in Claude Add to VS Code Run on PlugMCP

Host a copy with our keys and logs.

Server URL

https://diogenes-micro-gateway.corinth.workers.dev/mcp/agent-guardrails

The Claude button above opens Claude with the name and URL filled in. You still confirm it there.

shClaude Code

1claude mcp add --transport http io.github.stand-out-of-my-sun-diogenes-agent-guardrails-mcp https://diogenes-micro-gateway.corinth.workers.dev/mcp/agent-guardrails

Run in a terminal.

jsonClaude Desktop

1{2  "mcpServers": {3    "io.github.stand-out-of-my-sun-diogenes-agent-guardrails-mcp": {4      "command": "npx",5      "args": [6        "-y",7        "mcp-remote",8        "https://diogenes-micro-gateway.corinth.workers.dev/mcp/agent-guardrails"9      ]10    }11  }12}

claude_desktop_config.json

Remote · HTTPPublisher installStep-by-step: add this in Claude

Remote URL or a command on your machine? How the two installs differ

Run on PlugMCP

Host a copy with our keys and logs.

A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.

Launch

Server facts

Remote

Transport: http
Version: 1.0.0

Tools

No tool list yet. Remote servers get one after the first health check.

FAQ

Questions

Diogenes Agent Guardrails & Command Sandbox MCP (`diogenes-agent-guardrails-mcp`)

Diogenes Agent Guardrails & Command Sandbox MCP is a focused, zero-bloat Model Context Protocol (streamable-http) package powered by the Diogenes Microservice Gateway.

Instead of loading all 121 gateway endpoints into your LLM's context window, installing this package exposes only the 12 specialized agent-guardrails tools needed for Security:

12 pre-execution and post-execution AI agent security tools: command injection gate, AST SQL validator, Python sandbox, MCP manifest & rug-pull auditors, sampling firewall, output scrubber, PII redactor, loop breaker, A2A card verifier, egress SSRF guard, and factuality auditor.

⚡ 1-Click Install for Cursor & Claude Desktop

No API keys, user accounts, or local dependencies required. Zero setup — paste directly into your client config:

🖱️ Cursor IDE (`.cursor/mcp.json`)

Add to .cursor/mcp.json in your project root or global Cursor settings:

{
  "mcpServers": {
    "diogenes-agent-guardrails": {
      "transport": "streamable-http",
      "url": "https://diogenes-micro-gateway.corinth.workers.dev/mcp/agent-guardrails"
    }
  }
}

🧠 Claude Desktop (`claude_desktop_config.json`)

Add to claude_desktop_config.json (Mac: ~/Library/Application Support/Claude/claude_desktop_config.json | Windows: %APPDATA%\Claude\claude_desktop_config.json):

{
  "mcpServers": {
    "diogenes-agent-guardrails": {
      "transport": "streamable-http",
      "url": "https://diogenes-micro-gateway.corinth.workers.dev/mcp/agent-guardrails"
    }
  }
}

Prefer local stdio? Run via npx:
npx -y @stand-out-of-my-sun/diogenes-agent-guardrails-mcp

Included Tools in `agent-guardrails` (12 Tools)

MCP Tool Name	Underlying REST Route	Settlement	Capability
`verify_agent_command_safety`	`POST /api/v1/agent/guardrail-verify`	100 sats (L402)	Evaluates untrusted agent prompts, bash commands, and tool arguments to block prompt injection, destructive shell commands, and private-key exfiltration. Use when screening a general shell command or user prompt before agent execution; for statically validating SQL database queries at the AST level, use validate_sql_query_ast instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'payload' ('action_type' defaults to 'bash_command'), supports '?demo=true' or L402 (100 sats), and returns HTTP 400 if invalid.
`validate_sql_query_ast`	`POST /api/v1/agent/sql-guard`	75 sats (L402)	Performs static AST syntax tree parsing on SQL statements to verify strictly read-only SELECT clauses and reject mutations, stacked queries, or comment bypasses. Use when verifying that an agent-authored SQL statement is strictly read-only before running it on a database; for screening non-SQL bash commands or general agent prompts, use verify_agent_command_safety instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'sql_statement' ('dialect' defaults to 'postgres'), supports '?demo=true' or L402 (75 sats), and returns HTTP 400 if invalid.
`execute_python_sandbox`	`POST /api/v1/mpp/code-sandbox`	1500 sats (MPP)	Audits Python source code for forbidden syscalls (os, subprocess, socket, open, eval) inside an AST-governed WebAssembly sandbox with no host filesystem access. Use when executing LLM-generated Python snippets safely; for checking shell commands without executing code, use verify_agent_command_safety instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'python_script' ('timeout_profile' defaults to 'fast_1s'), supports '?demo=true' or MPP (1500 sats), and returns HTTP 400 if invalid.
`audit_mcp_server_manifest`	`POST /api/v1/agent/mcp-manifest-auditor`	150 sats (L402)	Scans an external MCP server's initial tools/list manifest to detect tool-name shadowing (read_file, bash) and hidden prompt-injection directives in descriptions. Use when vetting a newly discovered third-party MCP server before mounting it into an agent session; for comparing a previously pinned MCP baseline against a live mid-session tools/list response, use detect_mcp_schema_rugpull instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'manifest_json' ('audit_profile' defaults to 'strict'), supports '?demo=true' or L402 (150 sats), and returns HTTP 400 if invalid.

Free Account-Less Demo Mode: Append ?demo=true to any REST endpoint above for an instant HTTP 200 schema preview at zero cost.

Other Modular Diogenes MCP Packages

Install only the domain packages relevant to your workflow:

Package	Scoped MCP Endpoint	Spoke Repository
1. EVE: Frontier Sui Move Suite (14 Tools)	`https://diogenes-micro-gateway.corinth.workers.dev/mcp/eve-frontier`	`stand-out-of-my-sun/diogenes-eve-frontier-mcp`
2. Agent Guardrails & Sandbox (12 Tools)	`https://diogenes-micro-gateway.corinth.workers.dev/mcp/agent-guardrails`	`stand-out-of-my-sun/diogenes-agent-guardrails-mcp`
3. Web3, DeFi & 402 Security (15 Tools)	`https://diogenes-micro-gateway.corinth.workers.dev/mcp/web3-security`	`stand-out-of-my-sun/diogenes-web3-security-mcp`
4. Gemini Suite & AI Agents (15 Tools)	`https://diogenes-micro-gateway.corinth.workers.dev/mcp/gemini-suite`	`stand-out-of-my-sun/diogenes-gemini-suite-mcp`
5. Context, Code & Solvers (15 Tools)	`https://diogenes-micro-gateway.corinth.workers.dev/mcp/context-code-solver`	`stand-out-of-my-sun/diogenes-context-code-solver-mcp`
6. Dev, Data & Workflow Utilities (14 Tools)	`https://diogenes-micro-gateway.corinth.workers.dev/mcp/dev-utilities`	`stand-out-of-my-sun/diogenes-dev-utilities-mcp`

TensorBlock & MCP Index Profile Metadata

Field	Value
Category	`Security`
Transport	`streamable-http`
Endpoint	`https://diogenes-micro-gateway.corinth.workers.dev/mcp/agent-guardrails`
Manifest	`https://diogenes-micro-gateway.corinth.workers.dev/.well-known/mcp/agent-guardrails.json`
Health Check	`https://diogenes-micro-gateway.corinth.workers.dev/api/v1/health`
Auth	`none` (100% account-less free tier, MCP discovery & `?demo=true` previews; optional 6 flexible crypto payment rails for production calls: L402, x402, Base MPP, Garlicoin 0-Conf, BSC WGRLC, or Prepaid GRLC session API keys)
Install Confidence	`high` (Zero-install remote Streamable HTTP endpoint + root `package.json`, `smithery.yaml`, `server.json`, `glama.json`, and `mcp.json`)
License	`MIT`
Verification	`verified` (`@stand-out-of-my-sun` verified via `https://diogenes-micro-gateway.corinth.workers.dev/.well-known/tensorblock.json` & `https://diogenes-micro-gateway.corinth.workers.dev/.well-known/mcp/agent-guardrails.json`)
Maintainer	`@stand-out-of-my-sun`
Docs	`https://diogenes-micro-gateway.corinth.workers.dev/llms.txt`
Support

Add this server

Host a copy with our keys and logs.

Server facts

Tools

Questions

How do I install Diogenes Agent Guardrails & Sandbox MCP?

Does Diogenes Agent Guardrails & Sandbox MCP need an API key?

What transport does Diogenes Agent Guardrails & Sandbox MCP use?

When was Diogenes Agent Guardrails & Sandbox MCP last checked?

Documentation

Diogenes Agent Guardrails & Command Sandbox MCP (diogenes-agent-guardrails-mcp)

⚡ 1-Click Install for Cursor & Claude Desktop

🖱️ Cursor IDE (.cursor/mcp.json)

🧠 Claude Desktop (claude_desktop_config.json)

Included Tools in agent-guardrails (12 Tools)

Other Modular Diogenes MCP Packages

TensorBlock & MCP Index Profile Metadata

Diogenes Agent Guardrails & Command Sandbox MCP (`diogenes-agent-guardrails-mcp`)

🖱️ Cursor IDE (`.cursor/mcp.json`)

🧠 Claude Desktop (`claude_desktop_config.json`)

Included Tools in `agent-guardrails` (12 Tools)