What is the key difference between Agentward and Kastell?

Agentward belongs to the Security category with local stdio execution, while Kastell belongs to the Security category with local stdio execution.

How do I install Agentward or Kastell in Claude Desktop or Cursor?

Copy the mcpServers JSON configuration snippet provided on this page into your claude_desktop_config.json or ~/.cursor/mcp.json file and restart your AI client.

Are Agentward and Kastell free or paid?

Agentward operates under a Free / Open Source model (No auth required). Kastell operates under a Free / Open Source model (No auth required).

Which MCP server has more tools and community activity?

Agentward lists 6 tools with 2 views and 19 GitHub stars. Kastell lists 6 tools with 2 views and 56 GitHub stars.

Can I use both Agentward and Kastell together in the same MCP host?

Yes! MCP hosts like Claude Desktop, Cursor, Windsurf, Cline, and VS Code support configuring multiple servers under the mcpServers object simultaneously.

How do I install Agentward or Kastell in Claude Desktop, Cursor, or Windsurf?

Both servers follow the standard Model Context Protocol configuration format. Simply copy the JSON block from the configuration section above and paste it into your AI client's mcpServers configuration object (for instance in claude_desktop_config.json or ~/.cursor/mcp.json ), then completely restart or refresh the application.

Are Agentward and Kastell free to use, or do they require API keys?

Agentward is listed under a Free / Open Source model with No auth required . Kastell operates under a Free / Open Source model with No auth required . If environment variables are required (such as API keys), be sure to define them under the env key in your MCP client's configuration file.

Can I run both Agentward and Kastell at the same time in my AI client?

Yes! MCP clients support multi-server orchestration. You can include both agentward-ai-agentward and kastelldev-kastell as distinct keys inside the single mcpServers object in your configuration file. Your AI assistant will automatically select and call the appropriate tool from either server during chat sessions.

Which MCP server has higher directory engagement and quality ratings?

On AllMCPs, Agentward has a Quality Score of 45 /100 ( Fair ) with 2 views, 0 installs, and 19 GitHub stars. Kastell holds a Quality Score of 52 /100 ( Good ) with 2 views, 0 installs, and 56 GitHub stars.

Side-by-Side Model Context Protocol Comparison

Agentward vs Kastell

In-depth architectural comparison of the Agentward and Kastell MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.

At a Glance & Executive Verdict

Agentward

Security · Local stdio

Quality: 45/100 (Fair) | Auth: No auth required

Kastell

Security · Local stdio

Quality: 52/100 (Good) | Auth: No auth required

Verdict Summary: Choose Agentward if you need specialized Security tools running via a local process. Choose Kastell if your workspace requires Security integration with local subprocess execution. Both servers can be configured concurrently in your client's mcpServers manifest.

Which MCP Server Should You Choose?

Choose Agentward when:

You need dedicated capabilities in the Security domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: No auth required (Free / Open Source).
Primary tools included: Runtime enforcement of YAML-defined least-privilege policies, Sensitive data classification with compliance framework hints, Detection of supply chain threats including deserialization attacks.

Explore Agentward Details

Choose Kastell when:

You need dedicated capabilities in the Security domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: No auth required (Free / Open Source).
You have access to required keys: KASTELL_API_KEY, KASTELL_PROVIDER_TOKEN, KASTELL_SSH_KEY_PATH, KASTELL_CONFIG_PATH.
Primary tools included: 413 security checks in 29 categories, Automated safe fixes and 19-step production hardening, Compliance mapping to CIS, PCI-DSS, HIPAA.

Explore Kastell Details

Feature & Specification Comparison

Specification	Agentward agentward-ai Security	Kastell kastelldev Security
Summary	Permission control plane for AI agents. MCP proxy that enforces least-privilege YAML policies on every tool call, classifies sensitive data (PII/PHI), detects dangerous skill chains, and generates compliance audit trails. Supports stdio and HTTP proxy modes.	Server security auditing and hardening toolkit. 413 security checks across 29 categories (SSH, Firewall, Docker, TLS, HTTP Headers), CIS/PCI-DSS/HIPAA compliance mapping, 19-step production hardening, fleet management, and forensic evidence collection. Supports Hetzner, DigitalOcean, Vultr, and Linode. 13 MCP tools.
Category & Scope	Security	Security
Quality signal	45/100 (Fair)	52/100 (Good)
Transport Protocol	Local Subprocess (stdio)	Local Subprocess (stdio)
Auth Requirement	No auth required	No auth required
Pricing Model	Free / Open Source	Free / Open Source
Required Env Vars	None required	`KASTELL_API_KEYKASTELL_PROVIDER_TOKENKASTELL_SSH_KEY_PATHKASTELL_CONFIG_PATH`
Compatible Clients	Claude DesktopCursorWindsurfClineVS Code	Claude DesktopCursorWindsurfClineVS Code
Install path signal	`npx · low`	`npx · low`
Engagement & Health	2 views 0 copies 0 upvotes 19 stars	2 views 0 copies 0 upvotes 56 stars
Verified / Official	Community Listing	Community Listing
Open full listing	View Agentward Listing	View Kastell Listing

Tools & Capabilities Breakdown

Agentward Tools (6)

Runtime enforcement of YAML-defined least-privilege policies

Sensitive data classification with compliance framework hints

Detection of supply chain threats including deserialization attacks

Support for stdio and HTTP proxy modes

Pre-install security scanning of skill directories

Audit trail output in JSON Lines and RFC 5424 syslog formats

Kastell Tools (6)

413 security checks in 29 categories

Automated safe fixes and 19-step production hardening

Compliance mapping to CIS, PCI-DSS, HIPAA

Fleet management with multi-server support

Built-in MCP server with 17 AI tools

Support for Hetzner, DigitalOcean, Vultr, Linode

Ready-to-Paste Client Configurations

Paste either (or both) of these JSON server blocks into your client config file (e.g. claude_desktop_config.json or ~/.cursor/mcp.json).

Agentward Configuration

mcpServers (Claude Desktop / Cursor)

{
  "mcpServers": {
    "agentward-ai-agentward": {
      "command": "npx",
      "args": [
        "-y",
        "agentward-ai-agentward"
      ]
    }
  }
}

Kastell Configuration

mcpServers (Claude Desktop / Cursor)

{
  "mcpServers": {
    "kastelldev-kastell": {
      "command": "npx",
      "args": [
        "-y",
        "kastelldev-kastell"
      ],
      "env": {
        "KASTELL_API_KEY": "YOUR_KASTELL_API_KEY_HERE",
        "KASTELL_PROVIDER_TOKEN": "YOUR_KASTELL_PROVIDER_TOKEN_HERE",
        "KASTELL_SSH_KEY_PATH": "YOUR_KASTELL_SSH_KEY_PATH_HERE",
        "KASTELL_CONFIG_PATH": "YOUR_KASTELL_CONFIG_PATH_HERE"
      }
    }
  }
}

Frequently Asked Questions

Agentward is categorized under Security and uses a local stdio subprocess. In contrast, Kastell belongs to Security using local stdio subprocess. Select Agentward when you need capabilities focused on security and Kastell when you require tools for security.

More alternatives to Agentward More alternatives to Kastell Security category hub