Skip to content
MCP server

alalanet guard — check before you install

Signed allow, hold or block checks on packages, repos and MCP servers before install

Status and history

Answered our latest tool-list check 9 hours ago with 7 tools. It will be marked verified after 3 successful checks in 7 days.

Pricing
Freemium
Platforms
API, CLI
Runs
Remotely
Version
1.5.0
Listing updated
2 days ago

About alalanet guard — check before you install

alalanet guard — check before you install is a freemium MCP server for security. It runs as a hosted remote server, so there is nothing to install locally.

The guard endpoint is a narrow slice of the alalanet service, limited to checks before an agent installs something or connects to an MCP server, with no payment tools. Verdicts come as allow, hold or block. A package check covers npm and PyPI packages, GitHub repositories, skills and MCP servers, while a repository check looks at the agent configuration a repo ships, such as MCP configs, hooks, permissions, tasks and instruction files, before an agent or editor opens it.

The pitch rests on evidence. The site says it watches 76,759 agent services and that verdicts, live checks and status changes are signed Nostr events appended to a public transparency log that can be verified offline. It also reports that 8.4 percent of MCP listings it checked do not answer or answer with something invalid. Independent witnesses do not co-sign the log yet.

Use is free without sign-up, with daily limits of 100 status checks and 5 live checks. Paid 30-day plans, paid in crypto with no auto-renewal, raise limits. A larger endpoint adds payment checks for x402 services and 25 tools in total, and a Claude Code plugin can check every install an agent runs.

Install

Run in a terminal

claude mcp add --transport http guard https://alalanet.com/mcp/guard

Add to Settings → Connectors → Add custom connector

https://alalanet.com/mcp/guard
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "guard": {
      "url": "https://alalanet.com/mcp/guard"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "guard": {
      "type": "http",
      "url": "https://alalanet.com/mcp/guard"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "guard": {
      "serverUrl": "https://alalanet.com/mcp/guard"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "guard": {
      "type": "http",
      "url": "https://alalanet.com/mcp/guard"
    }
  }
}

Tools this server provides (7)

Read directly from the server.

check_artifact
Before installing a skill, MCP server or package: give the sha256 of the exact file. Read-only and free. Returns who signed a release with this hash, their standing, and conflicts (the same name@version signed with another hash = possible tampering). Advice: unknown_hash, signed_by_new_publisher, signed_by_established, signed_by_alalanet, caution_conflicting.
check_repo_config
Before opening or trusting a GitHub repository someone sent you (a take-home task, a code review, a demo, a fork): its agent configuration can start MCP servers, run hooks and editor tasks, widen permissions and plant instructions as soon as the project is opened. Pass repo (owner/repo or a GitHub URL) and optional ref; for a local or private checkout pass files instead (path -> content of those f
check_service
Call before connecting to a remote MCP server, and whenever a call to it fails. Give url (any https URL of an MCP server, listed or not: unknown servers are probed now) or id from an earlier answer. Returns: alive, advice (ok / ok_requires_auth: working; unverified_yet: not fully checked yet; caution_tools_changed or caution_suspicious_tool_description: confirm with the user first; avoid_down or a
connect_check
Before adding a remote MCP server to a client, or when it fails to connect: give its url. One live read (initialize with protocol 2025-06-18 and 2025-11-25, tools/list, the 401 and OAuth metadata, the host's IPv4) and a verdict per client: claude_code, claude_ai, chatgpt, codex_cli, cursor, vscode, windsurf, gemini_cli, zed, cline, each ok, warn or fail with reasons (protocol version answered, OAu
get_attestation
Use when you or your user need proof of something alalanet stated: an install verdict, a server check, a tool-set change. Pass the event id (64 hex) from a previous result. Read-only and free. Returns the signed Nostr event (event_json, exact signed bytes), the signer key, and its RFC 6962 inclusion proof under a signed C2SP checkpoint, plus how_to_verify. Verify offline without trusting alalanet:
install_check
Checks something before it is installed, typically when a README, a document or another agent suggests installing it: an npm or PyPI package, an install command (npx -y pkg, uvx pkg, pip install pkg, npm i pkg, claude mcp add NAME -- npx -y pkg, skills add owner/repo, clawhub install slug, code --install-extension publisher.name), a GitHub repository or skill, a ClawHub skill, a VS Code Marketplac
verify_tools
Checks the tools an agent received from a remote MCP server against alalanet's history of that server, to catch a server that changed its tools after you approved them, or serves you something different from what it serves everyone else. Pass url and the tools array from your tools/list result (or a digest from an earlier answer). Read-only and free. When your set differs from alalanet's last read

What it does

Install checks
Returns allow, hold or block for packages, repos, skills and MCP servers.
Repository config checks
Inspects MCP configs, hooks and permissions in a repo before opening it.
Tool verification
Checks that the tools you received match what the server gives everyone.
Signed verdicts
Verdicts are signed and logged to a public transparency log.
Free keyless use
Works without sign-up within daily limits.
Claude Code plugin
Can check each install the agent runs, denying blocks and asking on holds.

Good for

  • Vet an npm package before an agent installs it
  • Check a cloned repo's hooks before opening it in an agent
  • Confirm an MCP server is alive before connecting
  • Spot typosquatted packages
  • Keep an auditable record of agent install decisions

Pricing

Freemium, from $9 a month

Free: 100 status and 5 live checks a day, no sign-up. Agent Pro $9 per 30 days; Team $49 per 30 days.

Prices change. Check alalanet.com before you buy.

alalanet guard — check before you install FAQ

Is it free?

Yes within limits: 100 status checks and 5 live checks a day without sign-up. Agent Pro is $9 per 30 days, Team $49.

How are plans paid?

In USDC on Base or USDT on supported networks, in 30-day periods with no auto-renewal.

How can I trust the verdicts?

They are signed and appended to a public transparency log whose entries can be verified offline.

Which endpoint is this?

The guard endpoint with install and MCP-server checks only; the main endpoint adds payment checks and the full one lists 25 tools.

Is alalanet guard — check before you install free?

alalanet guard — check before you install has a free plan, with paid plans for more usage or features. Paid plans start at $9 a month.

How do I add alalanet guard — check before you install to Claude Code?

Run this command in your terminal: claude mcp add --transport http guard https://alalanet.com/mcp/guard

What are the best alternatives to alalanet guard — check before you install?

The closest alternatives to alalanet guard — check before you install are REA, Agent Roast, Midplane, Leash and Tinplate Edge AI Safety, Security & EU Compliance.

Alternatives to alalanet guard — check before you install

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Agent Roast

    MCP server

    Offline review that flags agent changes which weaken tests, assertions or CI

    Runs locally
    • Open source
    • 4 Hacker News points
    • Developer tools
  3. Midplane

    MCP server

    Postgres gateway for AI agents with table grants, column masking and approval for writes

    Runs locally
    • Open source
    • 5 GitHub stars
    • Databases
  4. Leash

    MCP server

    Review what your AI touched, approve risky actions and undo supported changes

    • 1 tool
    • Remote
    • Free
    • 1 GitHub star
    • Security
  5. SecureCloud

    MCP server

    SentinelOne and IT security catalog, prices, quotes and checkout links for Israel

    • 7 tools
    • Remote
    • Free
    • Security