Magicsword MCP vs Emilia Protocol
A side-by-side look at the Magicsword MCP and Emilia Protocol MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
M
Magicsword MCPSecurity · Local subprocess (stdio)Manage MagicSword endpoints, alerts, policies, and private intelligence through MCP.53GoodAuth: api key requiredVerdict: choose Magicsword MCP for security work as a local process; choose Emilia Protocol for security as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
MChoose Magicsword MCP when
- You need dedicated capabilities in the Security domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: API key required.
- You have the keys it needs:
MAGICSWORD_API_KEY, MAGICSWORD_BASE_URL. - You want tools like
whoami, list_endpoints, show_endpoint.
Choose Emilia Protocol when
- You need dedicated capabilities in the Security domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: No auth required.
- You want tools like
ep_guard_action, ep_check_signoff, ep_verify_receipt.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | M Magicsword MCP | |
|---|---|---|
| Category | Security | Security |
| Quality signal | 53/100 · Good | 71/100 · Great |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | API key required | No auth required |
| Pricing | BYOK (pay the provider) | Free |
| Required env vars | MAGICSWORD_API_KEYMAGICSWORD_BASE_URL | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 0 | 612 |
| Directory activity | 0 views 0 installs 0 upvotes | 5 views 0 installs 0 upvotes |
| Tools | 21 | 3 |
| Full listing | View Magicsword MCP | View Emilia Protocol |
Tools & capabilities
Magicsword MCP tools 21
whoamiReturns organization, key id, and scopes. Always call first when troubleshooting.list_endpointsLists endpoints with optional platform / status / hostname-glob filtering.show_endpointFetches one endpoint with OS, policy, compliance, upgrade, heartbeat, and AMSI details.list_agent_releasesLists available agent versions and per-platform latest releases.find_alertsSearches alerts by severity / ack state / since / hostname / MITRE technique.list_eventsLists audit/block telemetry events, including last-day event review workflows.triage_alertFetches one alert directly with triggering events, metadata, and file context; optionally acknowledges or dismisses it.list_policiesLists policies with current version + mode.show_policyShows one policy by id.manage_policy_rulesLists rules or adds explicit / event-derived rules to a policy by id or name. Avoid explicit flat hash rules for Windows WDAC.apply_policy_to_endpointsResolves endpoints and previews a policy assignment; `confirm=true` applies it after approval.flip_to_enforcingTwo-step preview/confirm flip with a server-issued one-time confirm token. Safety-critical.- +9 more on the listing page
Emilia Protocol tools 3
ep_guard_actionRequest authorization before an irreversible action: payments, wire transfers, fund releases, deletions, record or account changes, or sending messages with real-world effect. Submits the exact action for policy evaluation and human authorization. This MCP tool does not itself sit at the executor choke point: even after approval, the executor MUST match the returned action_hash and atomically consume the receipt before effect. If BLOCKED, poll ep_check_signoff with the receipt_id.ep_check_signoffPoll a pending authorization after ep_guard_action returns BLOCKED. Pass the receipt_id. Returns PENDING, APPROVED_PENDING_CONSUME, CONSUMED, or DENIED. Approval alone is not permission to execute: the executor must match action_hash and atomically consume the receipt at its own choke point.ep_verify_receiptAsk the configured EMILIA service to verify a stored trust receipt and report its hash and anchor status. Read-only, but not an offline verifier: the result is the service response for the supplied receipt_id.
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Magicsword MCP
{
"mcpServers": {
"magicsword-mcp": {
"command": "npx",
"args": [
"-y",
"@magicsword-io/magicsword-mcp"
],
"env": {
"MAGICSWORD_API_KEY": "YOUR_MAGICSWORD_API_KEY_HERE",
"MAGICSWORD_BASE_URL": "YOUR_MAGICSWORD_BASE_URL_HERE"
}
}
}
}
Emilia Protocol
{
"mcpServers": {
"emiliaprotocol-emilia-protocol": {
"command": "npx",
"args": [
"-y",
"@emilia-protocol/mcp-server"
]
}
}
}
Frequently asked questions
Magicsword MCP is categorized under Security and uses a local stdio subprocess. Emilia Protocol belongs to Security and uses a local stdio subprocess. Pick Magicsword MCP for security work and Emilia Protocol for security.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Magicsword MCP is bring-your-own-key: usage is billed by the API provider you supply a key for. Auth: api key required. Emilia Protocol is listed as free. Auth: no auth required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add magicsword-mcp and emiliaprotocol-emilia-protocol as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Magicsword MCP has a quality signal of 53/100 (Good) with 0 views, 0 installs and 0 GitHub stars. Emilia Protocol has 71/100 (Great) with 5 views, 0 installs and 612 GitHub stars.