An upstream-maintained MCP server for the Emilia Protocol authority control plane: it requests, tracks, and verifies signed receipts for exact agent actions at protected executor boundaries. It suits security teams that need finite agent mandates and portable evidence. It is not an identity system, policy engine, settlement rail, or certifier, and its preventive property depends on complete mediation of the protected path. The default tool surface is small, with broader tool sets behind explicit environment switches.
Strongest · Documentation 12/20 Weakest · Reliability 8/20
Static review · not runListed 2026-09-10
Read the FMRS scoring method →Runtime：Node.js
EP_API_KEY
API key for live action-guard, signoff, and write operations; public receipt lookup may work without it. Optional secret.
EP_INCLUDE_PROTOCOL_TOOLS
Set to true to advertise handshake, commit, and delegation tools in addition to the default three-tool action front door.
EP_INCLUDE_REGISTRY_TOOLS
Set to true to advertise the complete 36-tool legacy registry and reputation catalog.
{
"mcpServers": {
"emilia-protocol": {
"command": "npx",
"args": [
"-y",
"@emilia-protocol/mcp-server"
],
"env": {
"EP_API_KEY": ""
}
}
}
}
Shown for Claude Desktop. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.
{
"servers": {
"emilia-protocol": {
"command": "npx",
"args": [
"-y",
"@emilia-protocol/mcp-server"
],
"env": {
"EP_API_KEY": ""
}
}
}
}
Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).
claude mcp add emilia-protocol -e EP_API_KEY= -- npx -y @emilia-protocol/mcp-server
Run it in a terminal; replace any <…> placeholders with your own values first.
After adding the server to your MCP client, the Emilia Protocol default three-tool action front door (request, track, and verify signed receipts) should appear in the tool list. You can also run `npx -y @emilia-protocol/mcp-server` to confirm it starts, or `npx @emilia-protocol/issue demo` to issue an offline receipt without an API key.
Once connected, you can ask your AI assistant things like:
Listed from the project's documentation, not tested by this site.
The Emilia Protocol MCP server provides exact-action approval for consequential agent actions. It runs over stdio and is launched with npx from the npm package @emilia-protocol/mcp-server. Per the manifest, it lets clients request, track, and verify signed receipts, and it acts as the MCP-facing front door to the Emilia Gate authority control plane, which enforces finite customer-owned mandates at protected executor boundaries. It advertises a default three-tool action front door, with optional environment switches for handshake, commit, and delegation tools and for the legacy 36-tool registry and reputation catalog. The server is maintained by the upstream Emilia Protocol project (official). It is authorization and evidence infrastructure, not an identity system, wallet, reputation score, settlement rail, or universal policy engine, and it does not require that a human approve every action: authority can come from a bounded mandate, a bounded capability, a quorum, or a relying-party composition of native evidence. Preventive control holds only where the deployment completely mediates the protected path; it constrains no path that bypasses the enforcement point.
Manage your Hevy workout data from AI assistants via MCP.
Firecrawl's official MCP server for web search, scraping, and structured extraction for AI agents
One binary. One grammar. Evidence from the biomedical sources you already trust.
Encrypted, fully offline long-term memory for AI agents
Source revision 3f712d28b2cf Data synced 2026-10-19 Read the FMRS scoring method