Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, email [email protected] and we’ll put it right.

Emilia Protocol

NPM · @EMILIA-PROTOCOL/MCP-SERVER · SCANNED AUG 3

Trust & human sign-off for AI agents: approval required before irreversible agent actions

+18 this week 71 Trust /100
Trust breakdown (6 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score →

Supply Chain Security86
  • No malware found by supply-chain analysis.Pass
  • Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.Partial
  • No install/post-install scripts declared.Pass
  • Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability85
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 1989 tokens (~94/item across 21 items; 17 tools + 4 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management27
  • Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.

npm · @emilia-protocol/mcp-server

# add to Claude Code
claude mcp add emiliaprotocol-mcp-server -- npx -y @emilia-protocol/mcp-server
# add to Codex CLI
codex mcp add emiliaprotocol-mcp-server -- npx -y @emilia-protocol/mcp-server
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "emiliaprotocol-mcp-server": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@emilia-protocol/mcp-server"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add emiliaprotocol-mcp-server --command npx --arg -y --arg @emilia-protocol/mcp-server
# ~/.hermes/config.yaml
mcp_servers:
  emiliaprotocol-mcp-server:
    command: "npx"
    args: ["-y", "@emilia-protocol/mcp-server"]
// mcp.json
{
  "mcpServers": {
    "emiliaprotocol-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@emilia-protocol/mcp-server"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 3 Aug 26 +51
    • Provenance: unverified → fail security
    • Install scripts: unverified → pass security
    • Known CVEs: unverified → partial security
    • Security disclosure: unverified → fail functional
    • Dependency health: unverified → partial functional
    • Maintenance: unverified → pass functional
    • Stability: unverified → 0.27 functional
    • MCP protocol: unverified → pass functional
    • Schema quality: unverified → excellent functional
    • Tool coverage: unverified → 100 functional
    • License: unverified → pass functional
    • Schema quality: unverified → 100 functional
    • Licence: Apache-2.0 functional
  • 2 Aug 26 0
    • Security disclosure: fail → unverified functional
  • 1 Aug 26 −15
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 31 Jul 26 −18
    • Malware scan: pass → unverified security
  • 27 Jul 26 53

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 3 Aug 2026 · Analysed npm/@emilia-protocol/[email protected]

Provenance none

Ecosystem: npm · Outcome: none

Dependencies 94 packages

94 packages in the resolved dependency tree · 94 deprecated · 29 stale.

The dependency tree was only partially resolved, so these counts may be incomplete.

MCP tools — 17 exposed · ~1,907 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability.

Tool Tokens
ep_add_presentation ~173

Add an identity presentation (proof) to an active handshake. WRITE: appends the party's identity claims to the handshake for evaluation against its policy; supports full, selective, or zero-knowledge disclosure. Requires auth. Returns the updated presentation count and handshake state. Call after ep_initiate_handshake and before ep_verify_handshake.

NameTypeReqDescription
claimsobjectyesIdentity claims being presented
disclosure_modestringDisclosure mode: "full", "selective", "zk"
handshake_idstringyesHandshake ID to present to
issuer_refstringOptional credential issuer reference
party_rolestringyesRole of the presenting party
presentation_typestringyesType: "verifiable_credential", "ep_trust_profile", "attestation"

No output schema declared.

No examples provided.

ep_bind_receipt_to_commit ~76

Bind a post-action receipt to a commit, completing the commit-execute-receipt cycle. Links the behavioral outcome back to the signed authorization token.

NameTypeReqDescription
commit_idstringyesCommit ID to bind to (epc_...)
receipt_idstringyesReceipt ID to bind (ep_rcpt_...)

No output schema declared.

No examples provided.

ep_check_signoff ~73

Poll a pending authorization after ep_guard_action returns BLOCKED. Pass the receipt_id. Returns PENDING, APPROVED (the action may now proceed), or DENIED (with reason). Safe to call repeatedly until a decision is reached.

NameTypeReqDescription
receipt_idstringyesThe receipt_id returned by ep_guard_action.

No output schema declared.

No examples provided.

ep_create_delegation ~201

Create a delegation record. WRITE: persists to the EP ledger that a human or principal authorizes an agent to act on their behalf, with scope, expiry, and optional constraints. Requires auth. Returns a delegation_id that later actions reference (via ep_verify_delegation) to prove authorization. Use when a principal grants an agent standing authority for a bounded set of actions.

NameTypeReqDescription
agent_entity_idstringyesThe agent entity being authorized
constraintsobjectAdditional constraints (geo, merchant_category, etc.)
expires_atstringISO8601 expiry timestamp. If omitted, defaults to 24 hours.
max_value_usdnumberMaximum transaction value in USD this delegation authorizes (optional)
principal_idstringyesThe principal (human/org) granting the delegation
scopearrayyesList of permitted action types (e.g. ["purchase", "book", "send_email"])

No output schema declared.

No examples provided.

ep_get_commit_status ~71

Get the current state of a pre-action commit by id. Read-only. Returns one of active, revoked, expired, or fulfilled, plus the bound action hash and expiry — poll this to learn whether a commit may still be consumed.

NameTypeReqDescription
commit_idstringyesCommit ID (epc_...)

No output schema declared.

No examples provided.

ep_get_handshake ~51

Get the full state of a handshake including parties, presentations, binding, and result. Use this to check handshake progress or review completed exchanges.

NameTypeReqDescription
handshake_idstringyesHandshake ID to retrieve

No output schema declared.

No examples provided.

ep_guard_action ~260

REQUIRED before any 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. Returns APPROVED with a receipt the action may proceed under, or BLOCKED with a receipt_id + signoff_id while a named human reviews. Do NOT execute the action without an APPROVED result — if BLOCKED, poll ep_check_signoff with the receipt_id.

NameTypeReqDescription
action_typestringyesKind of action, e.g. "large_payment_release", "vendor_bank_account_change", "ai_agent_payment_action".
amountnumberAmount, for payments/releases.
currencystringISO currency code, e.g. "USD".
destinationstringWhere funds or data are going (account, address).
organization_idstringyesThe organization this action belongs to.
risk_flagsarrayOptional risk signals, e.g. ["new_destination","after_hours"].
summarystringOne-line, human-readable description the approver will see.
target_resource_idstringyesWhat is being acted on — an invoice id, account id, or record id.

No output schema declared.

No examples provided.

ep_initiate_handshake ~131

Initiate an EP Handshake — a structured identity exchange between parties. The handshake coordinates mutual presentation of identity proofs before a trust decision. Requires at least 2 parties and a governing trust policy.

NameTypeReqDescription
bindingobjectOptional binding constraints
interaction_idstringOptional external interaction reference
modestringyesHandshake mode: "mutual", "one-way", "delegated"
partiesarrayyesParties in the handshake (min 2). Each: { entity_ref, role }
policy_idstringyesTrust policy governing the handshake

No output schema declared.

No examples provided.

ep_install_preflight ~161

BEFORE installing or enabling third-party software an agent depends on — an npm package, GitHub app, browser extension, or MCP server — check it here. Evaluates the software against a fit-for-purpose trust policy and returns allow / review / deny with reasons covering publisher, requested permissions, provenance, and trust history.

NameTypeReqDescription
contextobjectInstall context: { host, install_scope, permission_class, data_sensitivity, execution_mode }
entity_idstringyesSoftware entity ID (e.g. github_app:acme/code-helper)
policystringSoftware policy: github_private_repo_safe_v1, npm_buildtime_safe_v1, browser_extension_safe_v1, mcp_server_safe_v1, or standard EP policies

No output schema declared.

No examples provided.

ep_issue_commit ~193

Issue a signed EP Commit before a high-stakes action. Returns a commit_id, decision (allow/deny/review), expiry, scope, and appeal path. The commit binds the agent to a specific action type, entity, and policy before execution.

NameTypeReqDescription
action_typestringyesAction type: install, connect, delegate, transact
contextobjectAdditional context metadata (optional)
counterparty_entity_idstringCounterparty entity ID (optional)
delegation_idstringDelegation ID if acting under delegation (optional)
entity_idstringyesEntity requesting the commit
max_value_usdnumberMaximum value in USD (optional)
policystringTrust policy to enforce (default: standard)
principal_idstringPrincipal authorizing the action (optional)
scopearrayAction scope list (optional)

No output schema declared.

No examples provided.

ep_list_policies ~30

List all available trust policies with their requirements and families. Use to discover which policy to evaluate against.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

ep_revoke_commit ~93

Revoke an active pre-action commit before it is fulfilled or expires. SIDE EFFECT: terminally cancels the commit — it can never be consumed after this, and the change is irreversible. Requires auth. Returns the revoked status; use when a pending action should be called off.

NameTypeReqDescription
commit_idstringyesCommit ID to revoke (epc_...)
reasonstringyesReason for revocation

No output schema declared.

No examples provided.

ep_revoke_handshake ~61

Revoke an active handshake. Only parties to the handshake may revoke it. Revocation is terminal — the handshake cannot be reopened.

NameTypeReqDescription
handshake_idstringyesHandshake ID to revoke
reasonstringyesReason for revocation

No output schema declared.

No examples provided.

ep_verify_commit ~76

Verify a pre-action commit — read-only, no side effects. Checks its signature, status, and validity and returns valid/invalid plus the current status, decision, and expiry. Use before relying on or consuming a commit to confirm it is genuine and still active.

NameTypeReqDescription
commit_idstringyesCommit ID (epc_...)

No output schema declared.

No examples provided.

ep_verify_delegation ~92

Verify that an agent currently holds a valid delegation from a principal for a specific action. Use this before accepting a task from an agent claiming to act on behalf of a human. Returns: valid/expired/not_found with scope details.

NameTypeReqDescription
action_typestringThe action type to check (must be in delegation scope)
delegation_idstringyesDelegation ID (ep_dlg_...)

No output schema declared.

No examples provided.

ep_verify_handshake ~82

Evaluate all presentations in a handshake against its governing policy — read-only, no mutation. Returns accepted (all requirements met), rejected (policy violations), or partial (awaiting presentations), each with reason_codes explaining the outcome. Call after the parties have added their presentations to decide whether the handshake clears.

NameTypeReqDescription
handshake_idstringyesHandshake ID to verify

No output schema declared.

No examples provided.

ep_verify_receipt ~83

Verify a trust receipt — its signature and Merkle inclusion against the anchored root. Read-only. Returns valid/invalid plus the verified claim (action, approver, outcome) and anchor status; use it to independently confirm a receipt was issued by EP and has not been tampered with.

NameTypeReqDescription
receipt_idstringyesReceipt ID (ep_rcpt_...)

No output schema declared.

No examples provided.