MANDATE Credential Broker
Measured conclusion: Deep-tested. L2 outcome: tools_ok.
MCP server for mandates, delegation, policy-gated execution, credential grants, and audit.
| Author | io.github.projetnanocorp |
|---|---|
| Access | remote |
| Publisher key required | No |
| Measured state | Deep-tested |
| L1 liveness | alive |
| L1 latency | 2309 ms |
| Last measured | 2026-10-24 |
Add to your agent
Copy this into your MCP client config:
{
"mcpServers": {
"MANDATE Credential Broker": {
"url": "https://mandate.nanocorp.app/mcp",
"transport": "streamable-http"
}
}
}
Measured tools (11)
mandate.discoverReturns this self-describing tool manifest.
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
mandate.mintCreates an active human-granted mandate for an agent and records it to the hash-chained ledger.
Parameters:
organization_id(required)agent_id(required)grantor_principal_id(required)budget_currency(required)budget_total(required)per_action_limit(required)expires_at(required)scopes(required)
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
mandate.delegateCreates a child mandate only when it is a no-escalation subset of the parent mandate.
Parameters:
parent_mandate_id(required)delegator_agent_id(required)delegate_agent_id(required)budget_total(required)per_action_limit(required)starts_at(required)expires_at(required)scopes(required)
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
mandate.authorize-actionSubmits an action through the Gateway and canonical Policy Engine; returns ALLOW, DENY, or REQUIRE_APPROVAL with ledger proof.
Parameters:
acting_agent_id(required)action_type(required)amount_minor(required)counterparty(required)
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
mandate.verify-proofRecords a proof payload hash and appends proof evidence to the hash-chained ledger.
Parameters:
organization_id(required)subject_type(required)subject_id(required)proof_type(required)payload(required)
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
mandate.revokeRevokes a mandate subtree and records the revocation to the hash-chained ledger.
Parameters:
revoked_by_principal_id(required)reason(required)
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
broker.register-credentialRegisters an opaque vault handle/reference only; plaintext secret fields are rejected and never ledgered.
Parameters:
organization_id(required)registered_by_agent_id(required)label(required)credential_type(required)vault_handle(required) — string — Opaque vault reference such as vault://provider/path; never a plaintext secret.allowed_action_type(required)metadata— object
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
broker.request-accessAsks the canonical Policy Engine for an ALLOW decision before issuing a short-lived HMAC-sealed grant bound to credential, mandate, agent, scope, and expiry.
Parameters:
credential_id(required)acting_agent_id(required)mandate_id(required)action(required)
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
broker.useRedeems a sealed grant for the bound acting agent and executes the bound action through the Gateway and Policy Engine; does not expose plaintext secrets.
Parameters:
grant_token(required)acting_agent_id(required)
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
broker.revoke-grantRevokes a broker grant by id and records the revocation to the ledger.
Parameters:
revoked_by_agent_id(required)reason(required)
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
broker.introspect-grantValidates a grant token seal, reports active/revoked/expired state, and records introspection to the ledger.
Parameters:
grant_token(required)
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.