Aurocrypt Connect
Server Details
Aurocrypt Connect: AI access to your services, under approvals you set, without sharing passwords.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 14 tools
The read/write split is clear, but the credential-type split (vault_invoke_read/write vs vault_provider_read/write) and vault_execute all perform provider calls and their boundaries require reading descriptions closely. More importantly, six metadata tools (vault_autonomy, vault_capabilities, vault_services, vault_connections, vault_profile, vault_usage) overlap heavily, so an agent asking 'what can I access?' has several plausible but subtly different entry points.
All tools share a consistent vault_ prefix and snake_case, with action tools following a vault_<target>_<verb> pattern (vault_invoke_read, vault_provider_write, vault_browser_action) and informational tools following vault_<noun>. The dual convention for verbs (verb_after_target) is readable but a minor deviation from the classic verb_noun pattern.
14 tools is within a reasonable range for a credential broker spanning multiple credential types, browser delegation, and discovery. It is slightly on the heavy side, with roughly half the surface devoted to read-only metadata/discovery rather than actionable operations.
The surface covers discovery, read/write across API-key and full-provider grants, delegated browser jobs with async result retrieval, model listing, and usage reporting — a solid lifecycle for a broker. Minor gaps exist: no explicit job cancellation or polling-timeout control, and connections/services can only be listed, not authorized or revoked.
Available Tools
14 toolsvault_autonomyAutonomy and owner authorityBRead-onlyIdempotentInspect
Show this AI's authority mode, provider-wide grants, user-owned connected resources, available provider surfaces (including dynamic Google API origins), and delegated browser profiles. Metadata only; no cookies, tokens, passwords, or provider secrets are returned.
Inputs: no named parameters.
vault_browser_actionUse an authorized browser sessionBDestructiveInspect
Queue one structured action in a user-controlled authenticated browser profile. Browser cookies/session storage remain on the worker. Returns a job_id; call vault_browser_result until complete.
Inputs: action (required), profile_id (required), risk_hint, human_approved, +1 more.
vault_browser_resultRead browser action resultBRead-onlyInspect
Read or consume the result of a previously queued API Vault browser job.
Inputs: job_id (required).
vault_capabilitiesAPI Vault capabilitiesARead-onlyIdempotentInspect
Describe API Vault's broker, autonomy modes, and credential boundary. Never returns stored credentials.
Inputs: no named parameters.
vault_connectionsAuthorized API-key connectionsARead-onlyIdempotentInspect
List API-key/PAT connections authorized to this connector. Safe metadata only; raw keys are never returned.
Inputs: no named parameters.
vault_executeUse a granular connected-service capabilityCDestructiveInspect
Execute one reviewed granular capability as the connected user, including approval-gated actions.
Inputs: account_id (required), capability_id (required), params, approval_id.
vault_invoke_readRead through an authorized API-key connectionARead-onlyIdempotentInspect
Read data through an authorized API-key/PAT connection using a GET request. API Vault controls authentication and destination hosts and injects the stored credential server-side; credentials are never returned. Use vault_invoke_write for any operation that sends data or changes provider state.
Inputs: path (required), connection_id (required), headers, operation, +1 more.
vault_invoke_writeInvoke an authorized API-key connectionBDestructiveInspect
Execute a provider operation through an authorized API-key/PAT connection using a POST request, including AI model calls. Authentication and destination hosts are controlled by API Vault; the stored credential is injected server-side and never returned.
Inputs: path (required), connection_id (required), body, headers, +3 more.
vault_modelsAvailable AI modelsARead-onlyIdempotentInspect
List AI models reachable through authorized API-key connections.
Inputs: no named parameters.
vault_profileAPI Vault profileARead-onlyIdempotentInspect
Return the stable API Vault profile represented by this authenticated connection. No provider credentials or internal owner identifiers are returned.
Inputs: no named parameters. Returns: id, name, nickname
vault_provider_readRead through a fully authorized providerARead-onlyIdempotentInspect
Read data through a full-provider or owner-equivalent grant on a registered provider API surface using a GET request. API Vault pins or validates the destination origin, binds GitHub/Supabase requests to resources authorized by this user, and injects that user's OAuth credential server-side. For google.api.generic, supply the exact HTTPS Google API origin under *.googleapis.com. Use vault_provider_write for any operation that changes provider state.
Inputs: path (required), account_id (required), surface_id (required), origin, +2 more.
vault_provider_writeAct through a fully authorized providerADestructiveInspect
Change provider state through a full-provider or owner-equivalent grant on a registered provider API surface. API Vault pins or validates the destination origin, binds GitHub/Supabase requests to resources authorized by this user, injects that user's OAuth credential server-side, classifies risk, and enforces the owner's financial/security/destructive/communication switches. For google.api.generic, supply the exact HTTPS Google API origin under *.googleapis.com.
Inputs: path (required), method (required), account_id (required), surface_id (required), +5 more.
vault_servicesConnected service capabilitiesARead-onlyIdempotentInspect
List granular OAuth-connected service capabilities explicitly granted to this AI, including safe metadata for the user's bound repositories, projects, and other provider resources.
Inputs: no named parameters.
vault_usageGateway usageBRead-onlyIdempotentInspect
Read metadata-only API-key gateway usage for this connector.
Inputs: limit.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Password vault for AI agents with scoped, user-approved access
Your AI and another company's AI on one signed line. People approve; nobody shares logins.
Reach your own computers from any AI app: files, search, commands, approvals and outage alerts.
Your apps as AI tools: one sign-in, one vault, 125 services and 1,851 endpoints, with receipts.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceAI permissions layer so you don't have to give your agent keys to access your apps. Manage policies for agents and approve actions you want on your phone, watch, web or desktop app.Apache 2.0
- AlicenseNot gradedqualityDmaintenanceZero-knowledge credential injection for AI agents. Your agent authenticates to websites and APIs without ever seeing a password, TOTP code, or API key.4 npm1MIT

Lanes Linkofficial
AlicenseNot gradedqualityAmaintenanceOne secure, self-hosted MCP endpoint connecting AI agents to your real accounts (mail, calendar, files, notes), with per-profile separation, explicit permission enforcement, and an append-only audit log.32 npm36Apache 2.0- AlicenseNot gradedqualityBmaintenanceLets AI agents make authenticated API and OAuth calls using stored credentials they never see, with per-credential Touch ID approval, proxy execution, and a local audit log of every use.1Apache 2.0
Glama MCP Gateway
Add one secure layer between your agents and this server.