@vengtoo/mcp-server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@@vengtoo/mcp-server check if user alice can view document 123"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
@vengtoo/mcp-server
Early access —
0.xreleases may have breaking changes. Pin your version if stability matters.
Manage your Vengtoo authorization model and check access through any MCP-compatible AI tool.
Exposes your Vengtoo tenant as MCP tools — create resource types, subjects, roles, and policies; assign them; and check authorization decisions — all from a conversation.
Install
First, create an API key in the Vengtoo dashboard under Settings → API Access. Then add the server to your MCP client config (Claude Code, Cursor, Windsurf, Cline, or any MCP-compatible tool):
{
"mcpServers": {
"vengtoo": {
"command": "npx",
"args": ["@vengtoo/mcp-server"],
"env": {
"VENGTOO_API_KEY": "vgt_..."
}
}
}
}Or with OAuth2 client credentials:
{
"mcpServers": {
"vengtoo": {
"command": "npx",
"args": ["@vengtoo/mcp-server"],
"env": {
"VENGTOO_CLIENT_ID": "client_...",
"VENGTOO_CLIENT_SECRET": "vgt_cs_..."
}
}
}
}Claude Code shortcut:
claude mcp add vengtoo -e VENGTOO_API_KEY=vgt_... -- npx @vengtoo/mcp-serverRelated MCP server: volcengine-mcp-server
Local build (development)
npm install
npm run build
node dist/index.jsPoint at a local agent instead of cloud:
"env": {
"VENGTOO_API_KEY": "vgt_...",
"VENGTOO_BASE_URL": "http://localhost:8181"
}Tools
Tool | What it does |
| Resource type management |
| Resource management |
| Subject management |
| Role membership |
| Role management |
| Policy management |
| Policy assignment (with optional |
| Evaluate whether a subject can perform an action on a resource |
| MCP governance — review, then approve or block the tools an AI agent can call through a gateway |
Environment variables
Variable | Required | Description |
| One of these two | API key starting with |
| One of these two | OAuth2 client credentials |
| No | Override API base URL. Default: |
Docs
License
MIT
Available Tools
29 toolsassign_policyA
Assign a policy to a subject, role, or group. This is what actually grants access — creating a policy alone does nothing until it is assigned.
entity_type must be "subject", "role", or "group".
For time-boxed (JIT) access: set expires_at. For future-dated access: also set starts_at.
Inputs: entity_id (required), policy_id (required), entity_type (required), starts_at, +1 more.
assign_role_to_subjectA
Give a subject a role. The subject inherits all policies assigned to the role. Use this to build RBAC: create a role, assign policies to it, then assign the role to subjects.
Inputs: role_id (required), subject_id (required).
check_authorizationA
Ask Vengtoo whether a subject can perform an action on a resource. Returns decision: true (allowed) or false (denied), plus the reason and which policy/access path was responsible.
Identify the subject and resource using either their Vengtoo UUID (id) or your system's own identifier (external_id). external_id is preferred in production — it avoids the need to store Vengtoo UUIDs.
For type-level checks (does this user have ANY access to this type of resource?): set resource_type and omit resource_id and resource_external_id. For instance-level checks (does this user have access to THIS specific resource?): set resource_id or resource_external_id.
Inputs: action (required), subject_type (required), resource_type (required), subject_id, +3 more.
create_namespaceA
Create a new namespace. Resources created inside this namespace are isolated from resources in other namespaces. Use "default" namespace unless you specifically need isolation.
Inputs: name (required), description.
create_policyA
Create a policy. A policy grants or denies a set of actions on a resource type (type-level) or a specific resource (instance-level). After creating, assign it to a subject or role with assign_policy.
For type-level: set resource_type_id and actions — the policy applies to ALL resources of that type. For instance-level: set resource_id and actions — the policy applies to ONE specific resource.
Inputs: name (required), effect (required), actions (required), priority, +3 more.
create_resourceA
Create a resource — a specific instance of a resource type (e.g. a specific document, a specific project). Set external_id to your system's own identifier (database UUID, slug) so you can reference it at evaluation time without storing Vengtoo's internal ID.
Inputs: name (required), type (required), description, external_id.
create_resource_typeA
Create a resource type. Do this before creating resources or policies. The actions list defines what verbs are valid for this type (e.g. ["read", "write", "delete"]). Policies targeting this type use these action names.
Inputs: name (required), actions (required), description.
create_roleA
Create a role. After creating it, assign policies to the role with assign_policy (entity_type: "role"), then assign subjects to the role with assign_role_to_subject.
Inputs: name (required), description.
create_subjectA
Create a subject — any principal that can be authorized (user, service, AI agent, device). Set external_id to your system's own user/service identifier so evaluation calls can reference it without a Vengtoo UUID lookup.
Inputs: name (required), type (required), external_id.
delete_namespaceA
Delete a namespace by ID. This does not delete the resources inside it.
Inputs: id (required).
delete_policyA
Delete a policy by ID. Subjects or roles that had this policy assigned immediately lose the access it granted.
Inputs: id (required).
delete_resourceC
Delete a resource by ID.
Inputs: id (required).
delete_resource_typeB
Delete a resource type by ID.
Inputs: id (required).
delete_roleA
Delete a role by ID. Subjects who had this role lose any access that came exclusively from it.
Inputs: id (required).
delete_subjectB
Delete a subject by ID.
Inputs: id (required).
get_namespaceC
Get a namespace by ID.
Inputs: id (required).
get_policyA
Get a policy by ID, including its resource and action assignments.
Inputs: id (required).
get_resourceC
Get a resource by ID.
Inputs: id (required).
get_resource_typeC
Get a resource type by ID.
Inputs: id (required).
get_roleB
Get a role by ID.
Inputs: id (required).
get_subjectC
Get a subject by ID.
Inputs: id (required).
list_namespacesA
List all namespaces in the tenant. Namespaces are optional containers that scope resources — useful when the same resource type name is used across multiple isolated environments (e.g., prod vs staging).
Inputs: no named parameters.
list_policiesA
List all policies in the tenant.
Inputs: no named parameters.
list_resourcesA
List resources in the tenant.
Inputs: no named parameters.
list_resource_typesA
List all resource types. A resource type defines a category of thing you protect (e.g. "document", "project", "invoice") and the actions available on it.
Inputs: no named parameters.
list_rolesA
List all roles. Roles are named collections of policies — assign a role to many subjects instead of assigning the same policies repeatedly.
Inputs: no named parameters.
list_subjectsA
List subjects (users, services, AI agents, or any other principal) in the tenant.
Inputs: type.
unassign_policyA
Remove a policy assignment from a subject, role, or group. Access granted by this policy is revoked immediately.
Inputs: entity_id (required), policy_id (required), entity_type (required).
unassign_role_from_subjectA
Remove a role from a subject. The subject immediately loses any access that came exclusively from this role.
Inputs: role_id (required), subject_id (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 29 tools
Each tool targets a distinct operation on a specific entity (e.g., create_namespace, assign_policy, check_authorization). There is no overlap; even assignment operations are clearly separated by entity type.
All tool names use consistent snake_case with a verb_noun pattern (e.g., create_resource, list_roles, delete_policy). Longer names like assign_role_to_subject remain descriptive and follow the pattern.
With 29 tools, the count is high but justified by the comprehensive coverage of multiple entity types (namespace, policy, resource, resource_type, role, subject) and their CRUD plus assignment operations. It slightly exceeds the ideal range but remains well-scoped.
The tool set lacks update operations for all entities (e.g., update_policy, update_role). This forces users to delete and recreate objects to modify them, which is a significant gap for a permissions management system.
Maintenance
Related MCP Connectors
Identity, authorization, audit trails, and revocable permissions for AI agents accessing MCP tools.
Zero-setup MCP gateway securely connecting AI to your tools with authentication and workflows
Connect MCP clients to 2,000+ AI models without managing provider API keys.
Connect any AI agent to 1,000+ apps and 27,000+ actions through one remote MCP server (OAuth).
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to discover and execute tools via a secure MCP server with JWT authentication, RBAC, rate limiting, and audit logging.1MIT
- AlicenseCqualityDmaintenanceMCP server that exposes Volcengine OpenAPI as tools, enabling AI agents to interact with Volcengine services like IAM.129 npm1MIT

Ceveto MCP Serverofficial
AlicenseAqualityDmaintenanceEnables AI agents to interact with the Ceveto business management API through MCP, with permission-filtered tools and secure Ed25519 authentication.3MIT- AlicenseNot gradedqualityBmaintenanceEnables AI agents to discover and invoke backend tools over MCP JSON-RPC while enforcing 3-legged OAuth 2.0 identity propagation, role-based access control, and protocol transcoding to REST APIs.1Apache 2.0