MCP gateway aggregating upstream MCP servers with OAuth, policies, and audit logging.
Critical gaps across all dimensions. Tool definitions are inferred from file paths and brief descriptions only, no explicit schema registration visible in provided source. Descriptions are minimal (10-50 chars), far below the 194-char baseline for production tools. No parameter schemas, type definitions, or input validation evident. No output schemas documented. Error handling and recovery guidance absent. The server manages upstream MCP aggregation and RBAC but lacks the structured definitions required for reliable LLM tool selection and composition.
Add a new upstream MCP server configuration
Add a new user to the organization
Check OAuth authentication status for an upstream
Establish connection to an upstream MCP server
Create a new role with specified permissions
Delete a role from the organization
Disconnect from an upstream MCP server
Get details for a specific upstream MCP server
No input schemas visible for any tool. Cannot verify parameter types, constraints, or descriptions.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 37 | 2026-07-28+ | v2 |
List default argument configurations for tools
List all roles in the organization
List all tools available from an upstream MCP server
List all configured upstream MCP servers
List all users in the organization
Refresh tool catalog for an upstream MCP server
Remove default argument configuration for a tool
Remove argument constraints for a tool in a role
Remove category default access policy from a role
Revoke tool access from a role
Remove an upstream MCP server configuration
Remove a user from the organization
Rename an existing role
Search audit log entries for compliance and monitoring
Set default argument values for a tool
Set argument constraints for a tool in a role
Configure automatic enablement of new tools for a role
Set default access policy for a tool category in a role
Configure MCP server access for a role
Grant tool access to a role
Configure fallback behavior for tool access in a role
Assign a role to a user
Get connection status of an upstream MCP server
All tool descriptions are under 20 characters (10-50 chars observed). Descriptions lack WHAT the tool does, WHEN to use it, and prerequisites. LLMs cannot reliably select tools without substantive descriptions.
No output schemas documented. LLMs cannot plan downstream tool calls or extract required fields (e.g., upstream_id, role_id, user_id) for chaining. Responses are opaque.
Destructive tools (remove_upstream, remove_user, delete_role) lack confirmation or dry-run support. No error guidance for recovery. Agents can delete resources without safeguards.
Tool definitions are inferred from file paths and brief descriptions only. No explicit tool registration with schemas visible in provided source code.