dev.verimand/mcp-authority-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| verimand.resolveC | Determine whether a trusted registered agent is currently authorized for a specific action. Calling this tool does not execute the protected action. |
| verimand.explainA | Explain a deterministic VAGP authority decision or permit. Informational only; it cannot create or modify authority. |
| verimand.get_authorityC | Return current bounded authority relevant to a trusted registered agent/action. Read-only. |
| verimand.get_mandateB | Retrieve server-side trusted mandate information. Read-only. |
| verimand.get_agent_dnaB | Return trusted Agent DNA state and fingerprint information from server-side trusted state. Read-only. |
| verimand.verify_permitB | Verify an existing VAGP execution permit against current authority evidence. Does not execute protected actions. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Each tool has a clearly distinct purpose: resolve checks authorization, explain provides reasoning, get_authority retrieves current bounded authority, get_mandate retrieves mandate info, get_agent_dna retrieves agent state, and verify_permit validates a specific permit. There is minimal overlap; even resolve and verify_permit differ in that resolve is action-based while verify_permit is permit-based, and descriptions make this explicit.
All tool names follow a consistent pattern: lowercase snake_case, starting with a verb (resolve, explain, get_*, verify_*). The get_* prefix is used for all read operations, and verify_* for validation. This consistency makes the tool set predictable and easy to navigate.
With 6 tools, the server is well-scoped for a read-only authority and permit service. Each tool addresses a distinct aspect of authority/verification without redundancy, and the count is within the ideal range for focused MCP servers.
The tool surface covers the core operations for querying authority: resolve, explain, get_authority, get_mandate, get_agent_dna, and verify_permit. It is read-only by design, so no create/update/delete tools are expected. The only minor gap is a lack of a list-type tool to enumerate all authorities or mandates, but this is not critical for the stated purpose.