Trust OS MCP Server
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TRUSTOS_API_KEY | Yes | Your Trust OS API key | |
| TRUSTOS_BASE_URL | No | Override API base URL (default: Trust OS gateway) |
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 |
|---|---|
| verify_decisionB | Verify a high-impact decision before execution using Trust OS. |
| create_decisionA | Create and verify a decision via the Trust OS Decision API. Returns decision_id, recommendation, risk assessment, proof_hash, and a trace_url for Dashboard inspection. |
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 2 tools
The two tools have distinct primary purposes—create_decision creates a new decision while verify_decision checks an existing one—but create_decision also includes verification, creating slight overlap. Descriptions are clear enough to guide correct selection in most cases.
Both tools follow the consistent verb_noun pattern: create_decision and verify_decision. The naming is uniform, predictable, and easy to extend.
With only two tools, the server feels thin for its domain, though the narrow scope may justify it. This is borderline and could benefit from additional tools to round out the functionality.
The server covers creation and verification but lacks essential operations like retrieving, listing, or updating decisions. This is a significant gap because agents cannot reference or manage existing decisions beyond their initial creation, making the surface incomplete for typical workflows.