@0n1x/rhinogent
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ONYX_BASE | No | Base URL for the 0n1x backend (default is the public 0n1x endpoint) |
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 |
|---|---|
| rhinogent_identityA | Resolve a self-custody Base/EVM address into its signed Rhinogent identity (callsign, did:pkh, Rhinogent-Verified credential). Keys stay with the agent; this reads the public identity. |
| rhinogent_verify_counterpartyA | Verify a merchant/domain/counterparty BEFORE an agent pays or trusts it. Returns a signed verdict grounded in facts (domain age, brand match, TLS), not opinion. |
| rhinogent_mandateB | Confirm a proposed action/spend is within the agent's granted mandate (amount, recipient, scope). Returns IN_SCOPE / OUT_OF_SCOPE, signed. |
| rhinogent_mint_identityA | Onboard a fresh self-custody agent: returns a signed identity card (callsign, did:pkh, Rhinogent-Verified credential) for a newly-generated Base address. The Rhinogent wallet generates the key client-side; this issues the public signed card. |
| rhinogent_sign_factA | Get an Ed25519-signed attestation of a verifiable FACT (e.g. an outcome, a price, a merchant detail) — signed reality the agent can hand a counterparty, not an opinion. |
| rhinogent_get_reputationA | Read an agent's intelligent, un-gameable reputation — proper-scoring accuracy (Brier) + stake-weighting + behavioral consistency, built on signed verified outcomes. This is what makes a Rhinogent identity worth trusting vs an empty wallet. |
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 targets a distinct function: identity creation vs resolution, reputation reading, mandate checking, fact signing, and counterparty verification. No overlap in purpose or ambiguity.
All tools share the 'rhinogent_' prefix and use snake_case, but naming pattern is mixed: some use action verbs (get, mint, sign, verify) while others are nouns (identity, mandate). Still clear and predictable.
With 6 tools, the server covers core agent identity and trust operations without being over- or under-scoped. Each tool serves a clear, necessary purpose.
Covers create/read for identity, read for reputation, and verification actions. Minor gaps: no update/delete for identity, no mandate creation or outcome submission tools, but these may be handled externally.