@bsvkey/inference-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| BSVKEY_API_KEY | No | channelId:channelSecret for a funded channel. Optional; can also be passed per call as apiKey. | |
| BSVKEY_BASE_URL | No | Gateway base URL (set to a self-hosted deployment if you run your own). | https://inference.bsvkey.com/v1 |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_modelsA | List the models this BSV inference gateway sells, with LIVE retail price (satoshis per 1,000 tokens) at the current BSV/USD rate. No key needed. Call first to choose a model. |
| inferA | Run one metered inference (OpenAI-compatible), paid per token in BSV from your prepaid channel. Returns the completion plus a receipt: satoshis charged, model routed to, and remaining balance. Requires a funded channel key (apiKey or BSVKEY_API_KEY). |
| channel_balanceA | Check a prepaid channel’s remaining BSV balance, spend, and request count. |
| open_channelA | Explains how to open + fund a prepaid channel. Funding is a real BSV payment signed by a wallet, so it is done once at the website; you then paste the returned channel key here (or set BSVKEY_API_KEY). |
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 4 tools
Each tool has a clearly distinct purpose: listing models, running inference, checking balance, and explaining channel setup. There is no meaningful overlap or ambiguity between them.
list_models and open_channel follow a verb_noun pattern, but infer is a bare verb and channel_balance is a noun phrase without an action verb. The names are readable and predictable in context, but the conventions are mixed.
Four tools is well-scoped for a paid inference gateway: discovery, usage, balance checking, and onboarding. Each tool serves a distinct and necessary step in the core workflow.
The core loop of choosing a model, running inference, checking balance, and funding/opening a channel is covered. Minor gaps like detailed transaction history or channel closure are absent, but agents can accomplish the primary purpose without dead ends.