Model Relay documentation

Setup

  1. Open Connections, sign in and add at least one provider API key.
  2. Add the connector in Muse. The endpoint is https://relay.svyat.site/mcp.
  3. On the consent page, keep Allow sending prompts on for full use, or turn it off for read-only access.

Authentication

OAuth 2.1 authorization code with PKCE (S256) and dynamic client registration. Metadata: https://relay.svyat.site/.well-known/oauth-authorization-server and https://relay.svyat.site/.well-known/oauth-protected-resource/mcp. Access tokens last one hour, refresh tokens rotate and last 90 days, and tokens are valid only for this MCP endpoint.

ScopeAllows
models:readRead tools only. This is the read-only connection.
models:invokeSending prompts to models.

Tools

ToolClassScopeInputsReturnsSide effects
list_modelsReadmodels:readprovider, search (both optional)Up to 100 model references with name and access method, the total count and whether the list was cut.None. Asks each connected provider for its model list, which providers do not bill.
usage_reportReadmodels:readdays, 1 to 365 (default 30)Calls, tokens and estimated cost per access method.None.
account_statusReadmodels:readNonePlan, price, limits, connected providers and the management link.None.
ask_modelWritemodels:invokemodel, prompt, context, system, max_tokens, viaAnswer, model, stop reason and token usage.Sends the text to the chosen provider. The provider may charge the user's account.
compare_modelsWritemodels:invokemodels (2 to 4), prompt, context, system, max_tokensOne answer or error per model.Sends the text to every chosen provider. Each may charge the user's account.
route_taskWritemodels:invoketask_kind (code, long_document, quick, general), prompt, contextAnswer, the model used and token usage.Sends the text to the selected provider. The provider may charge the user's account.

No tool is a sensitive write: none buys anything, publishes, or sends anything to another person.

Model references look like claude:claude-sonnet-5-5, openai:gpt-6.1-sol, gemini:gemini-4-argon or openrouter:openrouter/auto. Use list_models for the ones your keys can reach.

Status and failures

Model calls finish within the request. stop_reason says why an answer ended. A call that returns an error produced no answer. Retrying sends the prompt again and may be billed again. In compare_models, one failed model does not hide the others.

Errors

Failures are tool errors with the text code: message.

CodeMeaning
no_access_for_providerNo key is connected for that provider. Add one at /connect.
provider_auth_failedThe provider rejected the stored key. Replace it at /connect.
provider_limit_reachedThe provider's rate or spending limit was reached. It is not worked around.
provider_errorThe provider failed or could not be reached. Nothing was returned.
unknown_modelThe model reference is not valid. Call list_models.
rate_limitedThe per-user limit was exceeded. Retry after a minute.
plan_limitThe daily call limit of the plan was reached.
read_only_connectionThis connection was granted read-only access.
unauthorizedThe access token is missing or invalid. Reconnect.

Limits

Requirements

A Google account and an API key from Anthropic, OpenAI, Google AI Studio or OpenRouter. Model and regional availability follow your provider account.

Home · Documentation · Connections · Privacy · Terms · support@svyat.site