Schema | spiderswitch

spiderswitch

Describes the environment variables required to run the server.

Name	Required	Description
`COHERE_API_KEY`	No	API key for Cohere provider.
`GEMINI_API_KEY`	No	API key for Google provider (alternative: GOOGLE_API_KEY).
`GOOGLE_API_KEY`	No	API key for Google provider (alternative: GEMINI_API_KEY).
`OPENAI_API_KEY`	No	API key for OpenAI provider.
`MISTRAL_API_KEY`	No	API key for Mistral provider.
`AI_PROTOCOL_PATH`	No	Path to the ai-protocol directory (auto-detected if not set).
`DEEPSEEK_API_KEY`	No	API key for DeepSeek provider.
`AI_HTTP_TRUST_ENV`	No	Set to 1 to forward standard proxy env vars to ai-lib HTTP client.
`ANTHROPIC_API_KEY`	No	API key for Anthropic provider.
`SPIDERSWITCH_SYNC_DIST`	No	Disable dist sync when explicitly invoked (default: enabled).
`AI_PROTOCOL_DIST_BASE_URL`	No	Override raw dist source (default official GitHub raw URL).
`SPIDERSWITCH_SYNC_ON_INIT`	No	Enable dist sync during runtime initialization (default: disabled).
`AI_PROTOCOL_DIST_API_BASE_URL`	No	Override GitHub API listing source for models/providers dist json.
`SPIDERSWITCH_LIST_CACHE_TTL_SEC`	No	TTL for list_models cache (default: 5).
`SPIDERSWITCH_STATUS_CACHE_TTL_SEC`	No	TTL for get_status cache (default: 2).

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.

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

This server cannot be deployed

ActivityStale

ResponsivenessUnresponsive