Skip to content

History of three.ws Brain

io.github.nirholas/brain-mcp · Registry status: active

Report data on this entry

Every published change to this entry, most recent first.

Changes
2026-09-08Connection paths (source structure): – → {"packages":[{"registryType":"npm","identifier":"@three-ws/brain-mcp","version":"0.1.3","runtimeHint":"npx","transport":"stdio","environment":[{"name":"THREE_WS_BASE","description":"Base URL of the three.ws API that fronts the LLM router (/api/brain/chat). Override only when self-hosting or targeting a preview deployment.","format":"string","required":false,"secret":false},{"name":"THREE_WS_API_KEY","description":"Optional three.ws API key (sk_live_… / sk_test_…) or OAuth access token, sent as a Bearer token. Required only to use paid first-party flagships (Claude, GPT-5, o3, Grok, Qwen Plus, DeepSeek). Free open-weight tiers (GPT-OSS 120B, NVIDIA NIM models) work with no key. Create one at https://three.ws/dashboard/developers.","format":"string","required":false,"secret":true},{"name":"THREE_WS_TIMEOUT_MS","description":"Per-request timeout in milliseconds. Chat completions stream server-side and are collapsed into a single reply, so this is generous by default to ride out a long flagship answer.","format":"number","required":false,"secret":false}],"additional_arguments_declared":false}],"remotes":[]}
2026-08-26Description (raw): – → List LLM providers and run chat completions through the three.ws multi-provider router.
2026-08-20Declared version: 0.1.2 → 0.1.3
2026-08-20Last changed in the registry (raw): 2026-07-20 → 2026-08-19
2026-08-20First listed in the registry (raw): 2026-07-20 → 2026-08-19
2026-08-20Environment variable descriptions (raw): THREE_WS_API_KEY=Optional three.ws API key (sk_live_… / sk_test_…) or OAuth access token, sent as a Bearer token. Required only to use paid first-party flagships (Claude, GPT-4o, o3, Qwen Plus, DeepSeek). Free open-weight tiers (GPT-OSS 120B, NVIDIA NIM models) work with no key. Create one at https://three.ws/account. · THREE_WS_BASE=Base URL of the three.ws API that fronts the LLM router (/api/brain/chat). Override only when self-hosting or targeting a preview deployment. · THREE_WS_TIMEOUT_MS=Per-request timeout in milliseconds. Chat completions stream server-side and are collapsed into a single reply, so this is generous by default to ride out a long flagship answer. → THREE_WS_API_KEY=Optional three.ws API key (sk_live_… / sk_test_…) or OAuth access token, sent as a Bearer token. Required only to use paid first-party flagships (Claude, GPT-5, o3, Grok, Qwen Plus, DeepSeek). Free open-weight tiers (GPT-OSS 120B, NVIDIA NIM models) work with no key. Create one at https://three.ws/dashboard/developers. · THREE_WS_BASE=Base URL of the three.ws API that fronts the LLM router (/api/brain/chat). Override only when self-hosting or targeting a preview deployment. · THREE_WS_TIMEOUT_MS=Per-request timeout in milliseconds. Chat completions stream server-side and are collapsed into a single reply, so this is generous by default to ride out a long flagship answer.
2026-08-20Package versions (raw): 0.1.2 → 0.1.3
2026-08-16Last changed in the registry (raw): – → 2026-07-20
2026-08-16First listed in the registry (raw): – → 2026-07-20
2026-08-16Registry status message (raw): – → –
2026-08-16Schema version of the raw record (raw): – → https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json
2026-08-16Icon formats (raw): – → image/svg+xml
2026-08-16Environment variable descriptions (raw): – → THREE_WS_API_KEY=Optional three.ws API key (sk_live_… / sk_test_…) or OAuth access token, sent as a Bearer token. Required only to use paid first-party flagships (Claude, GPT-4o, o3, Qwen Plus, DeepSeek). Free open-weight tiers (GPT-OSS 120B, NVIDIA NIM models) work with no key. Create one at https://three.ws/account. · THREE_WS_BASE=Base URL of the three.ws API that fronts the LLM router (/api/brain/chat). Override only when self-hosting or targeting a preview deployment. · THREE_WS_TIMEOUT_MS=Per-request timeout in milliseconds. Chat completions stream server-side and are collapsed into a single reply, so this is generous by default to ride out a long flagship answer.
2026-08-16Environment variable formats (raw): – → number, string
2026-08-16Delivery form (raw): – → package
2026-08-16Remote hosts (raw): – → –
2026-08-16Remote URLs (raw): – → –
2026-08-16Runtime hints (raw): – → npx
2026-08-16Package versions (raw): – → 0.1.2
2026-08-16Package identifiers (raw): – → @three-ws/brain-mcp
2026-08-16Repository subfolder (raw): – → packages/brain-mcp
2026-08-16Repository platform (raw): – → github
2026-08-16Path environment variables (raw): – → –
2026-08-16Required secret headers (raw): – → –
2026-08-06Declared version: – → 0.1.2
2026-08-06Repository URL listed: – → yes
2026-08-06Path argument present: – → no
2026-08-06Execution location: – → local
2026-08-06Required secrets declared: – → no
2026-08-06Package registries (raw): – → npm
2026-08-06Repository (raw): – → https://github.com/nirholas/three.ws
2026-08-06Path arguments (raw): – → –
2026-08-06Transports (raw): – → stdio
2026-08-06Required secret variables (raw): – → –
2026-08-06Environment variables (raw): – → THREE_WS_BASE, THREE_WS_API_KEY, THREE_WS_TIMEOUT_MS

tracevero · https://tracevero.com/mcp/io-github-nirholas-brain-mcp/aenderungen