Newton MCP Gateway
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ATAI_API_KEY | No | Archetype AI API key. Required when NEWTON_BACKEND=api. | |
| NEWTON_BACKEND | Yes | Backend to use. Set to 'mock' for the built-in mock backend (no credentials needed), or 'api' to use the real Newton API. | |
| ATAI_API_ENDPOINT | No | Archetype AI API endpoint, e.g. https://api.u1.archetypeai.app/v0.5. Used with the real Newton backend. |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| newton_queryB | Ask Newton (text-reasoning model) a natural-language question about physical-world data. Ground it with inline text/JSON events or previously uploaded file_ids. Use system_prompt to force structured JSON output. |
| newton_embed_timeseriesA | Encode a sensor window with the Newton Omega encoder. Input is channel-first: outer list = channels, inner lists = samples. Returns one 768-dim embedding per channel. Leave normalize=false unless cross-window amplitude is irrelevant. |
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 2 tools
The two tools target clearly distinct operations: natural-language querying/reasoning versus timeseries embedding. There is no overlap in purpose or inputs, so an agent can easily select the correct tool.
Both tools use the newton_ prefix and snake_case, which is consistent. However, newton_query lacks the explicit object noun that newton_embed_timeseries includes, a minor deviation from a strict verb_noun pattern.
With only two tools, the surface feels thin for a gateway, falling into the borderline range. Each tool is distinct and earns its place, but the server could likely benefit from additional support tools.
The query tool references previously uploaded file_ids, yet there is no tool to upload, list, or manage files, creating a notable gap. Core query and embedding operations are present, but the grounding workflow is incomplete without file handling.