Schema | netherbymultimodal

netherbymultimodal

Describes the environment variables required to run the server.

Name	Required	Description	Default
`NETHERBY_PROVIDER`	No	Provider to use: 'stub' or 'onnx'	stub
`NETHERBY_LOG_LEVEL`	No	Log level: debug, info, warning, or error.	info
`NETHERBY_MAX_PAGES`	No	Reject payloads with more pages.	500
`NETHERBY_MODEL_PATH`	No	Path to the ONNX model. Required when NETHERBY_PROVIDER is 'onnx'.
`NETHERBY_MAX_TEXT_LEN`	No	Reject spans with text longer than this value.	100000
`NETHERBY_MIN_CONTAINMENT`	No	Threshold for assigning spans to layout regions.	0.5
`NETHERBY_MAX_SPANS_PER_PAGE`	No	Reject payloads with more spans per page.	50000
`NETHERBY_ALLOW_PROVIDER_FALLBACK`	No	Degrade to the stub provider if the ONNX model cannot be loaded.	true

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.

Features and capabilities supported by this server

Protocol revision2025-11-25

Capability	Details
`tools`	{}

Functions exposed to the LLM to take actions

Name	Description
fuse_documentA	Fuse layout regions with extracted text spans into ordered, labelled reading blocks. Runs fully offline.

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/J-X0/harrow-risk-multimodal-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server