Skip to main content
Glama
Sign In
luizGDpulz

mcp-nvidia-nim

by luizGDpulz
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

nim_analyze_vision

Analyze images, architecture diagrams, screenshots, and wireframes with multimodal models to extract insights and answer visual questions.

Instructions

Analyzes images, architecture diagrams, screenshots, and wireframes using large multimodal models (Llama 3.2 90B Vision or Nemotron Super VL 120B)

Input Schema

NameRequiredDescriptionDefault
modelNoMultimodal model: 'vision' (Llama 3.2 90B Vision) or 'super-vl' (Nemotron Super VL 120B). Default: 'vision'.
promptYesQuestion, instruction, or prompt regarding the visual input.
image_url_or_pathYesImage URL (http/https), local absolute filesystem path (e.g. /path/to/image.png), or base64 data URI.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It names the models but omits whether the call is read-only, what constraints exist on image size/format, latency, cost, or what the response contains — the behavioral context an agent needs to plan a call is largely absent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

One front-loaded sentence with zero repetition or filler. Brevity is a virtue here, though the sentence could have spent its length on usage or behavioral detail instead of the model names.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no annotations and no output schema, the definition is too thin: it says nothing about the return shape (raw text caption? structured analysis?), image constraints, or failure modes, leaving the agent to discover behavior by trial.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%: model options, prompt, and accepted image locators (URL, absolute path, base64 data URI) are all documented in the schema. The description adds no syntax or format detail beyond it, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('analyzes') and concrete resource types (images, architecture diagrams, screenshots, wireframes), plus the underlying models. Clear on its own, but never mentions siblings like nim_extract_document, so an agent can't tell from this text which visual task belongs where.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use, when-not-to-use, or alternative guidance. Siblings include nim_extract_document and nim_review_code, but nothing here says whether to route a screenshot OCR task to this tool or to document extraction.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools