video-understanding-mcp

by kwacky1

Overview Schema Source Related Servers Discussions Admin

TypeScript

Local

Probe local video

video_probe

Inspect a local media file to extract normalized metadata, using an absolute path within allowed read roots.

Instructions

Inspect a local media file with ffprobe and return normalised metadata. The path must be absolute and inside an allowed read root.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "path": "<path>"
    },
    "name": "video_probe"
  }
}

Input Schema

Name	Required	Description	Default
`path`	Yes	Absolute path to a local media file

Output Schema

Name	Required	Description	Default
`streams`	Yes
`cache_hit`	Yes
`container`	Yes
`duration_ms`	Yes
`input_sha256`	Yes
`schema_version`	Yes
`ffprobe_version`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 11, 2026

TDQS

A3.8/5.0

Behavior3/5

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

No annotations are provided, so the description must stand alone. It does convey a read-only inspection via ffprobe, but it does not explicitly state that the file is unmodified, require specific permissions, or warn about failure modes. It is minimally transparent but not rich.

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

Conciseness5/5

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

Two sentences, each earning its place: the first defines the operation, the second clarifies the precondition. The wording is direct, efficiently front-loaded, and contains no filler.

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

Completeness4/5

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

The tool has an output schema, so the return value is already documented. With only one parameter and clear purpose, the description covers the key constraint (path root). It does not address branch conditions for failure or permission, but it is sufficiently complete for a simple read-only inspection tool.

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

Parameters4/5

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

The schema describes 'path' as an absolute path to a local media file, but the description adds an important constraint: the path must be inside an allowed read root. This goes beyond the schema and adds meaningful semantic guidance for correct invocation.

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

Purpose5/5

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

The description clearly states a specific action (inspect), resource (local media file), method (ffprobe), and output (normalised metadata). This plainly differentiates it from the sibling video_transcribe, which would perform transcription rather than metadata inspection.

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 guidance is given about when to choose this tool over video_transcribe. The description mentions an execution constraint (absolute path, allowed read root) but does not address selection among alternatives or any prerequisite/context beyond that.

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

Deploy Server