Skip to main content
Glama

IvedaAI: Detection

ivedaai_detection

Perform AI detection on images: identify objects, colors, and license plates, run classifiers, and encode images or text with CLIP.

Instructions

IvedaAI API — Detection operations. Response JSON: "status" is the HTTP status code; "truncated"/"timedOut" flag a cut-off response.

GET /api/detection/classifiers — List available classifier

POST /api/detection/classifiers/{classifierName} — Do classification path: classifierName*:string file: provide as {path, filename?, contentType?} — local file to upload as "file" form fields (pass via body): threshold?:number

POST /api/detection/clip/image — Use clip encode image file: provide as {path, filename?, contentType?} — local file to upload as "file"

POST /api/detection/clip/text — Use clip encode text body: array of string

POST /api/detection/colors — Detect colors file: provide as {path, filename?, contentType?} — local file to upload as "file"

POST /api/detection/colors.image — Detect and draw colors file: provide as {path, filename?, contentType?} — local file to upload as "file" form fields (pass via body): label?:boolean

POST /api/detection/objects — Detect objects query: plugins?:string enum:AgeGenderClassifier|CrossCameraTrackingEngine|CrowdDetectionEngine|DwellEngine|ExtraAlertTrigger|FaceGdpr|FaceRecognitionEngine|HumanAttributeEngine, profileId?:integer file: provide as {path, filename?, contentType?} — local file to upload as "file"

POST /api/detection/objects.image — Detect and draw objects query: plugins?:string enum:AgeGenderClassifier|CrossCameraTrackingEngine|CrowdDetectionEngine|DwellEngine|ExtraAlertTrigger|FaceGdpr|FaceRecognitionEngine|HumanAttributeEngine, profileId?:integer, label?:boolean file: provide as {path, filename?, contentType?} — local file to upload as "file"

POST /api/detection/plates — Detect License Plate query: profileId?:integer file: provide as {path, filename?, contentType?} — local file to upload as "file"

POST /api/detection/plates.image — Detect and draw License Plate query: profileId?:integer, label?:boolean file: provide as {path, filename?, contentType?} — local file to upload as "file"

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
bodyNoJSON request body, or form field values when uploading a file.
fileNoLocal file to upload, for operations that accept a file.
pathNoPath parameters, e.g. { "cameraId": 12 }
queryNoQuery string parameters for this operation.
operationYesWhich API operation to call, from the list in this tool's description.
Behavior4/5

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

The description adds behavioral context beyond annotations: it warns that responses include 'status' and may have 'truncated'/'timedOut' flags, and it distinguishes between operations that merely detect and those that 'Detect and draw' (implying image output). This is useful context not present in the annotations.

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?

The description is well-structured as a numbered list of endpoints, making it easy to scan. It front-loads the important response caveat. However, the 'file: provide as {path, filename?, contentType?}' phrase is repeated 6 times, adding verbosity without new information.

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?

For a tool with 10 operations, the description covers all endpoints and their parameters, including query enums and file upload details. It mentions response status flags, but does not provide full return data structures or common error/auth requirements. Given the complexity, it is quite complete, though some details remain absent.

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

Parameters5/5

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

The description significantly enriches the generic schema by specifying which parameters apply to each operation, including classifierName, file, threshold, plugins with a full enum list, profileId, and label. This is essential for correctly invoking operations and goes well beyond the schema's generic 'path'/'query' descriptions.

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 'Detection operations' and enumerates 10 specific endpoints covering classifiers, classification, CLIP encode, colors, objects, and license plates. This provides a specific verb+resource mapping per operation and distinguishes this tool from siblings that focus on other IvedaAI domains.

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

Usage Guidelines3/5

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

The description implies usage when detection-related functionality is needed but gives no explicit guidance on when to use this tool versus alternatives. It does not mention any exclusions or alternative tools, leaving the agent to infer the right context from the operation list.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

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

curl -X GET 'https://glama.ai/api/mcp/v1/servers/WillORepO/ivedaAI-mcp-server'

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