Instagram Post Image Analyzer

Instagram

Operated by Sourcelane✓ verified

Image analysis connector for Instagram content that applies a vision model to profiles or specified posts to extract post metadata and rich visual intelligence. For each post it produces a concise visual description, a content-category label, lists of detected objects and visible brands/logos, on-image text extracted via OCR, a brand-safety classification, and suggested hashtags; it also collects basic post metadata such as identifiers, URL, media type, caption, engagement metrics, thumbnail, and author. Technical capabilities include configurable vision-model inference, object detection, logo/brand recognition, optical character recognition on images, content categorization, brand-safety scoring, and hashtag suggestion generated from image content and context.

Verified Sep 28, 12:10 AM

$0.018

per result

Up to 55 per call. Only pay for results returned; failed calls are refunded.

What people use it for

Auto tag and categorize a creator's or competitor's feed
Detect product placements and brand logos across posts
Build searchable image catalogs from Instagram content
Brand safety screening before a partnership
Generate hashtag ideas from real post imagery

Trust & reliability

7d uptime trend

Window	Uptime	Success rate	p50	p95
24h	—	—	—	—
7d	—	—	—	—
30d	—	—	—	—

Calling contract

Call it through Sourcelane's gateway or MCP server. We run the connector, apply your agent's spend guardrails, and bill only the results returned.

Call it via Sourcelane

curl -X POST https://cool-puffin-608.convex.site/v1/call \
  -H "Authorization: Bearer sl_live_your_agent_key" \
  -H "Content-Type: application/json" \
  -d '{"listing":"instagram-post-image-analyzer","params":{"username":"natgeo","maxPosts":5},"maxResults":10}'

Request params

Field	Type	Required	Description
`username`	string	optional	Instagram username whose recent posts to analyze (with or without @). Leave empty if you provide Post URLs instead.
`postUrls`	array	optional	Specific Instagram post or Reel URLs or shortcodes to analyze. If set, these are used instead of the username's recent posts.
`maxPosts`	integer	optional	Maximum number of posts to analyze when using a username. 0 means no cap. Capped at 55 per call.
`model`	string	optional	Vision model used to analyze each image. A fast, low cost model is recommended.

Each result contains

Field	Type	Description
`postId`	string	Post Id
`shortcode`	string	Shortcode
`postUrl`	string	Post Url
`mediaType`	string	Media Type
`caption`	string	Caption
`likeCount`	integer	Like Count
`commentCount`	integer	Comment Count
`thumbnailUrl`	string	Thumbnail Url
`authorUsername`	string	Author Username
`description`	string	Description
`category`	string	Category
`objects`	array	Objects
`brands`	array	—
`onImageText`	string	—
`brandSafety`	string	—
`suggestedHashtags`	array	—

Use Instagram Post Image Analyzer from Claude, ChatGPT or Cursor

Pick your tool and connect in under a minute. Then just ask — for example: “Pull the last 20 posts from @natgeo and tell me which formats get the most engagement.”

Connect Claude

Web, desktop and mobile. Paste one URL.

1Copy your personal connector URL
2In Claude open Settings → Connectors → Add custom connector
3Paste the URL and click Add — done

Manual setup (config files, REST, Python) +

Claude Code

Adds the Sourcelane MCP server with your key as a header.

terminal

claude mcp add --transport http sourcelane https://cool-puffin-608.convex.site/mcp \
  --header "Authorization: Bearer sl_live_your_agent_key"

Claude Desktop (config file)

Alternative to the connector URL: add to claude_desktop_config.json, then restart Claude.

claude_desktop_config.json

{
  "mcpServers": {
    "sourcelane": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://cool-puffin-608.convex.site/mcp",
        "--header",
        "Authorization:${AUTH_HEADER}"
      ],
      "env": {
        "AUTH_HEADER": "Bearer sl_live_your_agent_key"
      }
    }
  }
}

Cursor & Windsurf

Add to ~/.cursor/mcp.json (or Windsurf's mcp_config.json).

mcp.json

{
  "mcpServers": {
    "sourcelane": {
      "url": "https://cool-puffin-608.convex.site/mcp",
      "headers": {
        "Authorization": "Bearer sl_live_your_agent_key"
      }
    }
  }
}

VS Code

Save as .vscode/mcp.json. VS Code prompts for your key once.

.vscode/mcp.json

{
  "servers": {
    "sourcelane": {
      "type": "http",
      "url": "https://cool-puffin-608.convex.site/mcp",
      "headers": {
        "Authorization": "Bearer ${input:sourcelane-key}"
      }
    }
  },
  "inputs": [
    {
      "type": "promptString",
      "id": "sourcelane-key",
      "description": "Sourcelane agent key",
      "password": true
    }
  ]
}

ChatGPT Custom GPT (Actions)

Create a GPT → Actions → Import from URL, then Authentication: API Key, Bearer.

OpenAPI schema URL

https://sourcelane-amber.vercel.app/openapi.json

REST

One POST. Pass maxResults to cap cost.

curl

curl -X POST https://cool-puffin-608.convex.site/v1/call \
  -H "Authorization: Bearer sl_live_your_agent_key" \
  -H "Content-Type: application/json" \
  -d '{"listing":"instagram-post-image-analyzer","params":{"username":"natgeo","maxPosts":5},"maxResults":10}'

Python, LangChain, CrewAI, OpenAI Agents SDK…

Wrap the REST call as a tool, or point an MCP client at the endpoint.

python

import requests

res = requests.post(
    "https://cool-puffin-608.convex.site/v1/call",
    headers={"Authorization": "Bearer sl_live_your_agent_key"},
    json={
        "listing": "instagram-post-image-analyzer",
        "params": {"username":"natgeo","maxPosts":5},
        "maxResults": 10,
    },
    timeout=300,
)
body = res.json()
print(body["receipt"]["chargedMicros"], "micro-USD for", body["receipt"]["results"], "results")
print(body["data"])

Reviews

—

0 reviews

Leave a review

Loading reviews…