Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/HasData/instagram-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/hasdata/instagram-mcp/hasdata-instagram)<a href="https://agentmods.dev/rules/hasdata/instagram-mcp/hasdata-instagram"><img src="https://agentmods.dev/badge/rules/hasdata/instagram-mcp/hasdata-instagram/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/hasdata/instagram-mcp/hasdata-instagram"><img src="https://agentmods.dev/badge/rules/hasdata/instagram-mcp/hasdata-instagram.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00015 | $0.00605 |
| Opus 5.5 | $0.00006 | $0.00242 |
| Sonnet 5.5 | $0.00003 | $0.00121 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
hasdata-instagram scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instagram through HasData
Three tools. Two are keyed on handle, the third on the URL of a single post. hasdata_instagram_profile_getInstagramProfile returns the account, and hasdata_instagram_posts_getInstagramPosts returns its feed with limit and nextPageToken.
The profile already embeds latestPosts, so a question about the account and its recent work is one call rather than two.
What a post does not carry
A post holds id, shortcode, caption, type, productType, url, displayUrl, images, dimensionsWidth, dimensionsHeight, ownerUsername, ownerId and hasdataLink. It also carries likesCount, commentsCount, timestamp and publishDate, so the feed alone can rank posts by engagement and filter them by date. Do not spend a call on hasdata_instagram_comments_getInstagramComments to collect numbers the feed already returned; reach for it when the comment thread itself is wanted. mentions and hashtags appear only when the caption has them, taggedUsers lists accounts tagged in the media, and a carousel puts its members in childPosts.
mentions appears on many posts and hashtags on fewer, so both are optional. Parsing the caption yourself finds the same tags, which is the reliable route when coverage matters.
Twelve is the ceiling
One call returns twelve posts. limit above that still returns twelve, so a larger feed comes from following nextPageToken rather than from asking for more. The first page also repeats the twelve the profile already gave you, which makes the profile call the cheaper start.
Public, private and broken
A private account answers with private: true and little else. Branch on that flag before reading anything else, because the rest of the payload is thin by design rather than missing by accident.
A handle that does not resolve comes back with isError true and a 400. Read the error text rather than only the flag, because the same flag carries a 401 for a bad key and MCP error -32602 for a schema violation, and reporting a key problem as a missing account sends the reader after the wrong bug.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago Changed · +5 lines 26c3d5db5689
- 8d ago Changed 5d180316fa90
- 10d ago Changed 4b8c59edc6e9
- 23d ago First seen · 31 lines · 15 tokens per session scan A 24130f249aeb
hasdata-instagram is a cursor rule published in the GitHub repository HasData/instagram-mcp (16 stars, last pushed 3d ago), licensed MIT. It adds 15 tokens to every session and 605 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-23.
Other cursor rules, from other repositories
hasdata-booking
How to pull Booking.com hotel search and property details through the HasData MCP server.
hasdata-zillow
How to pull Zillow listings and property details through the HasData MCP server.
hasdata-indeed
How to pull Indeed job listings and postings through the HasData MCP server.
hasdata-tiktok
How to pull TikTok profiles, post feeds, keyword search and comments through the HasData MCP server.
hasdata-airbnb
How to pull Airbnb stays and listing details through the HasData MCP server.
hasdata-duckduckgo
How to pull DuckDuckGo results and the Search Assist answer through the HasData MCP server.