instagram-personal-mcp
A Model Context Protocol server that wraps
instagrapi so Claude (or any MCP
client) can read, engage, and DM from a personal Instagram account — no
Business/Creator switch, no Meta app review.
⚠️ Unofficial private API. This server uses Instagram's reverse-engineered mobile API (via
instagrapi). It is not affiliated with or endorsed by Meta. Accounts driving private-API traffic can be rate-limited, challenged, or permanently disabled. Use a burner account until you trust your setup, keep activity natural, and don't connect over VPNs / datacenter IPs.
24 tools across auth, profile/read, engagement, and DMs.
Quick start
git clone https://github.com/AleemHaider/instagram-personal-mcp
cd instagram-personal-mcp
python -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"
Drop your creds in a .env:
cp .env.example .env
# edit: IG_USERNAME, IG_PASSWORD
Then run it:
instagram-personal-mcp
The first call (e.g. instagram_session_status or instagram_login) will
authenticate and save a session file to
~/.config/instagram-personal-mcp/session.json. Subsequent runs reuse it.
Connect to Claude Desktop
Edit ~/.config/Claude/claude_desktop_config.json (Linux) /
~/Library/Application Support/Claude/claude_desktop_config.json (macOS):
{
"mcpServers": {
"instagram-personal": {
"command": "instagram-personal-mcp",
"env": {
"IG_USERNAME": "your_username",
"IG_PASSWORD": "your_password"
}
}
}
}
Restart Claude Desktop.
Tools
Auth
| Tool | What it does |
|---|---|
instagram_login |
Log in. Pass verification_code if 2FA is on. |
instagram_logout |
Log out and delete the saved session. |
instagram_session_status |
Report whether a usable session is loaded. |
Profile & read
| Tool | What it does |
|---|---|
instagram_get_my_profile |
Profile of the logged-in account. |
instagram_get_user_profile |
Public profile of another user. |
instagram_search_users |
Search users by keyword. |
instagram_get_user_posts |
Recent posts by a user. |
instagram_get_post |
Details of a single post (URL or media pk). |
instagram_get_post_comments |
Comments on a post. |
instagram_get_post_likers |
Users who liked a post. |
instagram_get_followers |
List a user's followers. |
instagram_get_following |
List who a user follows. |
instagram_get_timeline |
Home feed. |
instagram_get_user_stories |
Active stories from a user. |
Engagement
| Tool | What it does |
|---|---|
instagram_like_post |
Like a post. |
instagram_unlike_post |
Unlike a post. |
instagram_comment_on_post |
Comment on a post. |
instagram_follow_user |
Follow a user. |
instagram_unfollow_user |
Unfollow a user. |
instagram_save_post |
Save a post to your collection. |
instagram_unsave_post |
Remove a post from your saved collection. |
Direct messages
| Tool | What it does |
|---|---|
instagram_list_dm_threads |
List DM threads. |
instagram_get_dm_thread |
Messages in a thread. |
instagram_send_dm |
Send a DM (comma-separated usernames for group). |
2FA flow
- Call
instagram_login(no code) — if 2FA is required you'll get{"error": true, "code": "2FA_REQUIRED", ...}. - Get the code from your authenticator / SMS.
- Call
instagram_loginagain withverification_code="123456".
Errors
Tools return structured errors instead of raising. Look for error: true and a
machine-readable code:
NOT_LOGGED_IN— callinstagram_loginfirst.LOGIN_REQUIRED— saved session was rejected; log in again.2FA_REQUIRED— callinstagram_loginagain withverification_code.CHALLENGE_REQUIRED— Instagram wants a security challenge solved; log in from the IG app / web once to clear it.RATE_LIMITED—PleaseWaitFewMinutesfrom upstream; back off.USER_NOT_FOUND/MEDIA_NOT_FOUND— bad input or removed content.
Development
pip install -e ".[dev]"
pytest
Why a separate project from instagram-mcp?
The sibling instagram-mcp
wraps the official Instagram Graph API — Business/Creator accounts only,
requires a Meta app and tokens, fully ToS-compliant. This project wraps the
unofficial private API for personal accounts and carries the risks above.
They're kept separate so the official one stays clean and reviewable.
License
MIT — see LICENSE.
Metadata
Release files for instagram-personal-mcp 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| instagram_personal_mcp-0.1.0.tar.gz | 150.1 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| instagram_personal_mcp-0.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 159.2 kB
Release files / instagram_personal_mcp-0.1.0.tar.gz
| Download URL | instagram_personal_mcp-0.1.0.tar.gz |
|---|---|
| Size | 150.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
9e9304a23468192d3d4c4314cada683c7aeddd8a863c7ee193db1655213c9d8b
|
|
BLAKE2b-256 checksum How to use checksums |
f0c64da36c045f9c1312ff6306a7cd887b0e11548b747aac4308137dafb7672c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.7
|
Release files / instagram_personal_mcp-0.1.0-py3-none-any.whl
| Download URL | instagram_personal_mcp-0.1.0-py3-none-any.whl |
|---|---|
| Size | 9.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
de438b5640f4a5a9e147697e7f9934d43c6c64a78a82089ce109f1f6c6acd836
|
|
BLAKE2b-256 checksum How to use checksums |
2838937d98b4a974e2bcf3c3cd95ec8bc3421b017c5cdde44f14cf3eb1ff5be6
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.7
|
Security for instagram-personal-mcp 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.