npm:mcp-instagram-dm

Item: npm:mcp-instagram-dm
Rating: 74
Author: wmcp.sh

https://www.npmjs.com/package/mcp-instagram-dm

74/100 · MCP Trust Grade · checked 4h ago · MCP 2.1.1

What it offers — 15 tools · AI & ML

instagram_get_inbox

List recent Instagram DM conversations

instagram_get_thread

Get messages from a specific DM conversation. Automatically paginates when limit > 20 (e.g. limit=500 fetches 500 messages at once).

instagram_search_inbox

Search inbox by username or name (scans all pages)

instagram_send_message

Send a text message in an Instagram DM thread

instagram_send_link

Share a link in an Instagram DM thread

instagram_like_message

React to a message with an emoji (default: heart)

instagram_unsend_message

Unsend a message you sent (your own messages only)

instagram_mark_seen

Mark a conversation as read

instagram_get_pending

List pending (unapproved) DM requests

instagram_approve_pending

Approve a pending DM request

instagram_user_info

Get a user

instagram_search_users

Search Instagram users (useful for finding users to message)

instagram_create_thread

Start a new DM conversation by sending a message to one or more users

instagram_search_messages

Search for messages containing specific text within a DM thread

instagram_thread_info

Get conversation details: participants, group name, mute status, and more

Spec / packaging20%100

✓ depends on an MCP SDK
✓ declares a bin entry (runnable server)
✓ 15 tool(s) detected in source

Security (OWASP MCP)30%25

⚠ references sensitive file paths / env secrets
scanned 3 source files

Maintenance / popularity20%92

published within 90 days
2 published versions

Tool hygiene15%95

✓ ships TypeScript types
1 runtime deps

Transparency / provenance15%90

✓ public repository linked
✓ MIT license
18 weekly downloads

Findings

WARNMCP08 References sensitive file paths / environment secrets.

INFO Static analysis of npm package mcp-instagram-dm@2.1.1 (stdio server — no remote endpoint). Reliability/behavioral signals require running it; not measured.

Grade another server

We re-grade npm:mcp-instagram-dm on a schedule and alert your Slack/webhook the moment its tools change or its grade drops — rug-pull insurance for the connection.

Share this report card

A 1200×630 card with the grade + audit — drop it in a post, Slack, or your repo.

MCP Trust report card — npm:mcp-instagram-dm grade C

Share on X Open card image

https://wmcp.sh/mcp/grade/npm%3Amcp-instagram-dm

Embed this grade

A live badge — it re-verifies itself and shows current stability. Static scorecards can't. Paste it in your README or site to show users you're independently audited.

Markdown (for your README)

[![MCP Trust Grade C](https://wmcp.sh/mcp/grade/npm%3Amcp-instagram-dm/badge.svg)](https://wmcp.sh/mcp/grade/npm%3Amcp-instagram-dm)

HTML

<a href="https://wmcp.sh/mcp/grade/npm%3Amcp-instagram-dm"><img src="https://wmcp.sh/mcp/grade/npm%3Amcp-instagram-dm/badge.svg" alt="MCP Trust Grade C · wmcp.sh"></a>

Agents: check this before connecting

Add the wmcp.sh trust oracle as an MCP server and call grade_mcp_server / check_mcp_drift in your agent's pre-connection gate:

https://wmcp.sh/mcp/trust

How this grade is computed. An open, independent rubric — Spec conformance (20%), Security mapped to the OWASP MCP Top 10 (30%), Reliability (20%), Tool hygiene (15%), Transparency (15%) — run by connecting to the server and inspecting its real MCP surface. The grade is free and identical whether or not the operator pays. v1 uses static + spec signals from a single connection; continuous uptime, real latency, and annotation-truthing (declared readOnly vs observed behavior) layer on via the wmcp.sh proxy.