Instagram

Official33 toolsLive

by mcp-dir

Instagram for AI agents: publish, read comments and DMs, insights, and engage from your account.

io.github.mcp-dir/instagram-mcp (MCP)

This MCP server exposes an Instagram integration for AI agents. It uses the official API to publish content, read and reply to comments, send and receive direct messages, and retrieve profile and media insights for a connected Instagram account. It supports account connection via Business/Creator credentials or username/password (with 2FA).

🛠️ Key Features

Publish photos, videos, carousels, Reels, and Stories
Read and reply to comments
Talk in DMs
Pull profile and media insights
Advanced plan: like posts, follow/unfollow, list and view stories
Advanced plan: start a DM conversation
Connect in 2 clicks (Business or Creator) or via username/password
2FA supported

🚀 Use Cases

Publish Instagram media from AI agents
Manage comment threads and DM conversations
Monitor account and media performance via insights

⚡ Developer Benefits

Single integration for publishing, engagement, and insights through the official API
Account connection options suitable for different workflows

⚠️ Limitations

Additional engagement actions (likes/follows/story viewing/DM initiation) depend on the Advanced plan
Source data does not list the specific 33 tools or their exact parameters

Captured live from the server via tools/list.

instagram_actions_list_accounts

List the Instagram accounts connected to this install — id, username, label.

Parameters1

account

string

optional

Raw schema

{
  "type": "object",
  "properties": {
    "account": {
      "type": "string"
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

instagram_actions_like

Like one or more Instagram posts, addressed by post URL or shortcode (NOT the numeric media id the official API returns). Returns a job_id; poll instagram_actions_get_job_status.

Parameters2

posts	array	required
account	string	optional

Raw schema

{
  "type": "object",
  "properties": {
    "posts": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "account": {
      "type": "string"
    }
  },
  "required": [
    "posts"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

instagram_actions_list_comments

List the comments on a post, addressed by URL or shortcode. Returns each comment_id in the form that instagram_actions_like_comment accepts. The official API returns a DIFFERENT id that is not accepted there. Returns a job_id; poll instagram_actions_get_job_status.

Parameters2

posts	array	required
account	string	optional

Raw schema

{
  "type": "object",
  "properties": {
    "posts": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "account": {
      "type": "string"
    }
  },
  "required": [
    "posts"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

instagram_actions_like_comment

Like one or more comments. Each comment_id MUST come from instagram_actions_list_comments. The id returned by the official instagram_get_ig_media_comments belongs to a different namespace and is rejected. Returns a job_id; poll instagram_actions_get_job_status.

Parameters2

comment_ids	array	required
account	string	optional

Raw schema

{
  "type": "object",
  "properties": {
    "comment_ids": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "account": {
      "type": "string"
    }
  },
  "required": [
    "comment_ids"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

instagram_actions_follow

Follow one or more Instagram users by @username. Returns a job_id.

Parameters2

targets	array	required
account	string	optional

Raw schema

{
  "type": "object",
  "properties": {
    "targets": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "account": {
      "type": "string"
    }
  },
  "required": [
    "targets"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

instagram_actions_unfollow

Unfollow one or more Instagram users by @username. Returns a job_id.

Parameters2

targets	array	required
account	string	optional

Raw schema

{
  "type": "object",
  "properties": {
    "targets": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "account": {
      "type": "string"
    }
  },
  "required": [
    "targets"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

instagram_actions_list_stories

List a specific user's currently available stories (read-only, does not mark as seen). Returns a job_id (or the result inline when wait=true).

Parameters3

target	string	required
wait	boolean	optional
account	string	optional

Raw schema

{
  "type": "object",
  "properties": {
    "target": {
      "type": "string"
    },
    "wait": {
      "type": "boolean"
    },
    "account": {
      "type": "string"
    }
  },
  "required": [
    "target"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

instagram_actions_view_story

Watch (mark as seen) the stories of one or more profiles. Omit `targets` to watch the home tray. Returns a job_id.

Parameters2

targets	array	optional
account	string	optional

Raw schema

{
  "type": "object",
  "properties": {
    "targets": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "account": {
      "type": "string"
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

instagram_actions_send_message

Send the FIRST direct message to someone who has never messaged this account (the official API cannot do this). One recipient per call, low daily cap. Returns a job_id.

Parameters4

target	string	required
text	string	required
dry_run	boolean	optional
account	string	optional

Raw schema

{
  "type": "object",
  "properties": {
    "target": {
      "type": "string"
    },
    "text": {
      "type": "string"
    },
    "dry_run": {
      "type": "boolean"
    },
    "account": {
      "type": "string"
    }
  },
  "required": [
    "target",
    "text"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

instagram_actions_get_job_status

Get the status/progress/result of a previously started action by its job_id. Bulk support: accepts job_ids for batched execution.

Parameters3

job_id	string	required
account	string	optional
job_ids	array	optional

Raw schema

{
  "type": "object",
  "properties": {
    "job_id": {
      "type": "string"
    },
    "account": {
      "type": "string"
    },
    "job_ids": {
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  },
  "required": [
    "job_id"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

instagram_actions_list_jobs

List recent action jobs for the connected account, optionally filtered by status.

Parameters2

status	string	optional
account	string	optional

Raw schema

{
  "type": "object",
  "properties": {
    "status": {
      "type": "string",
      "enum": [
        "running",
        "completed",
        "failed",
        "queued"
      ]
    },
    "account": {
      "type": "string"
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

instagram_get_user_info

Get Instagram Business Account info including profile details and statistics. Use "me" to query your own authenticated account, or provide the numeric Business Account ID of an account you manage. NOTE: followers_count and follows_count are returned for your own profile (ig_user_id="me"). For other accounts, follower/… Bulk support: accepts ig_user_ids for batched execution.

Parameters4

ig_user_id	string	optional
graph_api_version	string	optional
account	string	optional
ig_user_ids	array	optional

Raw schema

{
  "type": "object",
  "properties": {
    "ig_user_id": {
      "type": "string"
    },
    "graph_api_version": {
      "type": "string"
    },
    "account": {
      "type": "string"
    },
    "ig_user_ids": {
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

instagram_get_ig_user_media

Get Instagram user's media collection (posts, photos, videos, reels, carousels). Use when you need to retrieve all media published by an Instagram Business or Creator account with support for pagination and time-based filtering. Bulk support: accepts ig_user_ids, auto_resolve_fb_page_ids for batched execution.

Parameters12

after	string	optional
limit	number	optional
since	number	optional
until	number	optional
before	string	optional
fields	string	optional
ig_user_id	string	optional
graph_api_version	string	optional
auto_resolve_fb_page_id	boolean	optional
account	string	optional
ig_user_ids	array	optional
auto_resolve_fb_page_ids	array	optional

Raw schema

{
  "type": "object",
  "properties": {
    "after": {
      "type": "string"
    },
    "limit": {
      "type": "number"
    },
    "since": {
      "type": "number"
    },
    "until": {
      "type": "number"
    },
    "before": {
      "type": "string"
    },
    "fields": {
      "type": "string"
    },
    "ig_user_id": {
      "type": "string"
    },
    "graph_api_version": {
      "type": "string"
    },
    "auto_resolve_fb_page_id": {
      "type": "boolean"
    },
    "account": {
      "type": "string"
    },
    "ig_user_ids": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "auto_resolve_fb_page_ids": {
      "type": "array",
      "items": {
        "type": "boolean"
      }
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

instagram_get_ig_media

Get a published Instagram Media object (photo, video, story, reel, or carousel). Use when you need to retrieve detailed information about a specific Instagram post including engagement metrics, caption, media URLs, and metadata. NOTE: This action is for published media only. For unpublished container IDs (from INSTAGR… Bulk support: accepts ig_media_ids for batched execution.

Parameters5

fields	string	optional
ig_media_id	string	required
graph_api_version	string	optional
account	string	optional
ig_media_ids	array	optional

Raw schema

{
  "type": "object",
  "properties": {
    "fields": {
      "type": "string"
    },
    "ig_media_id": {
      "type": "string"
    },
    "graph_api_version": {
      "type": "string"
    },
    "account": {
      "type": "string"
    },
    "ig_media_ids": {
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  },
  "required": [
    "ig_media_id"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

instagram_get_ig_media_comments

Tool to retrieve comments on an Instagram media object. Use when you need to fetch comments from a specific Instagram post, photo, video, or carousel owned by the connected Business/Creator account. Supports cursor-based pagination for navigating through large comment lists. An empty data array in the response indicat… Bulk support: accepts ig_media_ids for batched execution.

Parameters8

after	string	optional
limit	number	optional
before	string	optional
fields	string	optional
ig_media_id	string	required
graph_api_version	string	optional
account	string	optional
ig_media_ids	array	optional

Raw schema

{
  "type": "object",
  "properties": {
    "after": {
      "type": "string"
    },
    "limit": {
      "type": "number"
    },
    "before": {
      "type": "string"
    },
    "fields": {
      "type": "string"
    },
    "ig_media_id": {
      "type": "string"
    },
    "graph_api_version": {
      "type": "string"
    },
    "account": {
      "type": "string"
    },
    "ig_media_ids": {
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  },
  "required": [
    "ig_media_id"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

instagram_get_ig_media_insights

Tool to get insights and metrics for Instagram media objects (photos, videos, reels, carousel albums). Use when you need to retrieve performance data such as views, reach, likes, comments, saves, and shares for specific media. Note: Insights data is only available for media published within the last 2 years, and the a… Bulk support: accepts ig_media_ids for batched execution.

Parameters7

metric	array	required
period	string	optional
breakdown	string	optional
ig_media_id	string	required
graph_api_version	string	optional
account	string	optional
ig_media_ids	array	optional

Raw schema

{
  "type": "object",
  "properties": {
    "metric": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "period": {
      "type": "string"
    },
    "breakdown": {
      "type": "string",
      "enum": [
        "action_type",
        "story_navigation_action_type"
      ]
    },
    "ig_media_id": {
      "type": "string"
    },
    "graph_api_version": {
      "type": "string"
    },
    "account": {
      "type": "string"
    },
    "ig_media_ids": {
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  },
  "required": [
    "metric",
    "ig_media_id"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

instagram_get_user_insights

Get Instagram account-level insights and analytics (profile views, reach, follower count, etc.). Requires a Business or Creator account; personal accounts are not supported. Returned timestamps are in UTC. metric_type (time_series or total_value): When set to total_value, the API returns a total_value object instead o… Bulk support: accepts ig_user_ids for batched execution.

Parameters11

since	number	optional
until	number	optional
metric	array	optional
period	string	optional
breakdown	string	optional
timeframe	string	optional
ig_user_id	string	optional
metric_type	string	optional
graph_api_version	string	optional
account	string	optional
ig_user_ids	array	optional

Raw schema

{
  "type": "object",
  "properties": {
    "since": {
      "type": "number"
    },
    "until": {
      "type": "number"
    },
    "metric": {
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "reach",
          "follower_count",
          "online_followers",
          "accounts_engaged",
          "total_interactions",
          "likes",
          "comments",
          "shares",
          "saves",
          "replies",
          "follows_and_unfollows",
          "profile_links_taps",
          "views",
          "profile_views",
          "website_clicks",
          "engaged_audience_demographics",
          "reached_audience_demographics",
          "follower_demographics",
          "reposts",
          "threads_likes",
          "threads_replies",
          "threads_followers",
          "threads_follower_demographics",
          "threads_views",
          "threads_clicks",
          "threads_reposts",
          "quotes",
          "content_views"
        ]
      }
    },
    "period": {
      "type": "string",
      "enum": [
        "day",
        "lifetime"
      ]
    },
    "breakdown": {
      "type": "string"
    },
    "timeframe": {
      "type": "string",
      "enum": [
        "this_month",
        "this_week"
      ]
    },
    "ig_user_id": {
      "type": "string"
    },
    "metric_type": {
      "type": "string"
    },
    "graph_api_version": {
      "type": "string"
    },
    "account": {
      "type": "string"
    },
    "ig_user_ids": {
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

instagram_post_ig_user_media

Tool to create a media container for Instagram posts. Use this to create a container for images, videos, Reels, or carousels. This is the first step in Instagram's two-step publishing process - after creating the container, use the media_publish endpoint to publish it. Bulk support: accepts ig_user_ids, location_ids for batched execution.

Parameters20

caption	string	optional
alt_text	string	optional
children	array	optional
cover_url	string	optional
image_url	string	optional
user_tags	array	optional
video_url	string	optional
audio_name	string	optional
ig_user_id	string	optional
image_file	object	optional
media_type	string	optional
video_file	object	optional
location_id	string	optional
thumb_offset	number	optional
share_to_feed	boolean	optional
is_carousel_item	boolean	optional
graph_api_version	string	optional
account	string	optional
ig_user_ids	array	optional
location_ids	array	optional

Raw schema

{
  "type": "object",
  "properties": {
    "caption": {
      "type": "string"
    },
    "alt_text": {
      "type": "string"
    },
    "children": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "cover_url": {
      "type": "string"
    },
    "image_url": {
      "type": "string"
    },
    "user_tags": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "x": {
            "type": "number"
          },
          "y": {
            "type": "number"
          },
          "username": {
            "type": "string"
          }
        },
        "required": [
          "username"
        ]
      }
    },
    "video_url": {
      "type": "string"
    },
    "audio_name": {
      "type": "string"
    },
    "ig_user_id": {
      "type": "string"
    },
    "image_file": {
      "type": "object",
      "properties": {
        "name": {
          "type": "string"
        },
        "s3key": {
          "type": "string"
        },
        "mimetype": {
          "type": "string"
        }
      },
      "required": [
        "name",
        "s3key",
        "mimetype"
      ]
    },
    "media_type": {
      "type": "string",
      "enum": [
        "REELS",
        "CAROUSEL",
        "STORIES"
      ]
    },
    "video_file": {
      "type": "object",
      "properties": {
        "name": {
          "type": "string"
        },
        "s3key": {
          "type": "string"
        },
        "mimetype": {
          "type": "string"
        }
      },
      "required": [
        "name",
        "s3key",
        "mimetype"
      ]
    },
    "location_id": {
      "type": "string"
    },
    "thumb_offset": {
      "type": "number"
    },
    "share_to_feed": {
      "type": "boolean"
    },
    "is_carousel_item": {
      "type": "boolean"
    },
    "graph_api_version": {
      "type": "string"
    },
    "account": {
      "type": "string"
    },
    "ig_user_ids": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "location_ids": {
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

instagram_create_carousel_container

Create a draft carousel post with multiple images/videos before publishing. Instagram requires carousels to have between 2 and 10 media items. Container creation_ids expire in under 24 hours, so publish promptly after creation. Bulk support: accepts ig_user_ids, location_ids for batched execution.

Parameters13

caption	string	optional
children	array	optional
ig_user_id	string	optional
location_id	string	optional
share_to_feed	boolean	optional
child_image_urls	array	optional
child_video_urls	array	optional
child_image_files	array	optional
child_video_files	array	optional
graph_api_version	string	optional
account	string	optional
ig_user_ids	array	optional
location_ids	array	optional

Raw schema

{
  "type": "object",
  "properties": {
    "caption": {
      "type": "string"
    },
    "children": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "ig_user_id": {
      "type": "string"
    },
    "location_id": {
      "type": "string"
    },
    "share_to_feed": {
      "type": "boolean"
    },
    "child_image_urls": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "child_video_urls": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "child_image_files": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "name": {
            "type": "string"
          },
          "s3key": {
            "type": "string"
          },
          "mimetype": {
            "type": "string"
          }
        },
        "required": [
          "name",
          "s3key",
          "mimetype"
        ]
      }
    },
    "child_video_files": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "name": {
            "type": "string"
          },
          "s3key": {
            "type": "string"
          },
          "mimetype": {
            "type": "string"
          }
        },
        "required": [
          "name",
          "s3key",
          "mimetype"
        ]
      }
    },
    "graph_api_version": {
      "type": "string"
    },
    "account": {
      "type": "string"
    },
    "ig_user_ids": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "location_ids": {
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

instagram_post_ig_user_media_publish

Tool to publish a media container to an Instagram Business account. This action automatically waits for the container to finish processing before publishing. Instagram enforces an account-specific content-publishing rate limit over a 24-hour moving window; the exact cap varies by account and should be read live via IN… Bulk support: accepts ig_user_ids, creation_ids for batched execution.

Parameters8

ig_user_id	string	optional
creation_id	string	required
max_wait_seconds	number	optional
graph_api_version	string	optional
poll_interval_seconds	number	optional
account	string	optional
ig_user_ids	array	optional
creation_ids	array	optional

Raw schema

{
  "type": "object",
  "properties": {
    "ig_user_id": {
      "type": "string"
    },
    "creation_id": {
      "type": "string"
    },
    "max_wait_seconds": {
      "type": "number"
    },
    "graph_api_version": {
      "type": "string"
    },
    "poll_interval_seconds": {
      "type": "number"
    },
    "account": {
      "type": "string"
    },
    "ig_user_ids": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "creation_ids": {
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  },
  "required": [
    "creation_id"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

instagram_post_ig_comment_replies

Tool to create a reply to an Instagram comment. Use when you need to reply to a specific comment on an Instagram post owned by a Business or Creator account. The reply must be 300 characters or less, contain at most 4 hashtags and 1 URL, and cannot consist entirely of capital letters. Bulk support: accepts ig_comment_ids for batched execution.

Parameters5

message	string	required
ig_comment_id	string	required
graph_api_version	string	optional
account	string	optional
ig_comment_ids	array	optional

Raw schema

{
  "type": "object",
  "properties": {
    "message": {
      "type": "string"
    },
    "ig_comment_id": {
      "type": "string"
    },
    "graph_api_version": {
      "type": "string"
    },
    "account": {
      "type": "string"
    },
    "ig_comment_ids": {
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  },
  "required": [
    "message",
    "ig_comment_id"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

instagram_send_text_message

Send a text message to an Instagram user via DM in an existing conversation. Cannot initiate new DM threads — a prior conversation must exist. Requires an Instagram Business or Creator account with messaging permissions. Fails with error_subcode 2534022 if outside the messaging window; do not retry these failures. Bulk support: accepts ig_user_ids, recipient_ids, reply_to_message_ids for batched execution.

Parameters9

text	string	required
ig_user_id	string	optional
recipient_id	string	required
graph_api_version	string	optional
reply_to_message_id	string	optional
account	string	optional
ig_user_ids	array	optional
recipient_ids	array	optional
reply_to_message_ids	array	optional

Raw schema

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string"
    },
    "ig_user_id": {
      "type": "string"
    },
    "recipient_id": {
      "type": "string"
    },
    "graph_api_version": {
      "type": "string"
    },
    "reply_to_message_id": {
      "type": "string"
    },
    "account": {
      "type": "string"
    },
    "ig_user_ids": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "recipient_ids": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "reply_to_message_ids": {
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  },
  "required": [
    "text",
    "recipient_id"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

instagram_send_image

Send an image via Instagram DM to a specific user. Each send modifies inbox state; avoid bulk or automated sends without explicit user approval. Bulk support: accepts ig_user_ids, recipient_ids for batched execution.

Parameters7

image_url	string	required
ig_user_id	string	optional
recipient_id	string	required
graph_api_version	string	optional
account	string	optional
ig_user_ids	array	optional
recipient_ids	array	optional

Raw schema

{
  "type": "object",
  "properties": {
    "image_url": {
      "type": "string"
    },
    "ig_user_id": {
      "type": "string"
    },
    "recipient_id": {
      "type": "string"
    },
    "graph_api_version": {
      "type": "string"
    },
    "account": {
      "type": "string"
    },
    "ig_user_ids": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "recipient_ids": {
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  },
  "required": [
    "image_url",
    "recipient_id"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

instagram_mark_seen

Mark Instagram DM messages as read/seen for a specific user. Sends a 'mark_seen' sender action to indicate messages from the specified recipient have been read. Marking as seen is visible to the other party and changes inbox read state — use with explicit user approval in automated or bulk flows. IMPORTANT LIMITATIONS… Bulk support: accepts ig_user_ids, recipient_ids for batched execution.

Parameters6

ig_user_id	string	optional
recipient_id	string	required
graph_api_version	string	optional
account	string	optional
ig_user_ids	array	optional
recipient_ids	array	optional

Raw schema

{
  "type": "object",
  "properties": {
    "ig_user_id": {
      "type": "string"
    },
    "recipient_id": {
      "type": "string"
    },
    "graph_api_version": {
      "type": "string"
    },
    "account": {
      "type": "string"
    },
    "ig_user_ids": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "recipient_ids": {
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  },
  "required": [
    "recipient_id"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

instagram_get_conversation

Get details about a specific Instagram DM conversation (participants, etc). Requires a Business or Creator account with Instagram messaging permissions; personal accounts will return permission errors. Newly sent/received messages may take a few seconds to appear in results. Bulk support: accepts conversation_ids for batched execution.

Parameters4

conversation_id	string	required
graph_api_version	string	optional
account	string	optional
conversation_ids	array	optional

Raw schema

{
  "type": "object",
  "properties": {
    "conversation_id": {
      "type": "string"
    },
    "graph_api_version": {
      "type": "string"
    },
    "account": {
      "type": "string"
    },
    "conversation_ids": {
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  },
  "required": [
    "conversation_id"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

instagram_list_all_conversations

List all Instagram DM conversations for the authenticated user. Requires a Business/Creator account with messaging permissions; personal accounts return empty results. Response conversations are nested under `data.data` — accessing top-level `data` as the final list returns zero items. An empty `data` list is a valid … Bulk support: accepts user_ids, ig_user_ids for batched execution.

Parameters9

after	string	optional
limit	number	optional
user_id	string	optional
platform	string	optional
ig_user_id	string	optional
graph_api_version	string	optional
account	string	optional
user_ids	array	optional
ig_user_ids	array	optional

Raw schema

{
  "type": "object",
  "properties": {
    "after": {
      "type": "string"
    },
    "limit": {
      "type": "number"
    },
    "user_id": {
      "type": "string"
    },
    "platform": {
      "type": "string"
    },
    "ig_user_id": {
      "type": "string"
    },
    "graph_api_version": {
      "type": "string"
    },
    "account": {
      "type": "string"
    },
    "user_ids": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "ig_user_ids": {
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

instagram_list_all_messages

List all messages from a specific Instagram DM conversation. Requires a Business or Creator account with messaging permissions; personal accounts return empty results. Response data is nested under data.data (double-wrapped); attachment-only messages may have empty text fields. Bulk support: accepts conversation_ids for batched execution.

Parameters6

after	string	optional
limit	number	optional
conversation_id	string	required
graph_api_version	string	optional
account	string	optional
conversation_ids	array	optional

Raw schema

{
  "type": "object",
  "properties": {
    "after": {
      "type": "string"
    },
    "limit": {
      "type": "number"
    },
    "conversation_id": {
      "type": "string"
    },
    "graph_api_version": {
      "type": "string"
    },
    "account": {
      "type": "string"
    },
    "conversation_ids": {
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  },
  "required": [
    "conversation_id"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

show_version

Show the current MCP platform and adapter versions.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}

report_bug

Report a bug, missing feature, or send feedback. Include the conversation array with recent messages for reproduction.

Parameters3

message	string	required
context	string	optional
conversation	string	optional

Raw schema

{
  "type": "object",
  "properties": {
    "message": {
      "type": "string"
    },
    "context": {
      "default": "",
      "type": "string"
    },
    "conversation": {
      "default": "[]",
      "type": "string"
    }
  },
  "required": [
    "message"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

connect

Returns connection status and URLs. When all providers are connected, returns authenticated:true and empty pending[]. When credentials are missing, returns connect_url for the toolkit and per-install URLs.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}

toolkit_info

Returns the current toolkit state: installed MCPs, their connection status, the accounts connected to each one, and how many catalog tools each exposes.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}

marketplace

The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. Covers capability requests like "find an MCP that does X", "consulta um CPF", "is there a tool for Y". Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id → invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin. It also carries the mcp.ai PROMPT LIBRARY, which is about ready-made prompt TEXT rather than MCPs: search_prompts finds one, get_prompt returns its full text with {{variables}} filled, and publish_prompt saves a prompt and returns a shareable mcp.ai/p/<slug> link that opens without login.

Parameters23

action	string	optional
query	string	optional
mcp_id	string	optional
limit	number	optional
tier_slug	string	optional
immediate	boolean	optional
cancel_reason	string	optional
cancel_comment	string	optional
message	string	optional
report_context	string	optional
conversation	string	optional
request_name	string	optional
request_details	string	optional
tool_id	string	optional
arguments	string	optional
prompt_slug	string	optional
prompt_vars	string	optional
prompt_category	string	optional
prompt_tool	string	optional
prompt_title	string	optional
prompt_description	string	optional
prompt_body	string	optional
prompt_targets	array	optional

Raw schema

{
  "type": "object",
  "properties": {
    "action": {
      "default": "search",
      "type": "string",
      "enum": [
        "search",
        "describe",
        "install",
        "uninstall",
        "subscribe",
        "cancel",
        "resume",
        "report_bug",
        "request_mcp",
        "list_tools",
        "invoke",
        "search_prompts",
        "get_prompt",
        "publish_prompt"
      ]
    },
    "query": {
      "default": "",
      "type": "string"
    },
    "mcp_id": {
      "default": "",
      "type": "string"
    },
    "limit": {
      "default": 10,
      "type": "number"
    },
    "tier_slug": {
      "default": "",
      "type": "string"
    },
    "immediate": {
      "default": false,
      "type": "boolean"
    },
    "cancel_reason": {
      "type": "string",
      "enum": [
        "too_expensive",
        "missing_features",
        "switched_service",
        "unused",
        "customer_service",
        "too_complex",
        "low_quality",
        "other"
      ]
    },
    "cancel_comment": {
      "default": "",
      "type": "string"
    },
    "message": {
      "default": "",
      "type": "string"
    },
    "report_context": {
      "default": "",
      "type": "string"
    },
    "conversation": {
      "default": "[]",
      "type": "string"
    },
    "request_name": {
      "default": "",
      "type": "string"
    },
    "request_details": {
      "default": "",
      "type": "string"
    },
    "tool_id": {
      "default": "",
      "type": "string"
    },
    "arguments": {
      "default": "{}",
      "type": "string"
    },
    "prompt_slug": {
      "default": "",
      "type": "string"
    },
    "prompt_vars": {
      "default": "{}",
      "type": "string"
    },
    "prompt_category": {
      "default": "",
      "type": "string"
    },
    "prompt_tool": {
      "default": "",
      "type": "string"
    },
    "prompt_title": {
      "default": "",
      "type": "string"
    },
    "prompt_description": {
      "default": "",
      "type": "string"
    },
    "prompt_body": {
      "default": "",
      "type": "string"
    },
    "prompt_targets": {
      "default": [],
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "claude",
          "chatgpt",
          "cursor",
          "lovable"
        ]
      }
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

authenticate

MCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token. Best: add it to this server's config as a header `Authorization: Bearer <token>` for a permanent, non-expiring connection. Or paste it here for a session-only login: call with { token: "<jwt>" } after the user pastes, or with no args to get the link.

Parameters1

token

string

optional

Raw schema

{
  "type": "object",
  "properties": {
    "token": {
      "type": "string"
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

README.md9 KBView on GitHub

Instagram

Your Instagram account in Claude, Cursor and AI agents: publish, reply and measure

Connect your own Instagram account to Claude, Cursor or your own agent. Through the official API: publish photos, videos, carousels, Reels and Stories, read and reply to comments, talk in DMs, and pull profile and media insights. With the Advanced plan the same account also likes posts, follows and unfollows, lists and views stories, and starts a DM conversation. Connect in 2 clicks (Business or Creator account) or with username and password, 2FA supported.

📸 Really publishes: photos, videos, carousels, Reels and Stories through the official API
💬 Comments and DMs: read, reply, mark as seen and list conversations
📈 Profile and media insights: reach, impressions, engagement
❤️ Engagement on your own account (Advanced plan): like a post, like a comment, follow, unfollow, list and view stories, start a DM conversation
🔑 Two ways to connect: 2 clicks (Business/Creator) or username and password with 2FA
🧾 Async actions with a job id: track every action's state (get_job_status, list_jobs)
🌐 Mirrored REST API for your own backend, on top of MCP
💬 Works with any MCP client: Claude Desktop, Cursor, VS Code, Cline, Continue

Versão em português · Full docs (PT-BR) · Agent skill

One-click install

Claude (Web and Desktop)

Anthropic unified MCP installation at claude.ai/customize/connectors. The same link works for Claude Web and Claude Desktop (just be logged in):

➕ Open in Claude and connect

Manual (if the deeplink does not open): claude.ai/customize/connectors → + → Add custom connector → paste Name Instagram and URL https://api.mcp.ai/p_instagram.

Cursor

➕ Install Instagram in Cursor

VS Code (Copilot Chat)

➕ Install Instagram in VS Code

ChatGPT, Manus, OpenClaw and 40+ other clients

Works with any MCP client that speaks MCP over HTTP. The server URL is always:

code

https://api.mcp.ai/p_instagram

Per-client details: INSTALL.md.

Example prompts

code

Publish this image on my Instagram with the caption "today's launch"
Which new comments came in on my last 3 posts?
Reply to that comment thanking them
What was the reach of my Reels last week?
Like this post: https://www.instagram.com/p/CxAbCdEfGhI/
Follow the profile nasa from my account

27 tools available

Tool	Description
`instagram_actions_list_accounts`	List the Instagram accounts connected to this install — id, username, label.
`instagram_actions_like`	Like one or more Instagram posts, addressed by post URL or shortcode (NOT the numeric media id the official API returns).
`instagram_actions_list_comments`	List the comments on a post, addressed by URL or shortcode.
`instagram_actions_like_comment`	Like one or more comments. Each comment_id MUST come from instagram_actions_list_comments. The id returned by the official instagram_get_ig_media_comments belongs to a different namespace and is rejected. Returns a jo…
`instagram_actions_follow`	Follow one or more Instagram users by @username.
`instagram_actions_unfollow`	Unfollow one or more Instagram users by @username.
`instagram_actions_list_stories`	List a specific user's currently available stories (read-only, does not mark as seen).
`instagram_actions_view_story`	Watch (mark as seen) the stories of one or more profiles.
`instagram_actions_send_message`	Send the FIRST direct message to someone who has never messaged this account (the official API cannot do this).
`instagram_actions_get_job_status`	Get the status/progress/result of a previously started action by its job_id.
`instagram_actions_list_jobs`	List recent action jobs for the connected account, optionally filtered by status.
`instagram_get_user_info`	Get Instagram Business Account info including profile details and statistics.
`instagram_get_ig_user_media`	Get Instagram user's media collection (posts, photos, videos, reels, carousels).
`instagram_get_ig_media`	Get a published Instagram Media object (photo, video, story, reel, or carousel).
`instagram_get_ig_media_comments`	Tool to retrieve comments on an Instagram media object.
`instagram_get_ig_media_insights`	Tool to get insights and metrics for Instagram media objects (photos, videos, reels, carousel albums).
`instagram_get_user_insights`	Get Instagram account-level insights and analytics (profile views, reach, follower count, etc.).
`instagram_post_ig_user_media`	Tool to create a media container for Instagram posts.
`instagram_create_carousel_container`	Create a draft carousel post with multiple images/videos before publishing.
`instagram_post_ig_user_media_publish`	Tool to publish a media container to an Instagram Business account.
`instagram_post_ig_comment_replies`	Tool to create a reply to an Instagram comment.
`instagram_send_text_message`	Send a text message to an Instagram user via DM in an existing conversation.
`instagram_send_image`	Send an image via Instagram DM to a specific user.
`instagram_mark_seen`	Mark Instagram DM messages as read/seen for a specific user.
`instagram_get_conversation`	Get details about a specific Instagram DM conversation (participants, etc).
`instagram_list_all_conversations`	List all Instagram DM conversations for the authenticated user.
`instagram_list_all_messages`	List all messages from a specific Instagram DM conversation.

Details for each tool: docs/ferramentas.md (PT-BR)

How it works

code

1. Install the MCP in your client (Claude / Cursor / VS Code)
2. Connect YOUR account:
   • Basic    — 2 clicks, Business or Creator account (official API)
   • Advanced — username and password, 2FA supported
3. Reading and publishing answer immediately (official API)
4. Engagement actions are queued and return a job id
5. instagram_actions_get_job_status follows each action to the end

Engagement actions are asynchronous and run one at a time. Each takes ~40 s to ~2 min and the queue is serial, so this MCP is built to operate your account at a human pace, not for volume. If you need reading/publishing at scale, use the Basic plan, which is synchronous and free.

Pricing

Billed per connected account. See docs/precos.md (PT-BR).

Privacy & data protection

Sub-processors: the LLM host you choose (Claude, ChatGPT, Cursor, your own agent). Full list in docs/privacidade-lgpd.md.
Data returned by the tools is sent to the LLM host you choose, a sub-processor outside our control. We recommend plans with training opt-out.

FAQ

What is the difference between the Basic and Advanced plans? Basic is free, connects in 2 clicks and uses the official Instagram API (publishing, comments, DMs, insights). Advanced is a subscription per connected account and adds, on that same account, liking, following, unfollowing, listing/viewing stories and starting a DM conversation. Advanced also includes everything in Basic.

Do I need a Business or Creator account? For the Basic plan yes, that is what the official API requires. The Advanced plan connects with username and password (2FA supported) and has no such requirement.

How many actions per minute? Engagement actions are queued and executed one at a time, ~40 s to 2 min each. This MCP does not sell volume or bulk sending. Reading and publishing through the official API do not go through that queue.

Does this touch other people's accounts? No. Every action happens on the account you connected, with your authorization, and each one returns an auditable job id. Use it within Instagram's Terms of Use.

How do I like a post? Pass the post URL (https://www.instagram.com/p/… or /reel/…) or the shortcode. The numeric id the official API returns in id does not work for liking. If you listed media through the official side, use the permalink field.

Is there a REST API besides MCP? Yes. The same tool set is mirrored over REST with a Bearer token, with OpenAPI and a skill markdown you can paste into your own agent. See docs/api-rest.md.

Is the server open source? The server is proprietary (hosted). This repository is the public wrapper with manifests, docs and skills, all MIT.

Support

License

MIT — see LICENSE. The MCP server at api.mcp.ai/p_instagram is proprietary (hosted); this repo (manifests, docs, skills) is MIT.

Install

Tools (33)

instagram_actions_list_accountsinstagram_actions_likeinstagram_actions_list_commentsinstagram_actions_like_commentinstagram_actions_followinstagram_actions_unfollowinstagram_actions_list_storiesinstagram_actions_view_story

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://api.mcp.ai/p_instagram

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "instagram-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://api.mcp.ai/p_instagram"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

io.github.mcp-dir/instagram-mcp (MCP)

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

instagram_actions_list_accounts

instagram_actions_like

instagram_actions_list_comments

instagram_actions_like_comment

instagram_actions_follow

instagram_actions_unfollow

instagram_actions_list_stories

instagram_actions_view_story

instagram_actions_send_message

instagram_actions_get_job_status

instagram_actions_list_jobs

instagram_get_user_info

instagram_get_ig_user_media

instagram_get_ig_media

instagram_get_ig_media_comments

instagram_get_ig_media_insights

instagram_get_user_insights

instagram_post_ig_user_media

instagram_create_carousel_container

instagram_post_ig_user_media_publish

instagram_post_ig_comment_replies

instagram_send_text_message

instagram_send_image

instagram_mark_seen

instagram_get_conversation

instagram_list_all_conversations

instagram_list_all_messages

show_version

report_bug

connect

toolkit_info

marketplace

authenticate

Instagram

Your Instagram account in Claude, Cursor and AI agents: publish, reply and measure

One-click install

Claude (Web and Desktop)

Cursor

VS Code (Copilot Chat)

ChatGPT, Manus, OpenClaw and 40+ other clients

Example prompts

27 tools available

How it works

Pricing

Privacy & data protection

FAQ

Support

License

Install

Remote endpoint

Related servers