Instagram

io.github.mcp-dir/instagram-mcp · v0.1.0 · marketing-and-seo

Instagram is healthy: it completed an MCP handshake in 1052 ms and exposes 33 tools. It scores 60/100.

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

Endpoint: https://api.mcp.ai/p_instagram (streamable-http)

Repository · JSON · Add to my inventory

Score 60/100

health21.8 / 25
authEase15 / 15
toolQuality15 / 15
maintenance5 / 15
adoption0 / 10
usage0 / 10
security8 / 10
penalties−5

Scoring v0.3, computed 2026-10-15T05:20:53.227Z.

Health history

Checked (UTC)StatusLatencyError
2026-10-15T05:20:37.366ZHealthy1052

Tools (33)

instagram_actions_list_accountsList the Instagram accounts connected to this install — id, username, label.
instagram_actions_likeLike 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.
instagram_actions_list_commentsList 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.
instagram_actions_like_commentLike 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.
instagram_actions_followFollow one or more Instagram users by @username. Returns a job_id.
instagram_actions_unfollowUnfollow one or more Instagram users by @username. Returns a job_id.
instagram_actions_list_storiesList 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).
instagram_actions_view_storyWatch (mark as seen) the stories of one or more profiles. Omit `targets` to watch the home tray. Returns a job_id.
instagram_actions_send_messageSend 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.
instagram_actions_get_job_statusGet the status/progress/result of a previously started action by its job_id. Bulk support: accepts job_ids for batched execution.
instagram_actions_list_jobsList recent action jobs for the connected account, optionally filtered by status.
instagram_get_user_infoGet 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
instagram_get_ig_user_mediaList account media. REST response: read result.result.data and result.result.paging (not result.data). Null engagement fields mean unavailable, not zero; use media insights for saved, shares and views. Bulk support: accepts ig_user_ids, auto_resolve_fb_page_ids for batched execution.
instagram_get_ig_mediaGet 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 containe
instagram_get_ig_media_commentsTool 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 t
instagram_get_ig_media_insightsRead media insights. REST response: read result.result.data. Request metric=[views,reach,saved,shares] for views, reach, saves and shares; availability depends on the media type and metric. Bulk support: accepts ig_media_ids for batched execution.
instagram_get_user_insightsRead account insights at result.result.data in REST. An empty data array means insights are unavailable, not zero. It does not by itself establish a follower-count restriction. Bulk support: accepts ig_user_ids for batched execution.
instagram_post_ig_user_mediaTool 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
instagram_create_carousel_containerCreate 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.
instagram_post_ig_user_media_publishTool 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
instagram_post_ig_comment_repliesTool 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:
instagram_send_text_messageSend 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
instagram_send_imageSend 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.
instagram_mark_seenMark 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. IM
instagram_get_conversationGet 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 c
instagram_list_all_conversationsList 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 `dat
instagram_list_all_messagesList 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: accept
show_versionShow the current MCP platform and adapter versions.
report_bugReport a bug, missing feature, or send feedback. Include the conversation array with recent messages for reproduction.
connectReturns 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.
toolkit_infoReturns the current toolkit state: installed MCPs, their connection status, the accounts connected to each one, and how many catalog tools each exposes.
marketplaceThe 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 (ev
authenticateMCP.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