# Instadram (remote · api.instadram.me)

Whisky & bourbon collection in AI: search the catalog, read and manage your shelf (OAuth).

- Trust score: 89/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `api.instadram.me`: 89/100 (this document), [markdown](https://verifymcp.io/servers/me-instadram-instadram/api.md), [page](https://verifymcp.io/servers/me-instadram-instadram/api)

## Channel facts

- Endpoint: `https://api.instadram.me/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 97/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
  - The authorisation server supports Client ID Metadata Documents, the current MCP client-registration mechanism.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 72/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 5351 tokens (~111/item across 48 items; 48 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 70/100
  - Stability observed for 21 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 92/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 77% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 6 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 49 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Instadram MCP server?

Instadram is a hosted endpoint at https://api.instadram.me/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http me-instadram-instadram 'https://api.instadram.me/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "me-instadram-instadram": {
      "url": "https://api.instadram.me/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "me-instadram-instadram": {
      "type": "http",
      "url": "https://api.instadram.me/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.me-instadram-instadram]
url = "https://api.instadram.me/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "me-instadram-instadram": {
      "type": "remote",
      "url": "https://api.instadram.me/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add me-instadram-instadram --url 'https://api.instadram.me/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  me-instadram-instadram:
    url: "https://api.instadram.me/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "me-instadram-instadram": {
      "Transport": "http",
      "Url": "https://api.instadram.me/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add me-instadram-instadram -t streamable-http -u 'https://api.instadram.me/mcp'
```

### Other

```json
{
  "mcpServers": {
    "me-instadram-instadram": {
      "type": "http",
      "url": "https://api.instadram.me/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-04 (score 89, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 88, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 87, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 86, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-27 (score 85, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-25 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-23 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-20 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (48)

### `whoami` (~47 tokens)

Return the signed-in user's public profile (uid, username, display name) plus pro (paid or gifted Instadram Pro). Uses the Bearer token uid only. Available to free users.

### `list_my_bottles` (~138 tokens)

List bottles in the signed-in user's collection. Filters: status (unopened|opened|consumed|excluded|wishlist|active|tried) and optional text query. Always scoped to the token uid — a userId argument is ignored.

Input parameters:

- `cursor` (string): Opaque pagination cursor from a previous response (numeric offset)
- `limit` (integer): Page size (max 50)
- `offset` (integer): Number of items to skip
- `query` (string): Filter by display name, distillery, or notes
- `status` (string): Bottle status or shelf group (active / wishlist / tried)

### `get_my_bottle` (~46 tokens)

Get one bottle from the signed-in user's collection by id. 404 if missing or not theirs.

Input parameters:

- `bottleId` (string, required): Bottle document id in the caller's collection

### `get_shelf_value` (~90 tokens)

Value of the signed-in user's active shelf (opened + unopened) in USD, the same number as the app's Stats. paid: purchase price, or MSRP when no price was entered (msrpCount says how many used MSRP). msrp: every bottle at MSRP. excludedCount bottles have no usable price. totalCents is exact; total is dollars. Always scoped to the token uid.

### `search_catalog` (~79 tokens)

Search the public bottle catalog (expressions and distilleries). Does not return other users' collections.

Input parameters:

- `cursor` (string): Opaque pagination cursor from a previous response (numeric offset)
- `limit` (integer): Page size (max 50)
- `offset` (integer): Number of items to skip
- `query` (string, required)

### `get_expression` (~49 tokens)

Get one public catalog expression by id, or by path distilleries/{id}/brands/{id}/expressions/{id}.

Input parameters:

- `expressionId` (string, required): Expression document id or nested catalog path

### `list_my_activity` (~68 tokens)

List the signed-in user's own pours/activity. Never returns other users' activity.

Input parameters:

- `cursor` (string): Opaque pagination cursor from a previous response (numeric offset)
- `limit` (integer): Page size (max 50)
- `offset` (integer): Number of items to skip

### `list_my_collections` (~63 tokens)

List the signed-in user's shelf groups / collections.

Input parameters:

- `cursor` (string): Opaque pagination cursor from a previous response (numeric offset)
- `limit` (integer): Page size (max 50)
- `offset` (integer): Number of items to skip

### `search_users` (~104 tokens)

Search public Instadram profiles by exact username (usernames/{handle} or users.username) then displayName prefix. Returns uid, username, displayName, photoURL. Never email or billing fields.

Input parameters:

- `cursor` (string): Opaque pagination cursor from a previous response (numeric offset)
- `limit` (integer): Page size (max 50)
- `offset` (integer): Number of items to skip
- `query` (string, required): Username or display-name prefix

### `get_user` (~77 tokens)

Get one public profile by username or userId. Resolves handles via usernames/{handle}. Public fields only — no email, stripeCustomerId, or billing.

Input parameters:

- `userId` (string): Firebase uid of the target user
- `username` (string): Instadram handle (with or without @). Resolved via usernames/{handle}.

### `list_user_bottles` (~168 tokens)

List bottles on another user's public shelf. Requires username or userId. Same status/query/paging as list_my_bottles. 404 if the user is missing; empty list if they have no bottles.

Input parameters:

- `cursor` (string): Opaque pagination cursor from a previous response (numeric offset)
- `limit` (integer): Page size (max 50)
- `offset` (integer): Number of items to skip
- `query` (string): Filter by display name, distillery, or notes
- `status` (string): Bottle status or shelf group (active / wishlist / tried)
- `userId` (string): Firebase uid of the target user
- `username` (string): Instadram handle (with or without @). Resolved via usernames/{handle}.

### `get_user_bottle` (~91 tokens)

Get one bottle from another user's public collection. Requires username or userId plus bottleId. 404 if the user or bottle is missing.

Input parameters:

- `bottleId` (string, required): Bottle document id in the target user's collection
- `userId` (string): Firebase uid of the target user
- `username` (string): Instadram handle (with or without @). Resolved via usernames/{handle}.

### `list_user_activity` (~117 tokens)

List another user's pours/activity (authenticated feed read). Requires username or userId. Newest first. Same paging caps as list_my_activity.

Input parameters:

- `cursor` (string): Opaque pagination cursor from a previous response (numeric offset)
- `limit` (integer): Page size (max 50)
- `offset` (integer): Number of items to skip
- `userId` (string): Firebase uid of the target user
- `username` (string): Instadram handle (with or without @). Resolved via usernames/{handle}.

### `list_user_collections` (~103 tokens)

List another user's public shelf groups. Requires username or userId.

Input parameters:

- `cursor` (string): Opaque pagination cursor from a previous response (numeric offset)
- `limit` (integer): Page size (max 50)
- `offset` (integer): Number of items to skip
- `userId` (string): Firebase uid of the target user
- `username` (string): Instadram handle (with or without @). Resolved via usernames/{handle}.

### `fetch_bottle_reviews` (~165 tokens)

AI community-review research for a bottle (fetchBottleReviews). Not a user tasting-note form. iOS may have this flagged off; the tool still works. Pass bottleName, or bottleId (own collection), or username/userId + bottleId to resolve the display name then research. Returns reviews_found, msrp, general_consensus, summary, overall_rating, reviewers. Read/research only — does not write Firestore.

Input parameters:

- `bottleId` (string): Resolve display name from a collection doc, then research
- `bottleName` (string): Bottle display name to research
- `userId` (string): Firebase uid of the target user
- `username` (string): Instadram handle (with or without @). Resolved via usernames/{handle}.

### `lookup_bottle` (~113 tokens)

Add-bottle AI identify (analyzeBourbonImage). Photo (imageData) or text (query). Returns distillery, location, spirit.brand + expressions (name, proof, msrp, tasting_notes, etc.), success, confidence. Does not write a bottle or set expressionRef. Never generates art (transformImage is not used).

Input parameters:

- `imageData` (string): Base64 bottle photo, same as analyzeBourbonImage
- `query` (string): Bottle name when no photo is available

### `get_feed` (~86 tokens)

The Home feed as the app shows it: recent pours, adds and ratings from everyone (scope global, the app default) or only people you follow plus you (scope following). Blocked and hidden accounts are removed.

Input parameters:

- `cursor` (string): nextCursor from a previous page
- `limit` (integer)
- `offset` (integer)
- `scope` (string)

### `explore_catalog` (~42 tokens)

The Explore tab's bottle deck: recent public shelf bottles with photos from other collectors, one per expression, blocked and hidden accounts removed.

Input parameters:

- `limit` (integer)

### `discover_users` (~75 tokens)

Discover people like the app's People list: everyone (empty query) or a name/handle match, ranked like the app, with badge and whether you follow them. Use follow_user to follow.

Input parameters:

- `cursor` (string): nextCursor from a previous page
- `limit` (integer)
- `query` (string)

### `search_cocktails` (~113 tokens)

Cocktails to make with a bottle, like the app's recipe rail on a bottle page. Pass the bottle's name (plus spiritType, category, proof when known). Results note how many of the main liquors you already own. For browsing all drinks use explore_recipes.

Input parameters:

- `bottleName` (string, required): Bottle display name
- `category` (string)
- `limit` (integer)
- `proof` (number)
- `spiritType` (string): e.g. bourbon, gin

### `explore_recipes` (~61 tokens)

The Explore recipe feed: every drink, ordered by how few bottles you'd need to buy from your own shelf, then popularity. Paged with nextCursor.

Input parameters:

- `cursor` (string): nextCursor from a previous page
- `pageSize` (integer)

### `check_username` (~36 tokens)

Check whether an @handle is valid and free before set_username (same rules and messages as Edit Profile).

Input parameters:

- `username` (string, required)

### `export_shelf` (~41 tokens)

Export your whole collection as CSV (Pro, like Profile → Export Collection): the same columns and values as the app's file. Returns filename and csv text.

### `add_bottle_from_photo` (~205 tokens)

Add a bottle from a photo, like Add Bottle → photo in the app: the preview identifies it; after the user agrees, AI art is made from the photo (1K) and the bottle is added with it. Free: 5 AI art a day; Pro: unlimited. Two steps: repeat with confirm_token after the user agrees.

Input parameters:

- `confirm_token` (string): Omit first: you get a preview (and what it costs). Repeat with identical arguments plus this token after the user agrees.
- `distillery` (string)
- `imageData` (string, required): Base64 JPEG/PNG photo of the bottle (or a data: URL)
- `name` (string): Override the identified name
- `proof` (number)
- `rating` (number)
- `status` (string)
- `style` (string): Art style. Free: Elements. Pro: Elements, Dark, Blended, Heritage, Oak, Cheers.

### `regenerate_art` (~146 tokens)

Make new AI art for one of your bottles from its stored photo (or a new photo), like Think harder → Only regenerate the art. Uses 1 AI art credit (free 5/day, Pro unlimited). Two steps.

Input parameters:

- `bottle_id` (string, required)
- `confirm_token` (string): Omit first: you get a preview (and what it costs). Repeat with identical arguments plus this token after the user agrees.
- `imageData` (string): Base64 JPEG/PNG photo of the bottle (or a data: URL)
- `style` (string): Art style. Free: Elements. Pro: Elements, Dark, Blended, Heritage, Oak, Cheers.

### `reidentify_bottle` (~124 tokens)

Think harder about one of your bottles: identify it again from its photo and research fresh reviews. Reviews are saved when found; pass update_identity to also replace the name, distillery and proof. Two steps.

Input parameters:

- `bottle_id` (string, required)
- `confirm_token` (string): Omit first: you get a preview (and what it costs). Repeat with identical arguments plus this token after the user agrees.
- `imageData` (string): Base64 JPEG/PNG photo of the bottle (or a data: URL)
- `update_identity` (boolean)

### `search_public_bottles` (~88 tokens)

Search bottles like the app's Search tab: other collectors' shelf bottles (with owner username and display name) plus public catalog bottles, ranked like the app. Paged with nextCursor/hasMore/total.

Input parameters:

- `cursor` (string): nextCursor from a previous page
- `limit` (integer)
- `offset` (integer)
- `query` (string, required)

### `add_bottle` (~255 tokens)

Add a bottle to your shelf, wishlist or Tried list (same as the app's Add Bottle form). Free accounts can hold 25 unopened/opened bottles; Pro is unlimited. Two steps: the first call only previews and returns confirm_token; show the preview to the user and repeat the call with confirm_token only after they agree.

Input parameters:

- `bottle_notes` (string): Notes about this bottle (batch, gift, etc.)
- `collection_ids` (array): Your collection ids (list_my_collections)
- `confirm_token` (string): Omit on the first call to get a preview. After the user agrees, call again with identical arguments plus this token.
- `distillery` (string)
- `expression_path` (string): Catalog path from search_catalog (preferred)
- `is_favorite` (boolean)
- `name` (string): Bottle name when it isn't in the catalog
- `notes` (string): Your tasting notes
- `proof` (number)
- `purchase_price` (number)
- `purchased_from` (string)
- `rating` (number)
- `status` (string): unopened/opened count toward the free 25-bottle shelf; finished, wishlist and tried don't

### `update_bottle` (~118 tokens)

Edit your bottle: notes, price, store, custom name/distillery/proof, batch, barrel details, favorite. Two steps: the first call only previews and returns confirm_token; show the preview to the user and repeat the call with confirm_token only after they agree.

Input parameters:

- `bottle_id` (string, required): Id from list_my_bottles
- `confirm_token` (string): Omit on the first call to get a preview. After the user agrees, call again with identical arguments plus this token.
- `fields` (object, required)

### `set_bottle_status` (~144 tokens)

Move a bottle between unopened, opened, finished, wishlist and tried. Moving into unopened/opened re-checks the free 25-bottle limit. Two steps: the first call only previews and returns confirm_token; show the preview to the user and repeat the call with confirm_token only after they agree.

Input parameters:

- `bottle_id` (string, required): Id from list_my_bottles
- `confirm_token` (string): Omit on the first call to get a preview. After the user agrees, call again with identical arguments plus this token.
- `status` (string, required): unopened/opened count toward the free 25-bottle shelf; finished, wishlist and tried don't

### `rate_bottle` (~124 tokens)

Rate one of your bottles 0-5 in steps of 0.25 (0 clears). Posts a 'rated' update like the app. Two steps: the first call only previews and returns confirm_token; show the preview to the user and repeat the call with confirm_token only after they agree.

Input parameters:

- `bottle_id` (string, required): Id from list_my_bottles
- `confirm_token` (string): Omit on the first call to get a preview. After the user agrees, call again with identical arguments plus this token.
- `rating` (number, required)

### `remove_bottle` (~95 tokens)

Permanently delete one of your bottles. Two steps: the first call only previews and returns confirm_token; show the preview to the user and repeat the call with confirm_token only after they agree.

Input parameters:

- `bottle_id` (string, required): Id from list_my_bottles
- `confirm_token` (string): Omit on the first call to get a preview. After the user agrees, call again with identical arguments plus this token.

### `wishlist_add` (~148 tokens)

Put a bottle on your wishlist: a new one (expression_path or name), or move an existing bottle_id there. Two steps: the first call only previews and returns confirm_token; show the preview to the user and repeat the call with confirm_token only after they agree.

Input parameters:

- `bottle_id` (string): Id from list_my_bottles
- `confirm_token` (string): Omit on the first call to get a preview. After the user agrees, call again with identical arguments plus this token.
- `distillery` (string)
- `expression_path` (string): Catalog path from search_catalog (preferred)
- `name` (string): Bottle name when it isn't in the catalog

### `wishlist_remove` (~93 tokens)

Delete a bottle from your wishlist. Two steps: the first call only previews and returns confirm_token; show the preview to the user and repeat the call with confirm_token only after they agree.

Input parameters:

- `bottle_id` (string, required): Id from list_my_bottles
- `confirm_token` (string): Omit on the first call to get a preview. After the user agrees, call again with identical arguments plus this token.

### `log_pour` (~109 tokens)

Log that you're drinking one of your bottles (posts to your followers' feed, like the app's Pour). Two steps: the first call only previews and returns confirm_token; show the preview to the user and repeat the call with confirm_token only after they agree.

Input parameters:

- `bottle_id` (string, required): Id from list_my_bottles
- `confirm_token` (string): Omit on the first call to get a preview. After the user agrees, call again with identical arguments plus this token.

### `create_collection` (~91 tokens)

Create one of your collections. Two steps: the first call only previews and returns confirm_token; show the preview to the user and repeat the call with confirm_token only after they agree.

Input parameters:

- `confirm_token` (string): Omit on the first call to get a preview. After the user agrees, call again with identical arguments plus this token.
- `description` (string)
- `name` (string, required)

### `rename_collection` (~111 tokens)

Rename one of your collections (and optionally change its description). Two steps: the first call only previews and returns confirm_token; show the preview to the user and repeat the call with confirm_token only after they agree.

Input parameters:

- `collection_id` (string, required): Id from list_my_collections
- `confirm_token` (string): Omit on the first call to get a preview. After the user agrees, call again with identical arguments plus this token.
- `description` (string)
- `name` (string, required)

### `delete_collection` (~98 tokens)

Delete one of your collections. Its bottles stay on your shelf. Two steps: the first call only previews and returns confirm_token; show the preview to the user and repeat the call with confirm_token only after they agree.

Input parameters:

- `collection_id` (string, required): Id from list_my_collections
- `confirm_token` (string): Omit on the first call to get a preview. After the user agrees, call again with identical arguments plus this token.

### `add_to_collection` (~112 tokens)

Add one of your bottles to one of your collections. Two steps: the first call only previews and returns confirm_token; show the preview to the user and repeat the call with confirm_token only after they agree.

Input parameters:

- `bottle_id` (string, required): Id from list_my_bottles
- `collection_id` (string, required): Id from list_my_collections
- `confirm_token` (string): Omit on the first call to get a preview. After the user agrees, call again with identical arguments plus this token.

### `remove_from_collection` (~120 tokens)

Take one of your bottles out of one of your collections (the bottle stays on your shelf). Two steps: the first call only previews and returns confirm_token; show the preview to the user and repeat the call with confirm_token only after they agree.

Input parameters:

- `bottle_id` (string, required): Id from list_my_bottles
- `collection_id` (string, required): Id from list_my_collections
- `confirm_token` (string): Omit on the first call to get a preview. After the user agrees, call again with identical arguments plus this token.

### `delete_my_activity` (~106 tokens)

Delete one of your own feed posts (id from list_my_activity). The bottle stays on your shelf. Two steps: the first call only previews and returns confirm_token; show the preview to the user and repeat the call with confirm_token only after they agree.

Input parameters:

- `activity_id` (string, required): Id from list_my_activity
- `confirm_token` (string): Omit on the first call to get a preview. After the user agrees, call again with identical arguments plus this token.

### `follow_user` (~108 tokens)

Follow someone (username or userId from search_users). Two steps: the first call only previews and returns confirm_token; show the preview to the user and repeat the call with confirm_token only after they agree.

Input parameters:

- `confirm_token` (string): Omit on the first call to get a preview. After the user agrees, call again with identical arguments plus this token.
- `userId` (string): User id
- `username` (string): Instadram handle (with or without @)

### `unfollow_user` (~102 tokens)

Stop following someone. Two steps: the first call only previews and returns confirm_token; show the preview to the user and repeat the call with confirm_token only after they agree.

Input parameters:

- `confirm_token` (string): Omit on the first call to get a preview. After the user agrees, call again with identical arguments plus this token.
- `userId` (string): User id
- `username` (string): Instadram handle (with or without @)

### `block_user` (~122 tokens)

Block someone: hides their posts and profile from your feed, Explore and Discover (doesn't unfollow, like the app). Two steps: the first call only previews and returns confirm_token; show the preview to the user and repeat the call with confirm_token only after they agree.

Input parameters:

- `confirm_token` (string): Omit on the first call to get a preview. After the user agrees, call again with identical arguments plus this token.
- `userId` (string): User id
- `username` (string): Instadram handle (with or without @)

### `unblock_all_users` (~88 tokens)

Unblock every user you've blocked (same as Profile → Unblock All Users). Two steps: the first call only previews and returns confirm_token; show the preview to the user and repeat the call with confirm_token only after they agree.

Input parameters:

- `confirm_token` (string): Omit on the first call to get a preview. After the user agrees, call again with identical arguments plus this token.

### `update_profile` (~222 tokens)

Edit your profile like Edit Profile in the app: displayName, bio, location, website, instagram, twitter, facebook, tiktok. Only fields you pass change; an empty string clears an optional field. Photos and handle aren't changed here (see set_username). Two steps: the first call only previews and returns confirm_token; show the preview to the user and repeat the call with confirm_token only after they agree.

Input parameters:

- `bio` (string): Bio
- `confirm_token` (string): Omit on the first call to get a preview. After the user agrees, call again with identical arguments plus this token.
- `displayName` (string): Display name
- `facebook` (string): facebook; empty string clears it
- `instagram` (string): instagram; empty string clears it
- `location` (string): location; empty string clears it
- `tiktok` (string): tiktok; empty string clears it
- `twitter` (string): twitter; empty string clears it
- `website` (string): website; empty string clears it

### `set_username` (~113 tokens)

Change your @handle (3–20 characters: lowercase letters, numbers, underscore). Your old handle is released. Use check_username first. Two steps: the first call only previews and returns confirm_token; show the preview to the user and repeat the call with confirm_token only after they agree.

Input parameters:

- `confirm_token` (string): Omit on the first call to get a preview. After the user agrees, call again with identical arguments plus this token.
- `username` (string, required): New handle, with or without @

### `send_feedback` (~118 tokens)

Send a bug report, feature idea or other feedback to the Instadram team as you (same as Profile → Send Feedback). 10–5000 characters. Two steps: the first call only previews and returns confirm_token; show the preview to the user and repeat the call with confirm_token only after they agree.

Input parameters:

- `confirm_token` (string): Omit on the first call to get a preview. After the user agrees, call again with identical arguments plus this token.
- `kind` (string, required)
- `message` (string, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/me-instadram-instadram/api#diagnostics

## Score history

- 2026-11-05: 89
- 2026-11-04: 89
- 2026-11-03: 88
- 2026-11-02: 88
- 2026-11-01: 87
- 2026-10-31: 87
- 2026-10-30: 86
- 2026-10-29: 86
- 2026-10-28: 85
- 2026-10-27: 85
- 2026-10-26: 84
- 2026-10-25: 84
- 2026-10-24: 83
- 2026-10-23: 83
- 2026-10-22: 82
- 2026-10-21: 82
- 2026-10-20: 82
- 2026-10-19: 81
- 2026-10-18: 81
- 2026-10-17: 80
- 2026-10-16: 80
- 2026-10-15: 79

## Common questions

### What is the Instadram MCP server?

Instadram is an MCP server listed in the public MCP registry as me.instadram/instadram. Whisky & bourbon collection in AI: search the catalog, read and manage your shelf (OAuth). This page covers its hosted endpoint (https://api.instadram.me/mcp).

### Is the Instadram MCP server safe to use?

Instadram scores 89 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Instadram MCP server expose?

Instadram exposes 48 tools: whoami, list_my_bottles, get_my_bottle, get_shelf_value, search_catalog, and 43 more. Their descriptions and schemas cost roughly 5,132 tokens of context every time the server is loaded.

### Does the Instadram MCP server require authentication?

Yes. Instadram asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the Instadram MCP server still maintained?

Instadram is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://api.instadram.me/mcp
- Website: https://instadram.me/mcp
- Changelog RSS feed: https://verifymcp.io/servers/me-instadram-instadram/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/me-instadram-instadram/api.json
- HTML version of this page: https://verifymcp.io/servers/me-instadram-instadram/api