igagent
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| extract_postA | Harvest a public Instagram post/carousel/reel: given a post URL, share link or bare shortcode, decodes the public embed surface and downloads every exposed photo and video (magic-byte verified) to out_dir. Returns the summary plus the full post_manifest envelope (author, caption, media URLs, local files, errors, decode-slot provenance). No login, no API keys. Large carousels can take a minute. |
| lookup_postA | Fast metadata-only lookup of a public Instagram post: same decode pipeline as extract_post but with --no-download — author, caption, timestamps, media URLs, carousel shape, without writing media files. Use this when you only need to read the post. |
| read_manifestA | Read an existing post_manifest.json produced by a previous extract/lookup and return the full envelope. Refuses any file not named post_manifest.json. |
| get_schemaA | Return the JSON Schema (draft-07) describing the post_manifest envelope (schema_version 1.0) — use it to validate or explore the output contract. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
extract_post and lookup_post share the same decode pipeline and differ only in whether media is downloaded, which is the main potential confusion, but their descriptions clearly state the download vs metadata-only distinction. read_manifest and get_schema are cleanly distinct from each other and from the extraction tools.
All four tools follow a consistent verb_noun snake_case pattern (read_manifest, get_schema, extract_post, lookup_post). No mixed conventions or vague verbs.
Four tools is a tight, well-scoped set for an Instagram post extraction utility. It is on the lean side but each tool earns its place, with no redundancy.
The surface covers the full round-trip: discover the contract (get_schema), fetch metadata (lookup_post), fetch media (extract_post), and re-read prior output (read_manifest). No obvious dead ends, though there is no batch/multi-post operation for repeated use.