officialai-takedown
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OFFICIAL_AI_API_URL | No | Override the API base URL | https://theofficial.ai |
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| capture_evidenceA | Capture evidence of a URL hosting impersonating or stolen content: independent archive snapshot, retrieval timestamp, SHA-256 of the exact bytes, and a PDQ perceptual fingerprint of any image. Returns a typed evidence manifest. Run this FIRST, before the content is taken down or changed. |
| get_playbookA | Get the takedown playbook for a platform: legal bases, report-form URLs, documented email intakes, required fields, ID requirements, and response times. Every fact carries a primary-source citation with a retrieval date; unverifiable facts are marked UNVERIFIED, never guessed. Platforms: meta, youtube, tiktok, x, google. |
| draft_noticeA | Draft a platform-correct takedown notice from captured evidence. Statutory fields are computed deterministically; the result is a DRAFT the human must review and file themselves (the draft includes the form URL or documented email intake, plus step-by-step instructions). Use capture_evidence first to get an evidenceManifestId, and get_playbook to pick the right reportPathId. |
| check_authorizationA | Check whether content matches a registered authentic work in the Official AI registry. Query by sha256 (exact bytes) or pdq (perceptual fingerprint from capture_evidence). Returns the registry record or an honest 'unknown'; absence of a record is not a judgment about the content, and perceptual matches require human confirmation. |
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
Each tool targets a distinct step in the takedown process: evidence capture, authorization check, platform playbook retrieval, and notice drafting. There is no overlap in functionality.
All tool names follow a consistent verb_noun pattern in snake_case (e.g., capture_evidence, get_playbook), making them predictable and easy to use.
With 4 tools, the set is well-scoped for the domain of takedown assistance. Each tool serves a necessary function without redundancy or unnecessary complexity.
The tools cover the core workflow: capture evidence, check authorization, retrieve platform-specific playbook, and draft notice. Missing a tool for actually submitting the notice, but that is intentionally left to the human reviewer.