spoofzy
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SPOOFZY_API_KEY | No | Prepaid Spoofer API key (spz_…). A Cloud key placed here also works. Defaults to the key saved by `setup`. | |
| SPOOFZY_BACKEND | No | Backend to use: `cloud`, `api` or `auto` (Cloud when configured). | auto |
| SPOOFZY_CONFIG_DIR | No | Where `setup` stores credentials. | ~/.config/spoofzy |
| SPOOFZY_OUTPUT_DIR | No | Save every result in this folder instead of next to each file. | |
| SPOOFZY_WAIT_SECONDS | No | How long a call waits before returning. The Claude Code plugin uses 600; keep 50 for clients that time out calls after 60 seconds. | 50 |
| SPOOFZY_CLOUD_API_KEY | No | Spoofzy Cloud API key (spc_…). Defaults to the key saved by `setup`. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Spoofzy makes unique versions of images and videos ("spoofing"), strips hidden photo/video metadata and runs saved Spoofzy Cloud workflows, using the user's own Spoofzy account. Call spoofzy_account first to see what the account can do and what it costs. Before a run that uses the account's allowance, confirm the files, number of versions and settings with the user. Pass absolute file paths (folders work too). Results are saved in a spoofzy-output folder next to each source file unless output_dir is given; existing files are never overwritten. Long videos can outlast one call: check them with spoofzy_get_run. Reuse a request_id only to retry a call whose outcome was uncertain. Never ask the user to paste an API key into the chat: keys are configured outside the conversation.
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 |
|---|---|
| spoofzy_accountA | Check the Spoofzy connection: which keys are configured, the plan, which tools are available (Spoofer, many versions, Studio looks, Metadata Cleaner, workflows), what they cost, file limits, prepaid units and where results are saved. Call it first in a conversation and whenever a run is refused. Free and read-only. |
| spoofzy_spoofA | Make unique versions of local images or videos with the Spoofzy Spoofer. Uploads each file to the user's Spoofzy account, processes it and saves the results as -spoofzy-NN. in a spoofzy-output folder next to the source (or output_dir). Spoofzy Cloud makes 1, 5, 10, 20, 30, 40 or 50 versions per file; the prepaid Spoofer API makes 1 (up to 300 with batch access, otherwise one job per version). This uses the account's allowance: confirm the files, versions and settings with the user first. Returns when done or after wait_seconds; unfinished runs keep going and can be checked with spoofzy_get_run. |
| spoofzy_clean_metadataA | Remove hidden metadata (GPS location, device and camera details, capture dates) from local photos or videos with Spoofzy's Metadata Cleaner (needs a Spoofzy Cloud key). Saves cleaned copies as -clean-NN. in a spoofzy-output folder next to each source (or output_dir); originals are never modified. Uses the account's allowance: confirm first. |
| spoofzy_get_runA | Check a Spoofzy run by id: status, how many results are ready and which files were saved. Can wait for it to finish (wait_seconds). Runs started in this session are saved automatically when they finish; use spoofzy_download for other runs. Read-only. |
| spoofzy_downloadA | Save the results of a finished Spoofzy run into a local folder (never overwrites files). Use it for runs started with download=false, in the Spoofzy Cloud app, by a workflow or in an earlier session. Result links expire after a few days, so download promptly. |
| spoofzy_list_runsA | List recent Spoofzy runs: this session's runs (with their saved files) plus recent Spoofzy Cloud jobs and Studio runs. Read-only. |
| spoofzy_list_workflowsA | List saved Spoofzy Cloud workflows (reusable step stacks such as Caption → Spoof ×5): id, current version, input type, steps and outputs per run. Needs a Cloud key with 'Read workflows and history'. Read-only. |
| spoofzy_run_workflowA | Run a saved Spoofzy Cloud workflow on local files, on a saved original from the Spoofzy library (saved_original_id) or on a script (text, for voice workflows), then save the results. Uses the account's allowance: confirm with the user first. Needs a Cloud key with 'Run saved workflows' (plus 'Read workflows and history' to find the current version). |
| spoofzy_list_saved_originalsA | List the originals saved in the user's private Spoofzy Cloud library (id, name, type), for use with spoofzy_run_workflow. Needs a Cloud key with 'Read saved originals and voices'. Read-only. |
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 9 tools
Each tool targets a distinct resource or action: account status, two media operations (spoof, clean_metadata), workflow operations, and run lifecycle (get_run, list_runs, download). The only mild overlaps are get_run vs list_runs (single run vs recent runs) and spoof vs run_workflow (both process files and save results), but the descriptions clearly frame workflows as reusable step stacks.
All names share the spoofzy_ prefix and mostly follow verb_noun (list_runs, get_run, run_workflow, clean_metadata, list_saved_originals). Minor deviations are spoofzy_spoof (verb only) and spoofzy_account (noun only), but the pattern remains predictable.
Nine tools is well within the ideal range and each earns its place: one capability check, two processing actions, two listing tools for saved inputs, and three run-management tools. Nothing feels redundant or padding the surface.
The surface covers the core lifecycle: start a run (spoof, clean_metadata, run_workflow), monitor it (get_run, list_runs), and retrieve outputs (download), plus discovery of saved originals and workflows. Gaps are minor but real: no cancel/delete run, no way to save an original into the library, and no tool to create or edit workflows.