Sidearm

io.github.ebadrosPublished by GitHub account ebadrosv0.9.2Updated Oct 24, 2026

Protect media from AI training, detect AI-generated content, and find stolen work.

VerifiedSTDIODesktop onlySecurity & MonitoringMedia & DesignAI & ML

Overview

AI-generated overview

Sidearm wraps the Sidearm media-protection API, letting an assistant protect media from AI training, detect AI-generated content, and search for stolen work.

What you can do
  • Browse protection algorithms and run them, or protect media with a preset level and extract embeddings
  • Poll asynchronous jobs and check their progress and results
  • Detect AI-generated media, fingerprint matches, and whether content was used to train a model
  • Register, list, inspect, update and permanently delete media assets in the library
  • Search similar media, view account, rights, billing and provenance data, and identify media by fingerprint
  • Create, read and publish shareable result links, list deletion records, and search documentation or dashboard how-tos
When to use it
Useful when you want an assistant to handle media rights and provenance work: protecting artwork or footage from AI training, checking whether an image or clip is AI-generated, or investigating whether your content was used to train a model, all through your Sidearm account.
Requirements
Runs locally over stdio, typically launched with npx from the npm package, so Node.js is needed. Requires a Sidearm account and an API key supplied in the SDRM_API_KEY environment variable; SDRM_BASE_URL can override the API endpoint. Network access to the Sidearm API is required.
Before you install
The API key in SDRM_API_KEY is a live credential (sk_live_ prefix) that grants access to your account and credits; keep it out of shared configs. Tools can register, update and permanently delete media assets, publish share results publicly, and consume paid credits per algorithm, so confirm before destructive or spending actions. Media and metadata are sent to the Sidearm API.

Installation

In SourceWeft

  1. Open Sidearm in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

@sidearmdrm/mcp

MCP server for the Sidearm API — protect media from AI training, detect AI-generated content, and search for stolen work.

This package exposes the Sidearm REST API as Model Context Protocol (MCP) tools that AI agents (Cursor, Claude Desktop, Windsurf, etc.) can call directly.

Quick Start

1. Get an API key

Sign up at sdrm.io and create an API key at sdrm.io/api-keys.

2. Configure your agent

Add to your MCP configuration file:

Cursor (.cursor/mcp.json):

json
{  "mcpServers": {    "sdrm": {      "command": "npx",      "args": ["-y", "@sidearmdrm/mcp"],      "env": {        "SDRM_API_KEY": "sk_live_..."      }    }  }}

Claude Desktop (claude_desktop_config.json):

json
{  "mcpServers": {    "sdrm": {      "command": "npx",      "args": ["-y", "@sidearmdrm/mcp"],      "env": {        "SDRM_API_KEY": "sk_live_..."      }    }  }}

Windsurf (~/.codeium/windsurf/mcp_config.json):

json
{  "mcpServers": {    "sdrm": {      "command": "npx",      "args": ["-y", "@sidearmdrm/mcp"],      "env": {        "SDRM_API_KEY": "sk_live_..."      }    }  }}

That's it. Your agent can now call Sidearm tools.

Tools (27)

Discovery

ToolDescription
list_algorithmsBrowse available protection algorithms. Filter by category or media type.

Protection & Extraction

ToolDescription
run_algorithmRun specific algorithms on media by ID. Returns a job for async processing.
protect_mediaProtect media with a preset level (standard/maximum). Auto-selects algorithms.
extract_embeddingsExtract raw embedding vectors from media for downstream similarity search or ML pipelines.

Jobs

ToolDescription
check_jobPoll async job status. Returns progress and results when complete.

Detection

ToolDescription
detect_aiDetect whether media was AI-generated. Supports image, video, audio, text.
detect_fingerprintCheck if media has been previously registered using fingerprint matching.
detect_membershipTest whether your content was used to train a suspect AI model.

Search

ToolDescription
search_mediaSearch for similar media across your indexed library.
list_searchesList previous searches on your account.

Media Management

ToolDescription
register_mediaRegister and index media with optional protection mode (register, search_ready, standard, maximum).
list_mediaList media assets in your library (paginated, filterable).
get_mediaGet details of a specific media asset including protection status and algorithms applied.
update_mediaUpdate media metadata (e.g., original URL).
delete_mediaPermanently delete a media asset and all associated data.

Account, Rights & Billing

ToolDescription
get_accountGet your account details — ID, name, email, credit balance, and plan info.
get_rightsGet C2PA, IPTC, and rights information for a media asset.
get_billingView credit balance, usage breakdown, per-algorithm costs, and billing portal link.

Provenance & Identification

ToolDescription
get_provenanceGet the full provenance chain for an asset — algorithms, C2PA manifest, membership results.
identify_mediaIdentify media by its embedded Sidearm fingerprint and extract its C2PA provenance chain.

Shares

ToolDescription
create_shareCreate a shareable link for a detection, search, or provenance result (starts private).
get_shareGet a shared result by its share ID.
publish_shareMake a shared result publicly accessible.

Deletion Records

ToolDescription
list_deletionsList deletion records documenting permanently deleted assets.
get_deletionGet details of a specific deletion record including purged algorithms and storage status.

Documentation

ToolDescription
search_docsSearch the Sidearm API documentation. Returns relevant sections from the full developer reference.
navigate_uiLook up how to perform actions in the Sidearm dashboard. Returns step-by-step instructions.

Example Agent Conversations

"Protect this image from AI training"

Agent calls protect_media with the image URL, then check_job to get the protected file.

"What algorithms are available for audio?"

Agent calls list_algorithms with media_type: "audio".

"Run Nightshade and Glaze on my artwork"

Agent calls run_algorithm with algorithms: ["nightshade", "glaze"].

"Is this photo AI-generated?"

Agent calls detect_ai with the image, then check_job for results.

"Was my artwork used to train Stable Diffusion?"

Agent calls detect_membership with your media IDs and the model name.

"How do I upload files in the dashboard?"

Agent calls navigate_ui with query: "upload files" for step-by-step instructions.

Environment Variables

VariableRequiredDescription
SDRM_API_KEYYesYour Sidearm API key (sk_live_... or sk_test_...)
SDRM_BASE_URLNoOverride the API base URL (default: https://api.sdrm.io)

Development

bash
git clone https://github.com/sidearmDRM/mcp-server.gitcd mcp-servernpm installnpm run build

Test locally with the MCP Inspector:

bash
SDRM_API_KEY=sk_test_... npx @modelcontextprotocol/inspector node dist/index.js

License

MIT

Source: README.md at commit 8d055fe

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.9.2LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts