ReShare AI MCP server
Commit Nov 13, 2026Allows AI agents to upload, trim, schedule, and post videos to social media platforms and swap AI characters into reels.
Also known as reshareai/agents, agents
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 1.0.0
- Last commit
- Nov 13, 2026
- License
- MIT
What is ReShare AI MCP?
ReShare AI allows AI agents to upload, trim, schedule, and post videos to social media platforms and swap AI characters into reels.
Summary generated from the project's README
About ReShare AI MCP server
Managing social media video content through an AI agent is what ReShare AI enables for developers and creators. This remote MCP server allows users to upload videos, trim or stitch up to three clips together, preview content, and schedule posts across platforms like TikTok, Instagram, YouTube, Facebook, LinkedIn, and Threads. It also features an AI swap capability to insert AI characters into reels before publishing.
Users can connect via OAuth 2.1 for clients like Claude Desktop and ChatGPT, or use a personal API key starting with rsk_ for tools such as Claude Code, Cursor, and VS Code. The server operates via Streamable HTTP. While the main server provides full functionality, the OpenAI package uses a specific sharing-only endpoint that excludes the AI swap tools. To prevent accidental publishing, every post requires a preview and a manual confirmation step.
What you can do with it
- 1Automated video social postingUpload a video file, trim it to the desired length, and schedule it for a specific time on Instagram or TikTok.
- 2AI character integrationSwap an AI character into an existing reel and post the new version to social media.
- 3Social media performance trackingAsk your AI agent to retrieve and report on the analytics of your recent video posts.
Written from the project's README. Every use case is checked against a quote from it.
How to install ReShare AI MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall ReShare AI MCP in Claude Code
$ claude mcp add --transport http agents https://www.reshare.ai/api/mcpInstall ReShare AI MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"agents": {
"url": "https://www.reshare.ai/api/mcp"
}
}
}Install ReShare AI MCP in VS Code
.vscode/mcp.json
{
"servers": {
"agents": {
"type": "http",
"url": "https://www.reshare.ai/api/mcp"
}
}
}Install ReShare AI MCP in VS Code CLI
$ code --add-mcp '{"name":"agents","type":"http","url":"https://www.reshare.ai/api/mcp"}'Install ReShare AI MCP in Codex
$ codex mcp add agents --url https://www.reshare.ai/api/mcpInstall ReShare AI MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.agents] url = "https://www.reshare.ai/api/mcp"
Install ReShare AI MCP in Gemini CLI
$ gemini mcp add -s user --transport http agents https://www.reshare.ai/api/mcpInstall ReShare AI MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"agents": {
"url": "https://www.reshare.ai/api/mcp",
"type": "http"
}
}
}Configuration
RESHARE_API_KEY
| Name | Description | |
|---|---|---|
| RESHARE_API_KEY | — |
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablereshareai/agents is public and reachablegithub.com/reshareai/agents ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-13github.com/reshareai/agents ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeHTTPS endpoint answered 401 (sign-in required)Pass
README
View on GitHubReShare AI for AI agents
Connect ReShare AI to your AI agent and run both modes from a conversation:
- Sharing: upload your own video, trim it or stitch up to 3 clips, preview, then post now or schedule it to your connected social accounts (TikTok, Instagram, YouTube, Facebook, LinkedIn, Threads and more; X is coming soon), and read analytics.
- AI swap: swap one of your AI characters into a reel, then post the result.
Everything goes through one remote MCP server: https://www.reshare.ai/api/mcp (Streamable HTTP). The OpenAI
package (openai-plugin/) uses its Sharing-only endpoint https://www.reshare.ai/api/mcp/sharing (no AI swap tools,
no plan offers). Full guide and
tool list: https://www.reshare.ai/docs/agents.
Sign in
| Method | Use it for | How |
|---|---|---|
| OAuth 2.1 (sign in with ReShare AI) | claude.ai / Claude Desktop connectors, ChatGPT, the Codex plugin, any client that supports MCP OAuth | Add the server URL; the client opens ReShare AI's sign-in and asks what it may do: read, jobs (uploads, videos, swaps), post. Revoke it any time in Settings → Connect your agent. |
Personal API key rsk_… |
Claude Code, Codex CLI, Cursor, VS Code, scripts | Create one at https://www.reshare.ai/settings/agents, keep it in an environment variable, send Authorization: Bearer $RESHARE_API_KEY. |
Every post is previewed first (preview_post) and published only with confirm: true after you say yes.
What is in this repo
| Path | What |
|---|---|
.claude-plugin/marketplace.json |
Claude Code plugin marketplace (/plugin marketplace add reshareai/agents) |
claude-plugin/ |
Claude Code plugin: the MCP server (API key from RESHARE_API_KEY) + skills |
.agents/plugins/marketplace.json |
Codex plugin marketplace (codex plugin marketplace add reshareai/agents) |
openai-plugin/ |
Agent Plugins package for Codex and the ChatGPT/Codex plugin directory: MCP server with OAuth + skills |
codex/ |
Codex CLI with an API key: config.toml, AGENTS.md, skills for ~/.agents/skills |
server.json |
The listing for the official MCP Registry (ai.reshare/reshare) |
Skills (the same text in every client): share-my-video, swap-and-post, schedule-week, check-analytics (the OpenAI package leaves out swap-and-post).
Install
Claude Code (plugin)
export RESHARE_API_KEY=rsk_…
/plugin marketplace add reshareai/agents
/plugin install reshare@reshare
Claude Code (server only)
claude mcp add --scope user --transport http reshare https://www.reshare.ai/api/mcp --header "Authorization: Bearer $RESHARE_API_KEY"
Codex (plugin, OAuth)
codex plugin marketplace add reshareai/agents
codex plugin add reshare@reshare
Codex (API key)
codex mcp add reshare --url https://www.reshare.ai/api/mcp --bearer-token-env-var RESHARE_API_KEY
mkdir -p ~/.agents/skills && cp -R codex/skills/* ~/.agents/skills/
claude.ai, Claude Desktop, ChatGPT: add a custom connector with the URL https://www.reshare.ai/api/mcp and sign in.
Any other MCP client: a Streamable HTTP server at https://www.reshare.ai/api/mcp with either OAuth or the header
Authorization: Bearer rsk_…. Per-client snippets (Cursor, VS Code, Windsurf, Gemini CLI, Grok): https://www.reshare.ai/docs/agents.
Support
Help: https://www.reshare.ai/support · Privacy: https://www.reshare.ai/privacy · Terms: https://www.reshare.ai/terms
Maintainers
This folder is generated in the ReShare AI app repo (integrations/) and copied here as is. Skills are edited in
claude-plugin/skills/ and copied to the other clients by scripts/agent-submissions.ts in the app repo.
License: not chosen yet (see LICENSE once added).
License
MIT © Optijara AI LLC. The ReShare AI name and logo are trademarks of Optijara AI LLC and are not covered by the MIT license.
Support: support@reshare.ai
ReShare AI MCP questions
How do I add ReShare AI MCP to Claude Code?
Run claude mcp add --transport http agents https://www.reshare.ai/api/mcp in your terminal. Add --scope user to make it available in every project.
How do I add ReShare AI MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What social media platforms are supported?
Supported platforms include TikTok, Instagram, YouTube, Facebook, LinkedIn, and Threads, with X coming soon.
How do I prevent accidental posts?
Every post is previewed first and will only be published if you explicitly confirm it.