An extensible MCP-compliant context server that provides standardized access to social platform data
Beyond mcp server lets Claude, Cursor and other MCP clients work with Beyond directly. An extensible MCP-compliant context server that provides standardized access to social platform data.
An extensible Model Context Protocol server that provides standardized access to social platform data and onchain data. Currently supports Farcaster (via Neynar API) with placeholder for Twitter integration. More platforms like Telegram including onchain data will be added soon.
Once connected, the assistant can call these 14 tools directly:
Required — Set NEYNAR_API_KEY in your .env filesearch-content — Search for content on a social platformget-user-profile — Get a user's profile informationget-user-profile-by-wallet — Get user profile using wallet address (Farcaster only)get-user-balance — Get user's wallet balance (Farcaster only)get-user-content — Get content from a specific userget-thread — Get a conversation threadget-trending-topics — Get current trending topicsgetTrendingFeed — Get trending feed with multi-provider support (Farcaster only)get-wallet-profile — Get profile based on wallet addresssearch-channels — Search for channels on a platform (Farcaster only)Parameters — query, limit, cursorsearch-bulk-channels — Search for multiple channels in parallel (Farcaster only)Prerequisites — The Prerequisites tool exposed by this serverSetup follows the standard MCP pattern: clone or install the server, then register it in your client's configuration file and restart the client. The configuration snippets on this page cover Claude Desktop, Claude Code and Cursor.
Before the server will start you need to supply 3 environment variables: NEYNAR_API_KEY, ENABLE_FARCASTER, ENABLE_TWITTER. Keep credentials in your client's env block or a secrets manager rather than committing them.
AI-service servers chain other models into your assistant, turning a single chat into a small production pipeline. Beyond sits in that group, and the shape of its toolset — Required, search-content, get-user-profile among others — tells you what it is really for. Worth comparing against the other ai services servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.
| Tool | What it does |
|---|---|
| Required | Set NEYNAR_API_KEY in your .env file |
| search-content | Search for content on a social platform |
| get-user-profile | Get a user's profile information |
| get-user-profile-by-wallet | Get user profile using wallet address (Farcaster only) |
| get-user-balance | Get user's wallet balance (Farcaster only) |
| get-user-content | Get content from a specific user |
| get-thread | Get a conversation thread |
| get-trending-topics | Get current trending topics |
| getTrendingFeed | Get trending feed with multi-provider support (Farcaster only) |
| get-wallet-profile | Get profile based on wallet address |
| search-channels | Search for channels on a platform (Farcaster only) |
| Parameters | query, limit, cursor |
| search-bulk-channels | Search for multiple channels in parallel (Farcaster only) |
| Prerequisites | The Prerequisites tool exposed by this server. |
| Variable | Description | Required |
|---|---|---|
| NEYNAR_API_KEY | Credential the server authenticates with. | Yes |
| ENABLE_FARCASTER | Configuration value read at startup. | Optional |
| ENABLE_TWITTER | Configuration value read at startup. | Optional |
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Give your assistant a voice — text-to-speech, voice cloning and audio tools from the ElevenLabs API.
Give your assistant a real code sandbox — isolated cloud VMs for actually running the code it writes.
The ML hub in your context window — search models, datasets, papers and run Spaces from the official server.