AI news, model pricing, service status, and machine-payable premium tools. AFTA-certified.
registry version 2.0.5
npm
npx -y @tensorfeed/mcp-servernpm
npx -y @tensorfeed/mcp-server@2.0.5Streamable HTTP
https://mcp.tensorfeed.ai/mcp
Pick your client — the config below is generated for this server (both local and hosted-endpoint forms). Copy respects the “Pin version” switch above.
claude_desktop_config.json
{
"mcpServers": {
"mcp-server-15": {
"command": "npx",
"args": [
"-y",
"@tensorfeed/mcp-server"
],
"env": {
"TENSORFEED_TOKEN": "<YOUR_TENSORFEED_TOKEN>"
}
}
}
}{
"mcpServers": {
"mcp-server-15": {
"command": "npx",
"args": [
"-y",
"@tensorfeed/mcp-server@2.0.5"
],
"env": {
"TENSORFEED_TOKEN": "<YOUR_TENSORFEED_TOKEN>"
}
}
}
}Remote (hosted) endpoint
https://mcp.tensorfeed.ai/mcp
Claude Desktop: Settings → Connectors → Add custom connector, paste this URL.
Format verified against the official Claude Desktop docs ↗.
terminal
claude mcp add --env TENSORFEED_TOKEN=<YOUR_TENSORFEED_TOKEN> mcp-server-15 -- npx -y @tensorfeed/mcp-server
claude mcp add --env TENSORFEED_TOKEN=<YOUR_TENSORFEED_TOKEN> mcp-server-15 -- npx -y @tensorfeed/mcp-server@2.0.5
terminal
claude mcp add --transport http mcp-server-15 https://mcp.tensorfeed.ai/mcp
Format verified against the official Claude Code docs ↗.
.cursor/mcp.json
{
"mcpServers": {
"mcp-server-15": {
"command": "npx",
"args": [
"-y",
"@tensorfeed/mcp-server"
],
"env": {
"TENSORFEED_TOKEN": "<YOUR_TENSORFEED_TOKEN>"
}
}
}
}{
"mcpServers": {
"mcp-server-15": {
"command": "npx",
"args": [
"-y",
"@tensorfeed/mcp-server@2.0.5"
],
"env": {
"TENSORFEED_TOKEN": "<YOUR_TENSORFEED_TOKEN>"
}
}
}
}.cursor/mcp.json (hosted endpoint)
{
"mcpServers": {
"mcp-server-15": {
"url": "https://mcp.tensorfeed.ai/mcp"
}
}
}Format verified against the official Cursor docs ↗.
.vscode/mcp.json
{
"servers": {
"mcp-server-15": {
"command": "npx",
"args": [
"-y",
"@tensorfeed/mcp-server"
],
"env": {
"TENSORFEED_TOKEN": "<YOUR_TENSORFEED_TOKEN>"
}
}
}
}{
"servers": {
"mcp-server-15": {
"command": "npx",
"args": [
"-y",
"@tensorfeed/mcp-server@2.0.5"
],
"env": {
"TENSORFEED_TOKEN": "<YOUR_TENSORFEED_TOKEN>"
}
}
}
}.vscode/mcp.json (hosted endpoint)
{
"servers": {
"mcp-server-15": {
"type": "http",
"url": "https://mcp.tensorfeed.ai/mcp"
}
}
}Format verified against the official VS Code docs ↗.
mcp_config.json
{
"mcpServers": {
"mcp-server-15": {
"command": "npx",
"args": [
"-y",
"@tensorfeed/mcp-server"
],
"env": {
"TENSORFEED_TOKEN": "<YOUR_TENSORFEED_TOKEN>"
}
}
}
}{
"mcpServers": {
"mcp-server-15": {
"command": "npx",
"args": [
"-y",
"@tensorfeed/mcp-server@2.0.5"
],
"env": {
"TENSORFEED_TOKEN": "<YOUR_TENSORFEED_TOKEN>"
}
}
}
}mcp_config.json (hosted endpoint)
{
"mcpServers": {
"mcp-server-15": {
"serverUrl": "https://mcp.tensorfeed.ai/mcp"
}
}
}Format verified against the official Windsurf docs ↗.
Defined in the server's official registry manifest. Required secrets are shown as <YOUR_…> placeholders in the configs above.
TENSORFEED_TOKEN secret — Bearer token from /api/payment/buy-credits. Required for paid tiers (full verdicts, 8 to 90 day series, webhook watches, account status). Free tiers (news, status, pricing, verdict previews, 1 to 7 day series, model disc⭐ 1 stars · 最近更新于 32 天前 · MIT license
TensorFeed MCP Server The official Model Context Protocol server for TensorFeed.ai. Plugs into Claude Desktop, Claude Code, Cursor, and any MCP compatible client. Gives your agent real time AI ecosystem data through 24 sharp tools: free data tools, eight signed verdict decisions with free previews…
Summary from the project README — github.com/RipperMercs/tensorfeed-mcp
Distributed as npm, Streamable HTTP, listed under Other Tools. Review our MCP security guide before granting access to real data.
TensorFeed MCP Server The official Model Context Protocol server for TensorFeed.ai. Plugs into Claude Desktop, Claude Code, Cursor, and any MCP compatible client. Gives your agent real time AI ecosystem data through 24 sharp tools: free data tools, eight signed verdict decisions with free previews
Run the install command shown above, then paste the config for your client (Claude Desktop, Claude Code, Cursor, VS Code or Windsurf) into its MCP settings and restart the client.
The MCP server itself is free to install. The source is public on https://github.com/RipperMercs/tensorfeed-mcp. Any third-party service it calls may require its own API key and account.
Any MCP-compatible client can use it, including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf and custom agents.
Publish this server? Link back with a badge on your README or site — copy either snippet.
Markdown
[](https://mcpnav.net/server/mcp-server-15/)
HTML
<a href="https://mcpnav.net/server/mcp-server-15/"><img src="https://mcpnav.net/badge/mcp-server-15.svg" alt="Listed on MCPNav" height="20"></a>