mcpField
A
allcams.fm

allcams.fm

VerifiedFeaturedRemote
allcams.fmSearch0Updated 4w ago

About allcams.fm

allcams.fm is a read-only MCP server for AI agents to explore live webcam rooms and related category and model pages across five platforms. It provides current online listings and page information in 41 languages; the service is for adults 18 and over.

Key features

  1. 01Browse live models across five platforms
  2. 02Filter listings by category or nickname
  3. 03View model and category page details
  4. 04Search information in 41 languages
  5. 05Read-only access without an API key

Use cases

  1. 01Find models currently online in a category
  2. 02Check a model’s status and viewer count
  3. 03Explore category descriptions and related categories

MCP support

Exposes tools for listing online models and retrieving site, category, and model information to MCP clients. It is a remote, stateless Streamable HTTP server with no authentication.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://allcams.fm/api/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

5

This tool takes no parameters.

Details

From the project README

allcams MCP server

Live webcam rooms from five platforms as tools for an AI agent: who is online now, what a category or a model page says, in 41 languages. One URL, no key, read-only.

Adult content (18+). The site and every link the server returns are for adults only.

Endpointhttps://allcams.fm/api/mcp
TransportMCP Streamable HTTP, stateless, JSON responses
Authnone
Registryfm.allcams/cams
Docshttps://allcams.fm/mcp/ (Markdown: https://allcams.fm/mcp.md)
Agent cataloghttps://allcams.fm/.well-known/ai-catalog.json
llms.txthttps://allcams.fm/llms.txt

Connect

Claude Code

claude mcp add --transport http allcams https://allcams.fm/api/mcp

Claude.ai / Claude Desktop — Settings → Connectors → Add custom connector → URL https://allcams.fm/api/mcp, no authentication.

Cursor (.cursor/mcp.json)

{ "mcpServers": { "allcams": { "url": "https://allcams.fm/api/mcp" } } }

Any JSON-RPC client

curl -s https://allcams.fm/api/mcp \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

MCP Inspector

npx @modelcontextprotocol/inspector --cli https://allcams.fm/api/mcp --method tools/list

Tools

toolparametersreturns
site_overview—what the site is, key facts, sections, languages (the llms.txt)
list_categorieslanguage (default en)every category of one language with slug and one-line description
get_categorycategory, languageone category page: text, platforms, how many models online, related categories
get_modelnickname, languageone model page: online/offline and viewers, platform, languages, statistics, tags, links
list_onlinecategory, nickname, limit, languagemodels live right now, most viewers first

Every URL a tool returns is a page on allcams.fm: page_url opens the model page, watch_url opens the live room. Give them to users exactly as returned.

Resource: site://llms.txt.

Data

Five platforms (Stripchat, Chaturbate, Cam4, LiveJasmin, BongaCams), one shared vocabulary of categories, 41 languages. Who is online refreshes every 10 minutes; category and model text is the same the HTML pages show. Category and model pages also exist as Markdown twins (/<lang>/<slug>.md, /<lang>/model/<nickname>.md).

This repository

The server runs inside the allcams.fm backend; this repository holds its public description: server.json (the MCP registry manifest), this README and the licence. Issues and questions: open an issue here.

Licence

MIT — see LICENSE.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.