Skip to content
4bots logo

4bots MCP server

Which MCP servers are 4bots's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-26

← Back to 4bots

Whose server it is
  • Registry namenet.4bots/4botsverified in the MCP registry

The registry name sits under 4bots.net. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-26
  • Stateanswerschecked 2026-10-26
  • Tools9
  • Server calls itself4bots
  • Server version1.27.1
  • Protocol version2025-06-18

On 2026-10-26 the server answered initialize and tools/list without a sign-in. First answer in 92 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: add daily chess problems to an agent briefing; pick history stories and jokes for morning reading; receive business case studies and investing clips daily.
  • Checked on 2 of the 7 days it takes to judge reliability.

Once connected

  • For "add daily chess problems to an agent briefing", the likely first call is try_sample.
  • For "pick history stories and jokes for morning reading", the likely first call is try_sample.
  • For "receive business case studies and investing clips daily", the likely first call is try_sample.
  • create_setup_link change data without a sign-in: anyone with the address can call them.
  • Parameters are untyped or undescribed in 7 of 9 tools: check arguments before calling.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 2, the first on 2026-10-26
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
  • What an agent can do with it3 of 3 use cases
  • Answeredmeasuring2 of the 7 daily checks it takes to print a share
  • Median first answer306 ms
  • Space in an agent's context≈ 941 tokensthe definitions of all its tools (9), which an agent carries on every turn
  • Tool definitionsC · 70 of 100
  • Typed results0 of 9 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 7 of 9
  • Not saying whether it only reads or can destroy: 9 of 9

What an agent can do with it

  • can do · add daily chess problems to an agent briefing
  • can do · pick history stories and jokes for morning reading
  • can do · receive business case studies and investing clips daily

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

  • Tools that change data, on a server that answers without a sign-in: create_setup_link

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers9 tools · read 2026-10-26
  • try_sample

    Preview today's content from 3 channels. No signup, no arguments required. Call this first to see what your human would receive. If you like it, call start_subscription to activate. Args: source: Optional. How you found us (e.g…

  • list_channels

    All 10 channels with descriptions and pricing. Also shows proposed channels you can vote on.

  • start_subscription

    Activate instantly. No browser, no human action needed. Returns a session_token — store it for daily get_bundle calls. 100 free tokens on signup. Call list_channels for available slugs. Args: human_email: The human's email address…

  • get_bundle

    Get today's content for all subscribed channels. Call this once per day. Returns styled HTML (drop into your email where {4bots} goes) and plain text. Check low_balance — if true, send your human to manage_url to top up.

  • get_session

    Account status: credits, channels, delivery counts, manage URL.

  • create_setup_link

    Create a browser link for your human to pick channels themselves. For a fast start without human input, use start_subscription instead. Link expires in 7 days.

  • vote

    Vote for a proposed channel. Votes determine build order. Use list_channels to see proposed channel slugs.

  • get_summary

    Content catalog, privacy policy, and pricing in one call.

  • get_template

    Free HTML email template with {4bots} placeholder, plus suggested copy to introduce the service to your human. Drop get_bundle's html field where {4bots} appears.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "4bots": {
      "type": "http",
      "url": "https://4bots.net/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http 4bots https://4bots.net/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://4bots.net/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.