Skip to content
MCP server

sentence count, text discarded

Counts sentences in submitted text without retaining the text, for AI clients

Install
Platforms
API
Runs
Remotely
Version
1.0.0
Listing updated
today

Similar MCP servers

About sentence count, text discarded

sentence count, text discarded is an MCP server for developer tools. It runs as a hosted remote server, so there is nothing to install locally.

Sentence count is a small remote MCP server that takes a block of text, counts its sentences and returns the number. The text itself is discarded after the count, which the registry name and listing both state. It is reached over streamable HTTP at a hosted endpoint, so no local install is needed.

The server is one of many single-purpose utilities published by the same developer in the named-mcp-utilities repository, each registered under its own official registry name. The repository README describes the collection as independently listed servers for autonomous clients, and this entry is listed there as a sentence-counting intake.

It suits agent workflows that need a quick structural measure of text, such as checking whether a draft meets a sentence budget, before passing the content on elsewhere.

Install

Run in a terminal

claude mcp add --transport http sent-ok2 https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/sent-ok2/mcp

Add to Settings → Connectors → Add custom connector

https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/sent-ok2/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "sent-ok2": {
      "url": "https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/sent-ok2/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "sent-ok2": {
      "type": "http",
      "url": "https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/sent-ok2/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "sent-ok2": {
      "serverUrl": "https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/sent-ok2/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "sent-ok2": {
      "type": "http",
      "url": "https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/sent-ok2/mcp"
    }
  }
}

Using several servers? Build one config file with the MCP config generator.

What it does

Sentence counting
Returns the number of sentences found in the text it receives.
Text not retained
The submitted text is discarded once the count is produced, according to the listing.
Streamable HTTP transport
Exposed as a remote endpoint that MCP clients connect to over streamable HTTP.
Registry-listed utility
Published under an official MCP registry name within a set of small utility servers.

Good for

  • Checking the sentence count of a draft before it is sent to another step in an agent pipeline
  • Measuring text length in sentences for content length limits
  • Adding a lightweight text statistic to an MCP-based assistant without storing the input

sentence count, text discarded FAQ

How do I connect to this server?

The registry entry lists a remote streamable-http endpoint at a workers.dev URL under the s/sent-ok2 path. No package install is listed.

Is the submitted text stored?

The name and listing say the text is discarded. The listing describes it as a count-only utility.

How do I add sentence count, text discarded to Claude Code?

Run this command in your terminal: claude mcp add --transport http sent-ok2 https://agent-observatory-sensor.nolimit-observatory.workers.dev/s/sent-ok2/mcp

What are the best alternatives to sentence count, text discarded?

The closest alternatives to sentence count, text discarded are Word count, text discarded, URL-ish token count, text discarded, Title-case token count, text discarded, Unicode word count, text discarded and Whitespace word count, text discarded.

Where this comes from

  • Description: written from the project's README and its MCP Registry entry.
  • Install steps: from the official MCP Registry entry.

How AIPoweredBot checks servers