Koskamo

RemoveDuplicates.org MCP

A stateless MCP server that allows AI agents to remove duplicate lines, CSV/TSV rows, or Excel XLSX rows from text data. It processes data in memory without storing it, supporting options like case-insensitivity, trimming, and preserving order.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

RemoveDuplicates.org MCP logo, by RemoveDuplicates.orgVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-06Operated by RemoveDuplicates.org
MCP endpoint (Streamable HTTP)
https://removeduplicates.org/mcp
Vendor documentation

What its tools do

1 tool, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Read-only (1)

1 of 1 have a description · 1 of 1 declare behavior hints · 1 of 1 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Passed Official MCP Registry namespace is tied to removeduplicates.org ·
  • Passed Endpoint is on the registry namespace domain ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Remove duplicate lines from text lists
  • Remove duplicate rows from CSV/TSV data
  • Remove duplicate rows from Excel XLSX workbooks

Source and maintenance

Vendor evidenceRegistry 1.0.1
Maintenance checked

Protocol and capabilities

Server
removeduplicates 1.0.0
MCP protocol negotiated in check
2025-11-25
Tools
1 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Removes duplicate lines or CSV/TSV rows with the removeduplicates.org engine. Text is processed in memory for the call and never stored. For .xlsx workbooks, send the user to https://removeduplicates.org/excel, which works only in their browser.

Tools

1 advertised

remove_duplicates — Remove duplicates
Advertised by the server during the last successful anonymous check.
Advertised read-only

Remove duplicate lines from a text list, or duplicate rows from CSV/TSV text such as rows copied from Excel or Google Sheets. Uses the same engine as removeduplicates.org and returns the cleaned text with counts. Stateless: the text is processed in memory for this call only and is never stored.

remove_duplicates input schema
{
  "type": "object",
  "required": [
    "text"
  ],
  "properties": {
    "keep": {
      "enum": [
        "first",
        "last"
      ],
      "type": "string",
      "default": "first",
      "description": "Which occurrence of a duplicate survives."
    },
    "text": {
      "type": "string",
      "description": "The list or table text: one item per line, or CSV/tab-separated rows. Up to 131072 UTF-8 bytes."
    },
    "trim": {
      "type": "boolean",
      "default": false,
      "description": "Ignore surrounding spaces when comparing and return trimmed values."
    },
    "order": {
      "enum": [
        "preserve",
        "sort"
      ],
      "type": "string",
      "default": "preserve",
      "description": "preserve keeps the original order; sort returns a natural (numeric-aware) sort."
    },
    "format": {
      "enum": [
        "auto",
        "lines",
        "table"
      ],
      "type": "string",
      "default": "auto",
      "description": "auto detects CSV/TSV tables; lines compares whole lines; table forces CSV/TSV parsing."
    },
    "header": {
      "type": "boolean",
      "default": false,
      "description": "Tables only: keep the first row as a header outside duplicate checks and counts."
    },
    "compare": {
      "anyOf": [
        {
          "enum": [
            "row"
          ],
          "type": "string"
        },
        {
          "type": "integer",
          "minimum": 0
        },
        {
          "type": "array",
          "items": {
            "type": "integer",
            "minimum": 0
          },
          "minItems": 1,
          "uniqueItems": true
        }
      ],
      "default": "row",
      "description": "Tables only: \"row\" compares entire rows; a zero-based column index or an array of indices compares only those columns."
    },
    "ignoreCase": {
      "type": "boolean",
      "default": false,
      "description": "Treat values such as Apple and apple as duplicates."
    },
    "removeEmpty": {
      "type": "boolean",
      "default": true,
      "description": "Drop blank lines or all-blank rows."
    }
  },
  "additionalProperties": false
}
remove_duplicates output schema
{
  "type": "object",
  "required": [
    "text",
    "format",
    "stats"
  ],
  "properties": {
    "text": {
      "type": "string",
      "description": "The cleaned text, rows joined with \\n."
    },
    "stats": {
      "type": "object",
      "required": [
        "total",
        "unique",
        "removed",
        "duplicates",
        "emptyRemoved",
        "reduction"
      ],
      "properties": {
        "total": {
          "type": "integer",
          "description": "Input lines or data rows (header excluded)."
        },
        "unique": {
          "type": "integer",
          "description": "Lines or data rows kept."
        },
        "removed": {
          "type": "integer",
          "description": "duplicates + emptyRemoved."
        },
        "reduction": {
          "type": "number",
          "description": "Percent of input removed, one decimal."
        },
        "duplicates": {
          "type": "integer"
        },
        "emptyRemoved": {
          "type": "integer"
        }
      }
    },
    "format": {
      "type": "object",
      "required": [
        "kind",
        "columns",
        "header"
      ],
      "properties": {
        "kind": {
          "enum": [
            "lines",
            "csv",
            "tsv"
          ],
          "type": "string"
        },
        "header": {
          "type": "boolean"
        },
        "columns": {
          "type": "integer"
        }
      }
    }
  }
}
remove_duplicates annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (1 of 1 answered).

  1. 2026-11-07: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
363 ms
95th percentile latency
363 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 363 ms · metadata changed · 1 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http removeduplicates-org-mcp https://removeduplicates.org/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add removeduplicates-org-mcp --url https://removeduplicates.org/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable removeduplicates-org-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "removeduplicates-org-mcp": {
      "url": "https://removeduplicates.org/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "removeduplicates-org-mcp": {
      "type": "streamableHttp",
      "url": "https://removeduplicates.org/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start removeduplicates-org-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "removeduplicates-org-mcp": {
      "type": "http",
      "url": "https://removeduplicates.org/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http removeduplicates-org-mcp https://removeduplicates.org/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://removeduplicates.org/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "removeduplicates-org-mcp": {
      "serverUrl": "https://removeduplicates.org/mcp"
    }
  }
}

Let your agent find its tools

Find servers like RemoveDuplicates.org MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Do you run RemoveDuplicates.org MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing