Skip to main content

txtool-mcp

MCP server exposing txtool text processing capabilities as tools for Claude and other MCP-compatible agents.

Prerequisites

Install uv (if not already):

curl -LsSf https://astral.sh/uv/install.sh | sh

No separate install step needed — uvx fetches and runs txtool-mcp automatically.

Setup

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "txtool": {
      "command": "uvx",
      "args": ["txtool-mcp"]
    }
  }
}

Restart Claude Desktop — txtool tools will appear automatically.

Claude Code (CLI)

Option 1 — CLI command (recommended):

claude mcp add txtool -s user -- uvx txtool-mcp

Option 2 — Manual config:

Add to ~/.claude.json:

{
  "mcpServers": {
    "txtool": {
      "command": "uvx",
      "args": ["txtool-mcp"]
    }
  }
}

Restart Claude Code — txtool tools will appear automatically.

Other MCP-compatible tools (Kiro, etc.)

Refer to your tool's documentation for how to register MCP servers. Use uvx txtool-mcp as the server command.

Available Tools

Tool Description
search_in_files Search for a regex pattern in a file or directory
replace_in_file Find and replace in a file (with dry-run diff)
file_stats Line/word/char counts and top words
transform_text Trim, wrap, indent text
convert_case snake, camel, pascal, kebab, upper, lower, title
sort_text Sort lines (alpha, numeric, reverse, unique)
dedup_text Remove duplicate lines
truncate_text Keep first/last N lines
extract_from_text Extract emails, URLs, IPs, dates, phones, numbers
extract_between_markers Extract lines between start/end patterns
diff_files Compare two files (line/word/char level)
set_ops Set operations on file lines (only_a, only_b, common)
pretty_json Pretty-print JSON
minify_json Minify JSON
validate_json Validate JSON
get_json_value Extract value by dot-notation path
view_csv Render CSV as aligned table
filter_csv Filter CSV rows by condition
parse_env_file Parse .env file as key/value table
apply_template Replace {{VAR}} placeholders
parse_log_file Count log levels, show top errors
tail_file Show last N lines of a file
encode_decode Encode/decode base64, URL, HTML
hash_file_content Compute file hash (md5, sha1, sha256, sha512)
word_count Line/word/char counts for file or directory

Example Prompts

  • "Search for all TODO comments in my project"
  • "Replace all occurrences of 'foo' with 'bar' in this file — show me a diff first"
  • "Pretty print this JSON and extract the users[0].email value"
  • "Parse this log file and summarize the errors"
  • "Convert this text to snake_case"

Metadata

Release files for txtool-mcp 0.1.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for txtool-mcp 0.1.2
File Size Uploaded Provenance
txtool_mcp-0.1.2.tar.gz 5.2 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for txtool-mcp 0.1.2
File Interpreter ABI Platform
txtool_mcp-0.1.2-py3-none-any.whl Python 3 none any Details

Total release size: 11.2 kB

Release files / txtool_mcp-0.1.2.tar.gz

Download URL txtool_mcp-0.1.2.tar.gz
Size 5.2 kB
Tags Source
SHA-256 checksum
How to use checksums
1a312e355145c94d52669391f09fe8dbfdfe13661b1a94dd6cd0c5c2af56fbcc
BLAKE2b-256 checksum
How to use checksums
94782785cab3091132f2164f584a37db7d82d060c69d060c0f8b9b1cd4c0b84b
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.11.14

Release files / txtool_mcp-0.1.2-py3-none-any.whl

Download URL txtool_mcp-0.1.2-py3-none-any.whl
Size 6.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
a5a3785fa0085d32b365b7ab8fb1d4434debed858d9fb3394514d9104b12b528
BLAKE2b-256 checksum
How to use checksums
0f348aa8e6074539cabc64a3e61e69dd01bb3e369aed81a522b6a4329ca4400c
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.11.14

Security for txtool-mcp 0.1.2

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page