IT ToolsBLOCK
A comprehensive Model Context Protocol (MCP) server that provides access to over 100 IT tools and utilities commonly used by developers, system administrators, and IT professionals. Inspired by https://github.com/CorentinTh/it-tools
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[!WARNING] This project is deprecated and no longer maintained. It was built as a learning exercise to explore AI-assisted development and the Model Context Protocol (MCP). No further updates, bug fixes, or pull requests will be accepted. The repository is kept for reference only. If you need an actively maintained MCP server with IT utilities, look for community alternatives.
[](https://github.com/wrenchpilot/it-tools-mcp/actions/workflows/main.yml) [](https://hub.docker.com/r/wrenchpilot/it-tools-mcp) [](https://hub.docker.com/r/wrenchpilot/it-tools-mcp) [](https://www.npmjs.com/package/it-tools-mcp) [](https://www.npmjs.com/package/it-tools-mcp) [](https://github.com/wrenchpilot/it-tools-mcp/releases) [](https://github.com/wrenchpilot/it-tools-mcp/blob/main/LICENSE) [](https://github.com/wrenchpilot/it-tools-mcp/issues) [](https://github.com/wrenchpilot/it-tools-mcp/commits/main) [](https://hub.docker.com/r/wrenchpilot/it-tools-mcp) [](https://github.com/wrenchpilot/i
6482048f6d3cOBSERVED · 2026-10-10Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add it-tools-mcp -- npx -y [email protected]
claude mcp add it-tools-mcp:v5.10.9 -- docker run -i --rm docker.io/wrenchpilot/it-tools-mcp:v5.10.9:None
Exposed tools (119)
117 read · 2 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
analyze_distinct_words | read | |
analyze_text_stats | read | |
calculate_ip_subnet | read | |
calculate_ipv4_subnet | read | |
calculate_ipv6_subnet | read | |
calculate_percentage | read | |
capitalize_text | read | |
cat | read | |
compare_json | read | |
compare_text | read | |
convert_angle | read | |
convert_cidr_to_ip_range | read | |
convert_docker_compose_to_run | write | |
convert_docker_run_to_compose | write | |
convert_energy | read | |
convert_hex_to_rgb | read | |
convert_html_to_markdown | read | |
convert_ip_range_to_cidr | read | |
convert_json_to_csv | read | |
convert_json_to_toml | read | |
convert_list | read | |
convert_markdown_to_html | read | |
convert_number_base | read | |
convert_power | read | |
convert_rem_px | read | |
convert_rgb_to_hex | read | |
convert_roman_numerals | read | |
convert_temperature | read | |
convert_text_to_binary | read | |
convert_text_to_camelcase | read | |
convert_text_to_kebabcase | read | |
convert_text_to_lowercase | read | |
convert_text_to_nato | read | |
convert_text_to_pascalcase | read | |
convert_text_to_unicode | read | |
convert_text_to_uppercase | read | |
convert_toml_to_json | read | |
convert_unix_timestamp | read | |
curl | read | |
decode_base64 | read | |
decode_html | read | |
decode_jwt | read | |
decode_safelink | read | |
decode_url | read | |
decrypt_ansible_vault | read | |
dig | read | |
encode_base64 | read | |
encode_html | read | |
encode_html_entities | read | |
encode_url | read | |
encrypt_ansible_vault | read | |
evaluate_math | read | |
fang_url | read | |
format_css | read | |
format_html | read | |
format_javascript | read | |
format_json | read | |
format_phone | read | |
format_sql | read | |
format_xml | read | |
format_yaml | read | |
generate_ansible_inventory | read | |
generate_ascii_art | read | |
generate_basic_auth | read | |
generate_bip39 | read | |
generate_crontab | read | |
generate_hmac | read | |
generate_ipv6_ula | read | |
generate_lorem_ipsum | read | |
generate_mac_address | read | |
generate_markdown_toc | read | |
generate_numeronym | read | |
generate_otp | read | |
generate_password | read | |
generate_qr_code | read | |
generate_random_port | read | |
generate_svg_placeholder | read | |
generate_token | read | |
generate_traefik_compose | read | |
generate_ulid | read | |
generate_uuid | read | |
grep | read | |
hash_bcrypt | read | |
hash_md5 | read | |
hash_sha1 | read | |
hash_sha256 | read | |
hash_sha512 | read | |
head | read | |
identify_file_type | read | |
logging_setLevel | read | |
logging_status | read | |
lookup_http_status | read | |
lookup_mime_types | read | |
lookup_port_numbers | read | |
minify_json | read | |
normalize_email | read | |
nslookup | read | |
obfuscate_string | read | |
parse_ansible_inventory | read | |
parse_url | read | |
ping | read | |
ps | read | |
scp | read | |
search_emoji | read | |
show_ansible_reference | read | |
show_device_info | read | |
show_docker_reference | read | |
show_unicode_names | read | |
slugify_text | read | |
ssh | read | |
system_info | read | |
tail | read | |
telnet | read | |
test_regex | read | |
text_snakecase | read | |
top | read | |
validate_ansible_playbook | read | |
validate_docker_compose | read | |
validate_iban | read |
Trust audit
BLOCKgrade F · trust 50/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (4 observation(s))
- Network
- declared (7 observation(s))
- Shell
- declared (5 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- found
Findings (16)
parsed = yaml.load(inventory);
parsed = yaml.load(inventory);
parsed = yaml.load(playbook);
const parsed = YAML.load(yaml);
const parsed = yaml.load(content) as any;
path.join(home, '.ssh', 'id_rsa'),
path.join(home, '.ssh', 'id_ed25519'),
path.join(home, '.ssh', 'id_rsa'),
path.join(home, '.ssh', 'id_ed25519'),
"dog": ["🐶", "🐕", "🦮", "🐕🦺"],
{ jsonrpc: "2.0", id: 29, method: "tools/call", params: { name: "decode_jwt", arguments: { token: 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJzdWIiOiIxMjM0NTY3ODkwIiwibmFtZSI6IkpvaG4gRG9lIiwiaWF0IjoxNTE2.gitmessage
const hash = createHash('md5');const hash = createHash('sha1');const sshPrivateKey = fs.existsSync(os.homedir() + '/.ssh/id_rsa') ? fs.readFileSync(os.homedir() + '/.ssh/id_rsa', 'utf8') : undefined;
@iarna/toml, @modelcontextprotocol/sdk, @types/js-yaml, @types/papaparse, @types/qrcode, bcryptjs, bip39, color
Gates applied: no_behavioural_pass.
6482048f6d3cfull audit observations/trust-audit/mcp-server/wrenchpilot__it-tools.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-10 | 6482048f6d3c | BLOCK | F | 50 | first audit |
Questions
What is the IT Tools MCP server?
A comprehensive Model Context Protocol (MCP) server that provides access to over 100 IT tools and utilities commonly used by developers, system administrators, and IT professionals. Inspired by https://github.com/CorentinTh/it-tools
What tools does IT Tools expose?
119 in total: 117 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is IT Tools safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (50/100) and found 9 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does IT Tools need?
No credential environment variables were found in its source, so it appears to need none.
How does IT Tools run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as it-tools-mcp at 5.10.9.
How current is this page?
The grade is for one exact copy of the source (6482048f6d3c), read on 2026-10-10. The repository is watched and re-audited when it changes.