Agent Data Tools: Utilities
io.github.Nutshell2000/agent-data-tools-utilities · v1.341.0 · score 89/100 · checked 2026-11-22
Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works
109 tools: JSON repair, CSV, hashes, cron, dates, units, validators. 10 free calls.
Source: https://github.com/Nutshell2000/agent-data-tools
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 109 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (memory_delete). Require confirmation before the agent calls them. |
What was checked
- https://agent-data-tools.revmesh2074.workers.dev/mcp/utilities: answers without auth
Public tools: csv_preflight, memory_set, memory_get, recommend, pack_hash_toolbox, pack_json_toolbox, pack_encoding_toolbox, pack_text_analysis, pack_id_toolbox, pack_string_toolbox, text_language, useragent_parse, answers_page_evidence, answers_company_diligence, search_similar, keywords_ideas, x402_find, evidence_bundle, json_validate, json_format, json_minify, json_repair, json_to_csv, csv_to_json, base64_encode, base64_decode, url_encode, url_decode, url_parse, hash
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-nutshell2000-agent-data-tools-utilities-8cdd397c)