Skip to main content
Glama

What it is

89 stateless utility tools that AI agents reach for constantly: URL health checks, page extraction, MCP readiness, x402 server discovery, loyalty reward quotes, JWT inspection, DNS / RDAP lookups, JSON / CSV conversion, hash / base64, cron description, and more.

  • Stateless — every call is independent; no session, no cache, no DB.

  • No API keys — fixed public providers and user-supplied public URLs; see Privacy posture for destinations.

  • Deterministic — no LLMs, no model calls, no fuzzy outputs.

  • Bounded operations — network tools use per-call timeouts, subject to resolver and parser limits described below.

  • MCP-native — agent-readiness manifest, connection status, privacy audit.

This package was extracted from the Delx Protocol MCP server so any AI builder can use the toolkit directly, without depending on the Delx runtime. The public product and protocol context lives at ontology.delx.ai/utilities.

Related MCP server: @mate-tools/mcp-server

HTTP (v2 stateless)

Not shipped. The Python FastMCP extra is stdio-only. Adding Streamable HTTP would need extra Starlette /health wiring beyond a one-flag opt-in, so it stays documented-skip (same for google-ads-intent-mcp). The tools themselves are already request-stateless.

Install

pipx install "delx-agent-utilities[mcp]"

CLI entrypoints: delx-agent-utilities, delx-utils (alias), delx-utils-mcp (MCP server).

Quick use

From an MCP client (Claude Desktop, Cursor, Hermes, OpenClaw)

{
  "mcpServers": {
    "delx-utils": {
      "command": "delx-utils-mcp"
    }
  }
}

90 tools become available immediately, plus three agent-readiness surfaces:

  • delx_utilities_manifest

  • delx_utilities_connection_status

  • delx_utilities_privacy_audit

From the CLI

delx-utils manifest
delx-utils list-tools
delx-utils show util_url_health
delx-utils call util_url_health --json '{"url":"https://example.com"}'

From Python

import asyncio
from delx_agent_utilities import call_util_tool, list_util_tool_schemas

result = asyncio.run(call_util_tool("util_url_health", {"url": "https://example.com"}))
print(result["status_code"], result["latency_ms"])

schemas = list_util_tool_schemas()
print(f"{len(schemas)} tools available")

The 90 tools

Encoding & parsing (15)

util_json_validate, util_token_estimate, util_uuid_generate, util_timestamp_convert, util_base64, util_hash, util_regex_test, util_cron_describe, util_http_codes, util_timezone_lookup, util_unit_convert, util_business_days, util_jwt_inspect, util_csv_to_json, util_json_to_csv

Web extract (6)

util_page_extract, util_open_graph, util_links_extract, util_forms_extract, util_contact_extract, util_feed_discover

Network probes (8)

util_url_health, util_robots_inspect, util_sitemap_probe, util_tls_inspect, util_security_txt_inspect, util_http_headers_inspect, util_dns_lookup, util_rdap_lookup

x402 / API intel (6)

util_x402_server_probe, util_x402_resource_summary, util_x402_server_audit, util_api_health_report, util_openapi_summary, util_mcp_server_readiness_report

Identity / contact (1)

util_email_validate

Composite reports (8)

util_website_intelligence_report, util_domain_trust_report, util_docs_site_map, util_pricing_page_extract, util_company_contact_pack, util_api_integration_readiness, util_login_surface_report, util_content_distribution_report

Commerce workflows

util_loyalty_reward_quote

Public data and identity (4)

util_vin_decode, util_wmi_decode, util_lei_lookup, util_inflation_calculator

Local text, data, and identifiers (35)

util_holidays, util_slugify, util_mime_lookup, util_color_convert, util_ip_classify, util_cidr_contains, util_ulid_generate, util_html_strip, util_semver_compare, util_word_count, util_markdown_to_text, util_duration_parse, util_case_convert, util_query_string, util_url_join, util_percent_change, util_clamp, util_luhn_check, util_isbn_check, util_diff_lines, util_levenshtein, util_similarity, util_normalize_whitespace, util_extract_urls, util_extract_emails, util_url_encode, util_hex_convert, util_number_base, util_dedupe_lines, util_sort_lines, util_random_int, util_rot13, util_text_truncate, util_reading_time, util_random_choice

Sales-led local preflights (6)

util_seeded_random_sample, util_base_gas_budget_check, util_dns_record_diff, util_http_header_diff, util_x402_payment_preflight, util_image_result_contract_check

These six preflights were selected from aggregate external Commerce sales. They are local implementations only: pricing, x402 delivery, telemetry, and refund ownership remain in Delx Commerce.

Each tool's full input schema is available via delx-utils show <tool> or UTIL_TOOL_SCHEMAS["<tool>"] in Python.

Privacy posture

No API keys. No telemetry. No stored state. Networked tools may contact:

  • rdap.org/domain/<domain> for RDAP and dns.google/resolve for DNS-over-HTTPS.

  • vpic.nhtsa.dot.gov for VIN/WMI, api.gleif.org for LEI, and api.bls.gov for CPI data.

  • Public URLs supplied by the caller and their redirects; provider redirects can also change destinations. Do not submit secrets or private data in URLs or inputs.

The pinned HTTP inspection transport uses HTTP/1.1 with validated public DNS destinations and redirects. It fails closed when the relevant HTTP_PROXY, HTTPS_PROXY, or ALL_PROXY variable is nonempty, including lowercase variants; NO_PROXY does not override this. It keeps no cookie jar, requests identity encoding (compressed responses are rejected), and limits bodies to 8 MiB per hop. util_mcp_server_readiness_report pins each public destination, rejects redirects and URL credentials, and caps each response at 200,000 bytes; injected HTTP clients are not accepted. Fixed-provider HTTP clients have their own behavior and are not covered by the pinned transport's guarantees. OS DNS and some HTTP parser reads are not subject to a strict wall-clock deadline. See NETWORK_SECURITY.md and MIGRATION.md.

Call delx_utilities_privacy_audit (or delx-utils privacy-audit) to see the full posture in JSON form before invoking any networked tool.

Architecture

src/delx_agent_utilities/
├── __init__.py          # public re-exports
├── agent.py             # manifest / status / privacy_audit
├── cli.py               # CLI argparse
├── dispatcher.py        # call_util_tool, _normalize_util_args
├── mcp_server.py        # FastMCP server
├── schemas.py           # public re-export of UTIL_TOOL_NAMES / SCHEMAS
└── _internal/           # implementation, not stable across versions
    ├── _helpers.py
    ├── _schemas.py
    ├── _tools_encoding.py
    ├── _tools_cron.py
    ├── _tools_http_codes.py
    ├── _tools_sales_led.py
    ├── _tools_web.py    # roadmap: split into web/network/x402/composite in v0.2.0
    └── _tools_jwt_csv.py

Roadmap

  • v0.2.0 — split _internal/_tools_web.py (1k LOC) into per-domain modules: _tools_web_extract.py, _tools_network.py, _tools_x402.py, _tools_composite.py.

  • Per-tool unit tests (one file per tool) replacing the smoke-only suite.

  • Further provider and transport integration tests in controlled environments.

  • Configurable per-tool timeouts via env (DELX_UTILITIES_DEFAULT_TIMEOUT_S, DELX_UTILITIES_URL_HEALTH_TIMEOUT_S, …).

Provenance

Originally part of the Delx Protocol MCP server. Extracted on 2026-05-09 as a standalone open-source package so any AI builder can use the toolkit without depending on the Delx Protocol runtime.

The Delx Protocol itself (recovery / heartbeat / identity / governance primitives) remains closed-source; this package is the open utility layer beneath it.

Contributing

PRs welcome — see CONTRIBUTING.md. Common cuts that would help:

  • New utility tools that fit the "stateless / no API keys / deterministic" rule.

  • Splitting _internal/_tools_web.py per the v0.2.0 roadmap above.

  • Per-tool unit tests.

📧 Contact & Support

License

MIT — see LICENSE.

If this toolkit helps your agent workflow, please star the repo. Stars make the project easier for other AI builders to discover and help Delx keep shipping local-first agent infrastructure.

Author

David Mosiah — @delx369 — building the protocol layer for autonomous AI agents at Delx.

Available Tools

44 tools
delx_utilities_connection_statusC

Return runtime status. No network calls.

Inputs: no named parameters.

delx_utilities_manifestB

Return the agent-readiness manifest, including the full tool list.

Inputs: client.

delx_utilities_privacy_auditB

Return the privacy posture so agents can reason about safety.

Inputs: no named parameters.

util_api_health_reportC

Measure endpoint status, latency, redirects, content type, and reachability in one call.

Inputs: arguments (required).

util_api_integration_readinessC

Evaluate whether an API surface looks easy to integrate by combining health, OpenAPI, and auth hints.

Inputs: arguments (required).

util_base64C

Encode or decode Base64 strings.

Inputs: arguments (required).

util_company_contact_packC

Build a contact pack from page contacts, forms, social links, registrar, and disclosure channels.

Inputs: arguments (required).

util_contact_extractB

Extract emails, phones, and social links from a page for outreach, routing, and support.

Inputs: arguments (required).

util_content_distribution_reportC

Summarize how a site distributes content across Open Graph, feeds, socials, and crawl surface.

Inputs: arguments (required).

util_cron_describeC

Validate and describe a cron expression in plain English. Shows next 5 scheduled runs.

Inputs: arguments (required).

util_csv_to_jsonC

Convert raw CSV into JSON rows for downstream agents, prompts, and ETL steps.

Inputs: arguments (required).

util_dns_lookupC

Resolve A, AAAA, CNAME, MX, TXT, and NS records for fast domain and delivery checks.

Inputs: arguments (required).

util_docs_site_mapC

Map a docs surface with crawl hints, docs links, feeds, and likely reference sections.

Inputs: arguments (required).

util_domain_trust_reportC

Composite trust report with TLS, security.txt, headers, RDAP, DNS, and uptime signals.

Inputs: arguments (required).

util_email_validateC

Validate an email and its domain-level delivery records before outreach, signup, or routing.

Inputs: arguments (required).

util_feed_discoverC

Find RSS, Atom, and JSON feeds so agents can subscribe instead of scrape.

Inputs: arguments (required).

util_forms_extractC

Extract forms, methods, actions, and fields for browser automation and workflow planning.

Inputs: arguments (required).

util_hashC

Hash a string with SHA-256, SHA-1, or MD5.

Inputs: arguments (required).

util_http_codesA

Look up HTTP status codes. Returns name, description, and category. Without code param, returns common codes.

Inputs: arguments (required).

util_http_headers_inspectC

Inspect security, cache, redirect, and server headers to audit a URL quickly.

Inputs: arguments (required).

util_json_to_csvB

Convert structured JSON rows into CSV for exports, spreadsheets, and handoff.

Inputs: arguments (required).

util_json_validateB

Validate and pretty-print JSON. Returns validity, errors, and formatted output.

Inputs: arguments (required).

util_jwt_inspectB

Decode JWT claims quickly for auth debugging, routing, and token inspection.

Inputs: arguments (required).

util_login_surface_reportC

Inspect auth surface signals like login forms, signup links, reset links, and security headers.

Inputs: arguments (required).

util_mcp_server_readiness_reportC

Score an MCP server for initialize, tools/list, schema hygiene, manifest discovery, and agent usability.

Inputs: arguments (required).

util_openapi_summaryC

Summarize an OpenAPI document including title, version, paths, tags, and likely auth surface.

Inputs: arguments (required).

util_open_graphC

Extract Open Graph and Twitter card fields to preview how a URL will render in feeds and agents.

Inputs: arguments (required).

util_page_extractB

Turn any URL into clean page metadata and readable text for search, routing, and summarization.

Inputs: arguments (required).

util_pricing_page_extractC

Extract pricing-page signals like plan names, free trial hints, CTA patterns, and sales routes.

Inputs: arguments (required).

util_rdap_lookupC

Fetch registrar, status, and registration dates for trust, compliance, and domain ops.

Inputs: arguments (required).

util_regex_testC

Test a regex pattern against text. Returns matches, groups, and count.

Inputs: arguments (required).

util_robots_inspectC

Read robots.txt rules and sitemap declarations before crawling or indexing a domain.

Inputs: arguments (required).

util_security_txt_inspectC

Find security.txt contacts, disclosure policy, and trust links for a domain.

Inputs: arguments (required).

util_sitemap_probeC

Check sitemap and crawl-structure hints fast to see how a site exposes crawlable structure.

Inputs: arguments (required).

util_timestamp_convertC

Convert between timestamp formats: Unix epoch, ISO 8601, and human-readable.

Inputs: arguments (required).

util_tls_inspectC

Inspect TLS issuer, subject, SANs, and expiry to check trust and renewal risk.

Inputs: arguments (required).

util_token_estimateB

Estimate token count for text. Uses word/4 heuristic (GPT-family) and char/4 (Claude-family).

Inputs: arguments (required).

util_url_healthC

Check if a URL is reachable. Returns HTTP status, latency, and key headers.

Inputs: arguments (required).

util_uuid_generateC

Generate one or more UUIDv4 strings.

Inputs: arguments (required).

util_website_intelligence_reportC

Composite website intelligence report with page, social, link, form, feed, and contact signals.

Inputs: arguments (required).

util_x402_resource_summaryC

Summarize a server's .well-known/x402 resources, pricing surface, networks, and paths.

Inputs: arguments (required).

util_x402_server_auditC

Audit an x402 server with discovery, pricing, reliability, and documentation readiness signals.

Inputs: arguments (required).

util_x402_server_probeC

Probe an x402 server end-to-end: discovery, status, tools, reliability, and OpenAPI.

Inputs: arguments (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    C2.7/5.0

    Scored across 44 tools

    Disambiguation4/5

    Most tools have distinct purposes, such as DNS lookup vs. RDAP lookup, but some overlap exists (e.g., util_url_health and util_api_health_report both check reachability). Descriptions are clear enough to differentiate, but agents may occasionally confuse similar-sounding tools.

    Naming Consistency3/5

    Names follow a loose snake_case pattern but mix prefixes (delx_utilities_ vs. util_) and vary in structure (e.g., util_base64 vs. util_api_health_report). Some are noun-only, others combine domain and action, leading to moderate inconsistency.

    Tool Count3/5

    44 tools is on the high side for a single server. While the server aims to provide a broad utility set, the large number may overwhelm agents and increase selection errors. It is borderline excessive for typical use.

    Completeness3/5

    The tool set covers many web-focused utilities (HTTP, DNS, security, page extraction) but lacks general-purpose tools like string manipulation, math, or advanced data transformation. Gaps exist for operations beyond web analysis, leaving the surface partially incomplete.

    Maintenance

    ActivityMaintained
    ResponsivenessLimited data

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      A
      quality
      C
      maintenance
      Swiss-army-knife utility MCP server for AI agents. 18 tools for JSON validation/formatting, base64 encode/decode, hash generation, UUID generation, URL parsing, regex testing, markdown↔HTML conversion, text stats, slug generation, datetime conversion, cron parsing, text diffing, CSV↔JSON conversion, and JWT decoding. Zero API Key required
      18
      5
      -
    • A
      license
      A
      quality
      D
      maintenance
      MCP server providing 35 utility tools for AI agents including text analysis, encoding, hashing, password generation, JSON/CSV/XML parsing, regex, color, date, finance, URL metadata, SEO tags, DNS lookup, SSL inspection, and JWT decoding. Free, zero-dependency, and works with any MCP client.
      35
      64 npm
      MIT