Darwin-owned Public Sources
Server Details
Free bounded public HTTPS document and JSON reads. Exact host allowlist; real source provenance.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 2 tools
The two tools are cleanly separated by payload type: non-JSON static documents (HTML/Markdown/plain text) versus JSON. An agent can pick the correct tool purely from the target URL's content type, with no overlapping behavior.
Both follow a predictable read_official_<qualifier> snake_case pattern, which is easy to scan. The only minor wrinkle is that 'document' names a content category while 'json' names a format, so the parallel isn't perfectly symmetric (e.g. read_official_text would be tighter).
Two tools is on the thin side by general standards, but the server's purpose is deliberately narrow (allowlisted read-only fetching), so each tool earns its place. It sits at the borderline of minimal rather than comfortably scoped.
Core read coverage for text/HTML/Markdown and JSON is present with integrity metadata, but there is no way to enumerate the allowlisted hosts or discover sources, and no handling for common official-document formats like PDF. Agents must already know exact URLs and formats, which is a notable gap for a 'public sources' server.
Available Tools
2 toolsread_official_documentARead-onlyIdempotentInspect
Read an anonymous public HTTPS HTML, Markdown or plain-text document from the explicit official-source host allowlist. Returns actual static text, anchor URLs, final URL, retrieval time and raw response SHA256. No JavaScript rendering, search, research conclusion, login or paywall bypass. Complete within bounded source/output limits; otherwise fails without truncating. Free Darwin-owned hosting; no provider key required.
Inputs: url (required). Returns: text, links, format, status, +10 more
read_official_jsonARead-onlyIdempotentInspect
Read an anonymous public HTTPS JSON document from the explicit official-source host allowlist. Returns original decoded jsonText preserving numeric lexemes, final URL, retrieval time and raw response SHA256. No business data is inferred; duplicate keys and invalid JSON fail. No credentials, purchases or auth/paywall bypass. Free Darwin-owned hosting; no provider key required.
Inputs: url (required). Returns: text, links, format, status, +10 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
URL to Markdown or structured JSON (schema.org/OG); renders SPA; batch reads. No signup/key.
Free public web freshness and response-metadata checks for AI agents.
Read any web page as Markdown or JSON, map sites, run batches, watch pages. Blocked pages are free.
Read any public web page as clean text, and files of public GitHub repositories. Free, no key.
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables read-only retrieval of a public site's overview metadata and internal links, plus cleaned text from selected public pages, while rejecting requests to other hosts.2MIT
- AlicenseNot gradedqualityDmaintenanceProvides authenticated, rate-limited file reading, directory listing, and HTTPS fetching with strict path and domain allowlists.MIT
- AlicenseNot gradedqualityCmaintenanceEnables read-only retrieval of public site overview details and individual public page text, including page titles, meta descriptions, and on-site links, while rejecting other hosts and stripping scripts.MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI clients to read public webpages as Markdown or HTML, discover links, extract structured JSON, and perform bounded crawls.AGPL 3.0
Glama MCP Gateway
Add one secure layer between your agents and this server.