offweb: gemini, gopher and ipfs fetch for agents
Server Details
Fetch gemini://, gopher:// and ipfs:// URLs for agents. Hosted, signed receipt, x402 per call.
- 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 have entirely separate purposes: `fetch` performs the network retrieval, while `about` returns static operator/identity/limits metadata. There is no realistic way for an agent to confuse them, and the descriptions reinforce the split.
Both names are lowercase single words, but `fetch` is an action verb while `about` is an informational/meta label, so there is no consistent verb_noun pattern across the set. With only two tools this stays readable, but the convention is mixed rather than predictable.
Two tools is on the thin side even for a narrowly scoped offweb proxy: one operational tool plus one static info tool. The scope justifies a small surface, but there is no room for even modest variations (e.g. binary fetch or URL validation) without adding tools.
The core lifecycle for a single text fetch is covered, including explicit refusal semantics and a receipt, but the surface is notably limited: text only, 1 MiB cap with no truncation/pagination control, no binary or multi-URL support, and receipt verification relies solely on the key exposed by `about`.
Available Tools
2 toolsaboutWho runs offweb and what the receipt meansBInspect
Operator identity (Ley 34/2002 art. 10), the receipt public key, limits and the responsibility boundary.
Inputs: no named parameters. Returns: result
fetchFetch a gemini://, gopher:// or ipfs:// URLAInspect
Fetch one URL on a network HTTP agents cannot reach (gemini://, gopher://, ipfs://, ipns://) and return the text verbatim, plus an Ed25519 receipt that offweb fetched this URL at this time and got these bytes. Text only, 1 MiB cap. Refusals carry an error and nothing is fetched.
Inputs: url (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Related MCP Connectors
Fetch any URL as clean Markdown or metadata, and buy digital goods via x402 — for AI agents.
Read any web page (even JS sites), PDFs, tables, RSS & screenshots for AI agents. Pay via x402.
AI agent gateway with web fetching, data extraction, crypto pricing, and x402 payments
Live uptime and source-URL verification for AI agents, with per-call x402/USDC paid endpoints.
Related MCP Servers
- FlicenseNot gradedqualityBmaintenanceEnables AI agents to reliably fetch public web URLs and extract clean, agent-ready text, Markdown, links, and metadata, with automatic browser fallback and optional x402 payment support.-
- AlicenseNot gradedqualityBmaintenanceEnables AI agents and MCP clients to inspect a URL for reachability, then extract clean structured Markdown, headings, and links from public web pages, paid per successful request via x402 micropayments with no accounts or API keys.MIT
- FlicenseNot gradedqualityCmaintenanceEnables agents to read any web page or document as markdown, html, links, screenshots or extracted JSON, map and crawl entire sites, and drive a persistent browser session that stays open between calls so pages can be inspected and clicked without reloading. Callers pay per request with a wallet over x402 — no API key or signup — and every route answers its own free GET with the fields it expects.1-

x1-baas-mcpofficial
AlicenseNot gradedqualityBmaintenanceEnables AI agents to scrape any URL through a stealth browser with anti-bot bypass, returning clean Markdown, and optionally pay per request via x402 micropayments.1MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.