FRESH — Shared URL Freshness Intelligence
Server Details
Decide whether an agent should reuse cached URL knowledge or fetch the resource again.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- Repository
- GSterlingPress/fresh-api
- GitHub Stars
- 0
- Server Listing
- FRESH
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 2 tools
The two tools have clearly distinct roles: one is for pre-retrieval status checking, the other for post-retrieval metadata observation. No overlap or ambiguity exists between them.
Both tools follow the same 'fresh_' prefix with a descriptive verb ('check' and 'observe'), creating a consistent and predictable naming pattern.
With only two tools, the set is on the thin side but appropriately scoped for a very focused freshness utility. It does not feel excessively sparse, though it is minimal.
The tool pair covers the full lifecycle of freshness handling: check before retrieval and observe after retrieval. No obvious dead ends or missing operations within this narrow domain.
Available Tools
2 toolsfresh_checkShould I Fetch This URL Again?ARead-onlyIdempotentInspect
Return REUSE, REFETCH, or UNKNOWN before retrieving a URL again.
Inputs: url (required), lastSeenAt (required), toleranceSeconds.
fresh_observeReport URL ObservationBInspect
Report privacy-safe freshness metadata from a completed retrieval.
Inputs: url (required), etag, observedAt, contentHash, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Preflight a short or unknown URL before your agent fetches it. Returns next: fetch or skip.
Whether an AI agent may fetch a URL, on what terms, and at what price. Free, no key, no signup.
Policy-aware web access preflight: robots, licensing, payment and advertised routes for agents.
URL reality check for agents: status, content hash, classification, wayback fallback.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceProvides pre-fetch routing intelligence for AI agents by recommending the cheapest reliable route (HTTP, browser, machine endpoint, or avoid) before visiting a URL.-
- FlicenseNot gradedqualityDmaintenanceA shared distillation cache for AI agents — clean-crawl a URL once, distill it to token-optimal markdown, and serve it content-addressed across every agent (~73–89% fewer tokens). Includes a collective-notes layer and cutoff-aware change detection.-
- AlicenseNot gradedqualityDmaintenanceAnalyzes, generates, simulates, and optimizes caching strategies across HTTP, CDN, and browser layers for AI agents.40 npmMIT
- FlicenseNot gradedqualityBmaintenanceEnables AI agents to check and contribute recent observations of source-backed facts, reducing redundant revalidation of unchanged information.-
Glama MCP Gateway
Add one secure layer between your agents and this server.