MCP.Market

Fresh402 Agent Intelligence MCP server

online · 100% uptime
by kirillradchenko96·io.github.kirillradchenko96/fresh402·v3.0.3

Persistent web/Base observations and recoverable results. Free Register, 7 paid tools; REST/MCP.

B75/100grade B
What users say
No reviews yet
Be the first
Safety scan
B75/100

not scanned yet

Adoption
Growing

0 stars

Reviews

Write one

Nobody has reviewed Fresh402 Agent Intelligence yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Fresh402 Agent Intelligence tools

Tool list not cached yet. `describe` through the gateway fetches it live.

Not scanned yet. New listings are scanned within a day or two of arriving.

How Fresh402 Agent Intelligence compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
75/100
higher than 45% of 4,460 AI and agents servers
Uptime
100%
of our recent checks; the typical remote AI and agents server answers 100%
Response time
410 ms
faster than 34% of 2,331 AI and agents servers

Release history: 7 versions in the registry since 2026-10-07, latest 2026-10-31, typically one every 3 days.

Install Fresh402 Agent Intelligence in Claude Code, Cursor or VS Code

claude mcp add --transport http fresh402 https://api.fresh402.com/mcp
Add to Cursor

What the publisher says

From the Fresh402 Agent Intelligence repository's README, as published. We do not edit it. Read it on GitHub

Fresh402 v2.2 — Web Intelligence API for AI Agents

Check whether a source changed, extract usable content, and compare structured snapshots. Pay per call with x402 USDC on Base.

The hosted production API reports 2.2.0. Connect at fresh402.kirilllabs.workers.dev or its MCP endpoint. This documentation describes the hosted service; the repository's legacy implementation and backend release PR are maintained separately. A documentation release does not deploy the service.

Choose the operation

  • Register once to establish a persistent baseline and receive a watch_id. Re-registering the same watch returns its existing baseline without loading the target again.
  • Check before reusing a web source or spending on downstream browsing and reasoning. Get a change signal, noise filtering, conditional HTTP revalidation and an optional compact deterministic text diff. A cached Check is still a paid operation.
  • Extract when an agent needs content for retrieval: text, titles, metadata, headings, links and JSON-LD from public HTML, JSON or text, with optional CSS scoping.
  • Smart Diff when the change itself matters: compare a watch with its previous Smart Diff snapshot or fixed baseline, get structured additions/removals/modifications, and inspect significance scores with explainable deterministic rules.

Requests fetch eligible public HTTPS sources on demand. Fresh402 does not execute page JavaScript, render a browser, access authenticated sites, perform LLM-powered semantic analysis, continuously poll watches, or send push alerts. Security checks and rate, size, concurrency and operation limits apply; capacity failures may require a later retry.

Start with discovery

  • Live OpenAPI 3.1 reference: current request schemas, examples, response formats and payment headers.
  • API guide, MCP integration, pricing, request examples.
  • x402 resource manifest, agent guide, release notes.
  • Official MCP Registry: the existing identity is io.github.kirillradchenko96/fresh402.
  • Discovery audit: externally verified catalog status and outstanding reindexing or authorization requirements.

Free service metadata and MCP initialize / tools/list let a new agent learn all four tools without paying or fetching a target.

REST quick start

Register a baseline for free:

curl https://fresh402.kirilllabs.workers.dev/v1/register \
  -H 'Content-Type: application/json' \
  -d '{"url":"https://example.com/"}'

Use the returned watch_id in a Check or Smart Diff. The following unsigned request retrieves payment requirements, not a paid result:

curl -i https://fresh402.kirilllabs.workers.dev/v2/extract \
  -H 'Content-Type: application/json' \
  -d '{"url":"https://example.com/","max_chars":20000}'

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Fresh402 Agent Intelligence: common questions

Is Fresh402 Agent Intelligence MCP server safe?
Mostly: it is graded B (75/100). Read the Fresh402 Agent Intelligence safety report
How do I install Fresh402 Agent Intelligence?
It runs remotely at api.fresh402.com. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Fresh402 Agent Intelligence need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Fresh402 Agent Intelligence maintained?
The last commit was 23 days ago (2026-10-12). The latest release is v3.0.3.
Is Fresh402 Agent Intelligence up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
What can I use instead of Fresh402 Agent Intelligence?
Servers from other publishers that do the same job: agent-device MCP server, IWE (iwe.md) MCP server and Memanto MCP server.
How does Fresh402 Agent Intelligence compare with other AI and agents MCP servers?
safety score 75/100 (higher than 45% of 4,460 AI and agents servers); uptime 100% (of our recent checks; the typical remote AI and agents server answers 100%); response time 410 ms (faster than 34% of 2,331 AI and agents servers). Full comparison.

Alternatives to Fresh402 Agent Intelligence

Same job from other publishers: the closest match first, then the best rated.

  • agent-device
    Open source device layer for AI agents: control mobile, web, TV, and desktop apps over MCP
    A
  • IWE (iwe.md)
    Markdown knowledge base as agent memory. Runs against the notes directory it is started in.
    A
  • Memanto
    MCP server for Memanto - persistent semantic memory for any MCP-compatible agent
    A
  • World Model MCP
    Persistent 3D/2D spatial world model for AI agents with dynamic velocity and entity tracking.
    A
  • Mockserver
    Mock, record/replay, verify and chaos-test any HTTP, REST, gRPC or LLM dependency over MCP.
    A