Skip to content

FreshProof MCP server

io.github.ricksporto/freshproofricksportostreamable-httpv1.0.0Scanned

Timestamped public URL observations with SHA-256 fingerprints, paid in USDC on Base via x402.

4 tools: 3 change things and 1 only read.

Tools: 0 delete, 0 irreversible, 3 write, 1 read.
  • Reads private data · 0
  • Reads text others write · 2
  • Can send data out · 2
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

3 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the FreshProof MCP server can do

The FreshProof MCP server is published by the GitHub account ricksporto. It has 4 tools. It can create or change data (3 tools: verify_proof, observe_url and verify_url), but cannot delete data. 1 tool only reads.

2 tools bring in text other people can write (observe_url and verify_url); 2 tools can send data out of your system (observe_url and verify_url).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 20, 2026, version 1.0.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

4 tools

Changes things 3Claude Code: ask
  • observe_urlBuy a timestamped FreshProof observation of a public HTTP/HTTPS URL.Reads text others writeCan send data outNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Buy a timestamped FreshProof observation of a public HTTP/HTTPS URL. Returns final URL, observation timestamp, age, HTTP status, SHA-256 body hash, body size, ETag, Last-Modified, fetch duration, and whether the observation came from shared cache or a fresh public-network request. Set max_age=0 when a new public-network request is required. The response body itself is not returned.

    Annotations the server declares

    • title: Observe Public URL
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • verify_proofVerify an existing FreshProof Proof Receipt without making a new network request.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Verify an existing FreshProof Proof Receipt without making a new network request. This free tool checks deterministic receipt integrity and optionally evaluates trust policy rules. Use it when you already have a proof_id from observe_url or verify_url and want to re-check evidence without paying for another observation. The result includes valid, decision (PASS, FAIL, or UNKNOWN), per-rule checks, and the stored receipt.

    Annotations the server declares

    • title: Verify FreshProof Proof
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • verify_urlVerify what is observable at a public URL before an agent trusts, pays, or acts.Reads text others writeCan send data outNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Verify what is observable at a public URL before an agent trusts, pays, or acts. This paid tool combines observe_url and verify_proof in one call: it buys an observation, creates or returns a Proof Receipt, and evaluates the supplied trust policy. Set max_age=0 when current public-network evidence is required. The result contains both observation evidence and verification with decision PASS, FAIL, or UNKNOWN.

    Annotations the server declares

    • title: Observe and Verify URL
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
Only reads 1Show 1 read-only tool
  • freshproof_infoDescribe FreshProof, its observation semantics, current MCP price and payment network.No findings

    Why it is in this group

    • The description's first verb is "describe": a word for reading.
    Description, as the server wrote it
    Describe FreshProof, its observation semantics, current MCP price and payment network. This tool is free.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write2
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out2
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:10 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
3
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://freshproof.ricardobessellp-11d.workers.dev/mcp: tools/list returned 4 tools to an anonymous client, including verify_proof (write), observe_url (write), verify_url (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http freshproof https://freshproof.ricardobessellp-11d.workers.dev/mcp
claude mcp add --transport http freshproof https://freshproof.ricardobessellp-11d.workers.dev/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__freshproof__freshproof_info"
    ],
    "ask": [
      "mcp__freshproof__verify_proof",
      "mcp__freshproof__observe_url",
      "mcp__freshproof__verify_url"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as freshproof. Review it before you use it.

Capability tags behind 2 rules
  • mcp__freshproof__observe_url untrusted-input, outbound
  • mcp__freshproof__verify_url untrusted-input, outbound

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.github.ricksporto/freshproof/verify?hash=6d1324cdcf73135efdbe0d53ec48eceabe55c2e57454629905712afd0233defa" | jq -e '.changed == false'

Pinned hash 6d1324cdcf73, from Nov 20, 2026, 10:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.ricksporto/freshproof/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.ricksporto/freshproof
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.ricksporto/freshproof.svg)](https://radar.anlyon.com/servers/io.github.ricksporto/freshproof)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:46 UTC.

FreshProof MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the FreshProof MCP server safe?

No scan can promise that. What its definitions show: 4 tools, 3 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the FreshProof MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the FreshProof MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the FreshProof MCP server have?

4 tools: 3 write, 1 read. verify_proof, observe_url, verify_url and freshproof_info.

Does the FreshProof MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the FreshProof MCP server send data to outside services?

2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): observe_url and verify_url.

Has the FreshProof MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.