ProofFetch — Cited Web Evidence MCP server
io.github.equinoxaifinance-rgb/proof-fetchequinoxaifinance-rgbstreamable-httpv0.3.1Scanned
Web pages your agent can quote: 1,000 full fetches a month free, no card, then $0.01 a page.
3 tools: 1 change things and 2 only read.
- Reads private data · 0
- Reads text others write · 2
- Can send data out · 2
- 3 findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here changes things. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
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 ProofFetch — Cited Web Evidence MCP server can do
The ProofFetch — Cited Web Evidence MCP server is published by the GitHub account equinoxaifinance-rgb. It has 3 tools. It can create or change data (1 tool: proof_fetch_evidence), but cannot delete data. 2 tools only read.
2 tools bring in text other people can write (proof_fetch_preflight and proof_fetch_evidence); 2 tools can send data out of your system (proof_fetch_preflight and proof_fetch_evidence).
The fixed checks matched 3 findings (credentials-mention and annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.
Last scanned Nov 10, 2026, version 0.3.1.
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.
3 tools
Changes things 1Claude Code: ask
proof_fetch_evidenceFetch a public URL and return its cited, paragraph-addressable text with integrity hashes and a receipt.Reads text others writeCan send data out2 findings
Why it is in this group
- The name "proof_fetch_evidence" says "fetch": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "fetch" and "url": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Info
The input schema at properties.url.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.url.description: "...Not a search phrase or placeholder. No credentials, private networks, authenticated pages..."
- Warn
The server marks "proof_fetch_evidence" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "proof_fetch_evidence" says "fetch": a word for reading.
Description, as the server wrote it Fetch a public URL and return its cited, paragraph-addressable text with integrity hashes and a receipt. Uses one credit from a ProofFetch key, and only when extraction succeeds. Needs the key sent as the MCP request header Authorization: Bearer <key>: a free key holds 1,000 extractions (no card, POST /v1/keys/free or the ProofFetch home page); a paid key holds 500 for $5.00 (sold on the ProofFetch home page). Example: {"url":"https://example.com/"}.
Annotations the server declares
- title: Get cited page text (uses a key credit)
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Only reads 2Show 2 read-only tools
proof_fetch_offerReturns the offer and request schema without buying.No findings
Why it is in this group
- The name "proof_fetch_offer" says "fetch": a word for reading.
Description, as the server wrote it Returns the offer and request schema without buying. Full cited text: 1,000 free extractions with a free key (no card), then $0.01 a page either way: a 500-page card pack for $5, or $0.50 per Stripe MPP call, which returns the page plus an API key holding 49 more. Cited text uses POST /v1/evidence with a caller-generated idempotency key. Example arguments: {}.
Annotations the server declares
- title: Show the offer and prices
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
proof_fetch_preflightFree: checks a public URL and returns fetchability, provenance, hashes, deterministic injection indicators and a free preview of the first 1,000 or so characters of text (short pag…Reads text others writeCan send data out1 finding
Why it is in this group
- The name "proof_fetch_preflight" says "fetch": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Findings
- Info
The input schema at properties.url.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.url.description: "...Not a search phrase or placeholder. No credentials, private networks, authenticated pages..."
Description, as the server wrote it Free: checks a public URL and returns fetchability, provenance, hashes, deterministic injection indicators and a free preview of the first 1,000 or so characters of text (short pages come back whole); not a safety guarantee. No payment or purchase. Example: {"url":"https://example.com/","maxChars":30000}.
Annotations the server declares
- title: Check a public page (free)
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
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.
Looked at Nov 20, 2026, 19:21 UTC, unchanged since Nov 20, 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
- 2
- 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 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://prooffetch.steellantern.com/mcp: tools/list returned 5 tools to an anonymous client, including proof_fetch_evidence (write), proof_fetch_crawl (write)
Posture changes
- Nov 20, 2026
- Tools that change things, listed without credentials: 1 to 2
Findings
Matches of fixed checks, with the text they matched.
The server marks "proof_fetch_evidence" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "proof_fetch_evidence" says "fetch": a word for reading.
The input schema at properties.url.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.url.description: "...Not a search phrase or placeholder. No credentials, private networks, authenticated pages..."
The input schema at properties.url.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.url.description: "...Not a search phrase or placeholder. No credentials, private networks, authenticated pages..."
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Tools that change things, listed without credentials: 1 -> 2.View diff
- Tools that change things, listed without credentials: 1 to 2
Tools2 changed.~2 changedView diff
- Changed:proof_fetch_evidenceChanges thingsinputSchema
- Changed:proof_fetch_preflightOnly readsinputSchema
Tools2 changed.~2 changedView diff
- Changed:proof_fetch_evidenceChanges thingsdescriptioninputSchema
- Changed:proof_fetch_offerOnly readsdescription
Install
Pinned to version 0.3.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http proof-fetch https://prooffetch.steellantern.com/mcpclaude mcp add --transport http proof-fetch https://prooffetch.steellantern.com/mcpRun 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.
{
"permissions": {
"allow": [
"mcp__proof-fetch__proof_fetch_offer"
],
"ask": [
"mcp__proof-fetch__proof_fetch_preflight",
"mcp__proof-fetch__proof_fetch_evidence"
],
"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 proof-fetch. Review it before you use it.
Capability tags behind 2 rules
- mcp__proof-fetch__proof_fetch_preflight untrusted-input, outbound
- mcp__proof-fetch__proof_fetch_evidence 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.equinoxaifinance-rgb/proof-fetch/verify?hash=e5e3d82de0139889107b22e6efbb0c9020caf7facccc2f7526841789c116b5d0" | jq -e '.changed == false'Pinned hash e5e3d82de013, from Nov 10, 2026, 20:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.equinoxaifinance-rgb/proof-fetch/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.equinoxaifinance-rgb/proof-fetch)Source: MCP Registry · repository. Synced Oct 29, 2026, 11:17 UTC.
ProofFetch — Cited Web Evidence MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the ProofFetch — Cited Web Evidence MCP server safe?
- No scan can promise that. What its definitions show: 3 tools, 1 of which can change, send or delete something, and 3 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 ProofFetch — Cited Web Evidence MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the ProofFetch — Cited Web Evidence 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 ProofFetch — Cited Web Evidence MCP server have?
- 3 tools: 1 write, 2 read. proof_fetch_evidence, proof_fetch_preflight and proof_fetch_offer.
Does the ProofFetch — Cited Web Evidence MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the ProofFetch — Cited Web Evidence 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): proof_fetch_preflight and proof_fetch_evidence.
Has the ProofFetch — Cited Web Evidence MCP server changed its tools?
- Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 10, 2026. Every change is on this page and in its Atom feed.