fetchgate MCP server
dev.fetchgate/fetchgatefetchgate.devstreamable-httpv0.1.0Scanned
Fetch any URL as clean Markdown or metadata, and buy digital goods via x402 — for AI agents.
10 tools: 4 change things and 6 only read.
- Reads private data · 2
- Reads text others write · 5
- Can send data out · 5
- 2 findings
Tools listed without sign-in. Remote posture
With Anlyon
4 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.
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 fetchgate MCP server can do
The fetchgate MCP server is published by fetchgate.dev, a domain the MCP Registry verified. It has 10 tools. It can create or change data (4 tools: scan_for_prompt_injection, check_x402_endpoint, check_base_token and scan_mcp_server), but cannot delete data. 6 tools only read.
2 tools read private data (list_products and get_agent_census); 5 tools bring in text other people can write (read_url, get_metadata, list_products and 2 more); 5 tools can send data out of your system (read_url, get_metadata, scan_for_prompt_injection and 2 more). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
The fixed checks matched 2 findings (tool-shadowing and credentials-mention). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 15, 2026, version 0.1.0.
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.
10 tools
Changes things 4Claude Code: ask
check_base_tokenScreen a token contract on Base before an agent buys it.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.
Description, as the server wrote it Screen a token contract on Base before an agent buys it. Reads the contract (ERC-20 metadata, owner, upgradeable proxy, and mint / pause / blacklist / fee selectors in its bytecode) and its DEX liquidity (WETH and USDC held by its Uniswap and Aerodrome pools, read on-chain). Returns a verdict — ok, caution, avoid or unknown — with the reasons. A heuristic screen: it does not simulate a sell, read tax rates or check pool age. Wraps GET /v1/token/check. Same free daily tier as read_url; $0.01/call via x402 after that.
check_x402_endpointDecide whether an unfamiliar pay-per-call (x402) endpoint is worth paying.Can 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.
What it can reach
- 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 Decide whether an unfamiliar pay-per-call (x402) endpoint is worth paying. Sends one unpaid GET to read its live payment challenge (format, price, network, signing domain), then adds its settled-call and unique-payer history, whether its live price matches its listed price, and its domain's reputation (template farm or not, share of its endpoints that answer). Returns a verdict — ok, caution, avoid or unknown — with the reasons. Nothing is paid. Use before an agent sends money to an endpoint it has not used before. Wraps GET /v1/x402/check. Same free daily tier as read_url; $0.01/call via x402 after that.
scan_for_prompt_injectionCheck untrusted content BEFORE acting on it.Can send data out1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Warn
The description contains "override, tool", wording about other tools or servers.
What this check looks forMatched text
description: "...20 detection rules covering instruction override, tool hijacking, data exfiltration, system-pr..."
Description, as the server wrote it Check untrusted content BEFORE acting on it. Give a `url` to fetch and scan a web page (its visible text and, separately, text hidden in HTML comments, alt/title/aria attributes and meta tags), or give `text` to scan a tool result, retrieved document or message you already have. Runs 120 detection rules covering instruction override, tool hijacking, data exfiltration, system-prompt extraction, jailbreak framing and encoding tricks (zero-width and Unicode-tag smuggling, homoglyphs, base64). Returns a 0-100 risk score, a recommended action (block / review / flag / none) and each match with its evidence. Heuristic: a clean result means nothing obvious tripped, not that the content is safe. Wraps /v1/scan. Same free daily tier as read_url; $0.003/call via x402 after that.
scan_mcp_serverConnect to a remote Streamable HTTP MCP server, fetch its tools/list (sends only initialize, notifications/initialized and tools/list — never tools/call) and scan every tool name, …Can send data out1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "...Unicode, directives aimed at the model, credential/secret references, exfiltration shapes..."
Description, as the server wrote it Connect to a remote Streamable HTTP MCP server, fetch its tools/list (sends only initialize, notifications/initialized and tools/list — never tools/call) and scan every tool name, description, parameter description and the server's initialize `instructions` string for tool-poisoning patterns: hidden-instruction markers, invisible Unicode, directives aimed at the model, credential/secret references, exfiltration shapes and instructions about other tools. Returns per-tool findings with severity, excerpt and a score band. Use it before installing or trusting a third-party server. Heuristic: a clean result means nothing obvious in what the server declares about itself, not that it is safe. Wraps GET /v1/mcp-scan. Free, rate-limited per caller; private/internal-network hosts are rejected.
Only reads 6Show 6 read-only tools
get_agent_censusReturn the Agent Web Crawler Census: every named bot observed crawling a live, publicly-listed x402 + MCP endpoint over a 24-hour window, each with a case-insensitive regex `matche…Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_agent_census" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "return" and "directory": it reads files.
- untrusted-inputThe description's first sentence says "return" and "web": it reads web pages, which anyone can write.
Description, as the server wrote it Return the Agent Web Crawler Census: every named bot observed crawling a live, publicly-listed x402 + MCP endpoint over a 24-hour window, each with a case-insensitive regex `matcher` and a behavioural `category` (liveness-monitor, directory-crawler, price-scraper, security-research, ai-training, ...) so you can classify your own access log. Observed first-hand, not aggregated from third-party bot lists. Notable finding: of the named agent-web crawlers in the census, zero have ever presented a payment, and several declare that in their own User-Agent string. Wraps GET /v1/agent-census.json. Free, unmetered, no payment required. CC BY 4.0.
get_metadataFetch a URL server-side and return structured metadata: title, description, canonical URL, OpenGraph/Twitter card fields, favicon URL, language, and published/modified timestamps w…Reads text others writeCan send data outNo findings
Why it is in this group
- The name "get_metadata" says "get": a word for reading.
What it can reach
- 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.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Fetch a URL server-side and return structured metadata: title, description, canonical URL, OpenGraph/Twitter card fields, favicon URL, language, and published/modified timestamps when present. Wraps GET /v1/meta. Same free tier as read_url; priced at $0.001/call via x402 once exhausted.
get_purchase_infoLook up a product by id (from list_products) and explain exactly how to buy it: its price, and the x402 purchase flow step by step (the 402 challenge shape, the PAYMENT-SIGNATURE h…Reads text others writeNo findings
Why it is in this group
- The name "get_purchase_info" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
Description, as the server wrote it Look up a product by id (from list_products) and explain exactly how to buy it: its price, and the x402 purchase flow step by step (the 402 challenge shape, the PAYMENT-SIGNATURE header, and the signed download URL you get back on success). Does not take payment itself — informational only, mirroring the pre-payment leg of GET /v1/buy/:id.
list_productsList Fetchgate's digital-goods catalog: id, name, description, priceUsd, currency, file format, size, sha256, and a walletless humanUrl checkout link for each product for sale.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "list_products" says "list": a word for reading.
What it can reach
- private-dataThe description's first sentence says "list" and "file": it reads files.
- untrusted-inputThe description's first sentence says "list" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it List Fetchgate's digital-goods catalog: id, name, description, priceUsd, currency, file format, size, sha256, and a walletless humanUrl checkout link for each product for sale. Wraps GET /v1/products. Free, no rate limit, no payment required just to browse.
read_urlFetch a URL server-side and return its main content as clean Markdown, with scripts/styles/nav/ads/boilerplate stripped out.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "read_url" says "read": a word for reading.
What it can reach
- untrusted-inputThe name "read_url" says "read" and "url": it reads web pages, which anyone can write.
- 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.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Fetch a URL server-side and return its main content as clean Markdown, with scripts/styles/nav/ads/boilerplate stripped out. Wraps GET /v1/read. Free tier: 30 calls/day per caller; priced at $0.002/call via x402 once that's exhausted (see get_purchase_info for how the x402 flow works). Only http:// and https:// URLs are accepted; private/internal-network hosts are rejected.
search_x402_servicesSearch for a pay-per-call (x402) API that does what you need.No findings
Why it is in this group
- The name "search_x402_services" says "search": a word for reading.
Description, as the server wrote it Search for a pay-per-call (x402) API that does what you need. Unlike a raw directory, results are limited to endpoints that answered a real x402 payment challenge AND had at least 5 settled calls from at least 2 distinct payers in the last 30 days, so dead, never-bought and template-farm listings are left out. Each result has the endpoint URL, method, price in USD, networks, 30-day calls and unique payers, and a flag when the payer count looks farmed. Use it when you need a paid API (search, scraping, enrichment, LLM, market data…) and want one that demonstrably works. Wraps GET /v1/x402/search. Same free daily tier as read_url; $0.005/call via x402 after that.
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.
50 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 2 private-data tools breaks every one.
- Reads private data2
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write5
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out5
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__fetchgate__get_agent_census",
"mcp__fetchgate__list_products"
]
}
}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, 18:52 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
- 4
- 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 4 tools that change things (4 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://fetchgate.dev/mcp: tools/list returned 10 tools to an anonymous client, including scan_for_prompt_injection (write), check_x402_endpoint (write), check_base_token (write), scan_mcp_server (write)
Findings
Matches of fixed checks, with the text they matched.
The description contains "override, tool", wording about other tools or servers.
What this check looks forMatched text
description: "...20 detection rules covering instruction override, tool hijacking, data exfiltration, system-pr..."
- Infoscan_mcp_server
The description mentions "credential".
What this check looks forMatched text
description: "...Unicode, directives aimed at the model, credential/secret references, exfiltration shapes..."
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 0.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http fetchgate https://fetchgate.dev/mcpclaude mcp add --transport http fetchgate https://fetchgate.dev/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__fetchgate__list_products",
"mcp__fetchgate__get_purchase_info",
"mcp__fetchgate__get_agent_census",
"mcp__fetchgate__search_x402_services"
],
"ask": [
"mcp__fetchgate__read_url",
"mcp__fetchgate__get_metadata",
"mcp__fetchgate__scan_for_prompt_injection",
"mcp__fetchgate__check_x402_endpoint",
"mcp__fetchgate__check_base_token",
"mcp__fetchgate__scan_mcp_server"
],
"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 fetchgate. Review it before you use it.
Capability tags behind 8 rules
- mcp__fetchgate__read_url untrusted-input, outbound
- mcp__fetchgate__get_metadata untrusted-input, outbound
- mcp__fetchgate__list_products private-data, untrusted-input
- mcp__fetchgate__get_purchase_info untrusted-input
- mcp__fetchgate__get_agent_census private-data, untrusted-input
- mcp__fetchgate__scan_for_prompt_injection outbound
- mcp__fetchgate__check_x402_endpoint outbound
- mcp__fetchgate__scan_mcp_server 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/dev.fetchgate/fetchgate/verify?hash=f8a08a1e85af7fd9a3e5fbae365a2caca062a9acc9d317dcd7b915350657886a" | jq -e '.changed == false'Pinned hash f8a08a1e85af, from Nov 15, 2026, 01:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/dev.fetchgate/fetchgate/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/dev.fetchgate/fetchgate)Source: MCP Registry. Synced Oct 21, 2026, 18:11 UTC.
fetchgate MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the fetchgate MCP server safe?
- No scan can promise that. What its definitions show: 10 tools, 4 of which can change, send or delete something, and 2 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 fetchgate MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the fetchgate 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 fetchgate MCP server have?
- 10 tools: 4 write, 6 read. scan_for_prompt_injection, check_x402_endpoint, check_base_token, scan_mcp_server, read_url, get_metadata, list_products, get_purchase_info and 2 more.
Does the fetchgate MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the fetchgate MCP server send data to outside services?
- 5 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): read_url, get_metadata, scan_for_prompt_injection, check_x402_endpoint and scan_mcp_server.
Has the fetchgate MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 15, 2026.