ReadGZH MCP server
io.github.sweesama/readgzhsweesamastreamable-httpv1.0.0Scanned
Read WeChat public account articles via MCP. 99.89% anti-scraping success, 50-87% token compression.
5 tools: 5 only read.
- Reads private data · 5
- Reads text others write · 5
- Can send data out · 1
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
Decide which of this server's tools your agent can use.
- 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 ReadGZH MCP server can do
The ReadGZH MCP server is published by the GitHub account sweesama. It has 5 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.
5 tools read private data (readgzh.read, readgzh.list, readgzh.search and 2 more); 5 tools bring in text other people can write (readgzh.read, readgzh.list, readgzh.search and 2 more); 1 tool can send data out of your system (readgzh.read). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
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.
5 tools
Only reads 5Show 5 read-only tools
readgzh.getGet a cached WeChat article by its short slug/URL path via ReadGZH.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "readgzh.get" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "get" and "chat": it reads messages.
- untrusted-inputThe description's first sentence says "get" and "chat": it reads messages, which other people can write.
Description, as the server wrote it Get a cached WeChat article by its short slug/URL path via ReadGZH. Use when you have a slug like 'minicpm-o-4-5' from a previous read.
readgzh.listList recently cached WeChat articles via ReadGZH.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "readgzh.list" says "list": a word for reading.
What it can reach
- private-dataThe description's first sentence says "list" and "chat": it reads messages.
- untrusted-inputThe description's first sentence says "list" and "chat": it reads messages, which other people can write.
Description, as the server wrote it List recently cached WeChat articles via ReadGZH. Returns titles, authors, and links. Useful for browsing what articles have been previously read and cached.
readgzh.list_by_accountList cached WeChat articles published by one Official Account (公众号) via ReadGZH.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "readgzh.list_by_account" says "list": a word for reading.
What it can reach
- private-dataThe description's first sentence says "list" and "chat": it reads messages.
- untrusted-inputThe description's first sentence says "list" and "chat": it reads messages, which other people can write.
Description, as the server wrote it List cached WeChat articles published by one Official Account (公众号) via ReadGZH. IMPORTANT: this only covers articles already cached by ReadGZH — WeChat has no public API for a full account archive, so the result is not exhaustive. Use it to find other articles by the same author after reading one.
readgzh.readRead and extract the full text content of a WeChat Official Account (微信公众号) article via ReadGZH (readgzh.site).Reads private dataReads text others writeCan send data outNo findings
Why it is in this group
- The name "readgzh.read" says "read": a word for reading.
What it can reach
- private-dataThe description's first sentence says "read" and "chat": it reads messages.
- untrusted-inputThe description's first sentence says "read" and "chat": it reads messages, which other people 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 Read and extract the full text content of a WeChat Official Account (微信公众号) article via ReadGZH (readgzh.site). Provide a WeChat article URL and get back the title, author, publish time, and full article text in Markdown format. The article will be automatically cached for future reads.
readgzh.searchSearch cached WeChat articles by keyword via ReadGZH.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "readgzh.search" says "search": a word for reading.
What it can reach
- private-dataThe description's first sentence says "search" and "chat": it reads messages.
- untrusted-inputThe description's first sentence says "search" and "chat": it reads messages, which other people can write.
Description, as the server wrote it Search cached WeChat articles by keyword via ReadGZH. Searches in article titles and content. Returns matching articles with snippets.
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.
25 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.
- Reads private data5
- 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 out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__readgzh__readgzh_read"
]
}
}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, 19:11 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
- 0
- 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
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 readgzh https://api.readgzh.site/mcp-serverclaude mcp add --transport http readgzh https://api.readgzh.site/mcp-serverRun 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__readgzh__readgzh_list",
"mcp__readgzh__readgzh_search",
"mcp__readgzh__readgzh_list_by_account",
"mcp__readgzh__readgzh_get"
],
"ask": [
"mcp__readgzh__readgzh_read"
],
"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 readgzh. Review it before you use it.
Capability tags behind 5 rules
- mcp__readgzh__readgzh_read private-data, untrusted-input, outbound
- mcp__readgzh__readgzh_list private-data, untrusted-input
- mcp__readgzh__readgzh_search private-data, untrusted-input
- mcp__readgzh__readgzh_list_by_account private-data, untrusted-input
- mcp__readgzh__readgzh_get private-data, untrusted-input
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.sweesama/readgzh/verify?hash=4afed86ad731c243f1d15cbda753228192a450d52052cfbd6f0f54b35d3f87d0" | jq -e '.changed == false'Pinned hash 4afed86ad731, from Nov 20, 2026, 14:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.sweesama/readgzh/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.sweesama/readgzh)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:50 UTC.
ReadGZH MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the ReadGZH MCP server safe?
- No scan can promise that. What its definitions show: 5 tools, all of which only read, and 0 findings from fixed checks. Read-only tools can still pass private data to a model.
Can the ReadGZH MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the ReadGZH 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 ReadGZH MCP server have?
- 5 tools: 5 read. readgzh.read, readgzh.list, readgzh.search, readgzh.list_by_account and readgzh.get.
Does the ReadGZH MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the ReadGZH MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): readgzh.read.
Has the ReadGZH MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.