DeveloperHub Docs MCP server
io.developerhub/docsdeveloperhub.iostreamable-httpv0.2.0Scanned
Search, browse and read DeveloperHub's own docs. Every docs site on DeveloperHub serves one at /mcp
7 tools: 7 only read.
- Reads private data · 0
- Reads text others write · 4
- Can send data out · 2
- 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 DeveloperHub Docs MCP server can do
The DeveloperHub Docs MCP server is published by developerhub.io, a domain the MCP Registry verified. It has 7 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.
4 tools bring in text other people can write (list_pages, read_page, list_endpoints and 1 more); 2 tools can send data out of your system (read_page and read_endpoint).
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, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 16, 2026, version 0.2.0.
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.
7 tools
Only reads 7Show 7 read-only tools
list_endpointsList the endpoints of one API reference (method, path and summary), grouped by tag, each linked by the URL read_endpoint takes.Reads text others writeNo findings
Why it is in this group
- The name "list_endpoints" says "list": a word for reading.
What it can reach
- 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 the endpoints of one API reference (method, path and summary), grouped by tag, each linked by the URL read_endpoint takes.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
list_pagesList the pages of one documentation section, nested as its sidebar shows them, each linked by the URL read_page takes.Reads text others writeNo findings
Why it is in this group
- The name "list_pages" says "list": a word for reading.
What it can reach
- 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 the pages of one documentation section, nested as its sidebar shows them, each linked by the URL read_page takes.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
list_sectionsList the documentation sections and API references of a version, with the slug that list_pages and list_endpoints take.No findings
Why it is in this group
- The name "list_sections" says "list": a word for reading.
Description, as the server wrote it List the documentation sections and API references of a version, with the slug that list_pages and list_endpoints take.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
list_versionsList the versions of the documentation.No findings
Why it is in this group
- The name "list_versions" says "list": a word for reading.
Description, as the server wrote it List the versions of the documentation. The default version is the one every tool uses when you name none.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
read_endpointRead one API endpoint as Markdown: its parameters, request body and responses, with the schemas they use.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "read_endpoint" says "read": a word for reading.
What it can reach
- 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 one API endpoint as Markdown: its parameters, request body and responses, with the schemas they use. Pass its URL as list_endpoints gives it, with its #anchor.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
read_pageRead a documentation page as Markdown.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "read_page" says "read": a word for reading.
What it can reach
- 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 a documentation page as Markdown. Pass its URL as search or list_pages gives it, or its path on this site. For a section's pages call list_pages, and for an API reference list_endpoints and read_endpoint.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
searchSearch the documentation and return the most relevant excerpts for a query, each with its source page title and link.No findings
Why it is in this group
- The name "search" says "search": a word for reading.
Description, as the server wrote it Search the documentation and return the most relevant excerpts for a query, each with its source page title and link.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
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 write4
- 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, 18:23 UTC, unchanged since Oct 29, 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.
Tools6 added, 1 changed.+6 added~1 changedView diff
- Added:list_endpointsOnly reads
- Added:list_pagesOnly reads
- Added:list_sectionsOnly reads
- Added:list_versionsOnly reads
- Added:read_endpointOnly reads
- Added:read_pageOnly reads
- Changed:searchOnly readsinputSchema
Install
Pinned to version 0.2.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http docs https://docs.developerhub.io/mcpclaude mcp add --transport http docs https://docs.developerhub.io/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__docs__search",
"mcp__docs__list_versions",
"mcp__docs__list_sections",
"mcp__docs__list_pages",
"mcp__docs__list_endpoints"
],
"ask": [
"mcp__docs__read_page",
"mcp__docs__read_endpoint"
],
"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 docs. Review it before you use it.
Capability tags behind 4 rules
- mcp__docs__list_pages untrusted-input
- mcp__docs__read_page untrusted-input, outbound
- mcp__docs__list_endpoints untrusted-input
- mcp__docs__read_endpoint 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.developerhub/docs/verify?hash=f0a8b411e4a5cd2fb91a262937b8d44386c4ba825930dd4d78a7835605bc07c9" | jq -e '.changed == false'Pinned hash f0a8b411e4a5, from Nov 16, 2026, 12:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.developerhub/docs/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.developerhub/docs)Source: MCP Registry. Synced Nov 16, 2026, 12:17 UTC.
DeveloperHub Docs MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the DeveloperHub Docs MCP server safe?
- No scan can promise that. What its definitions show: 7 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 DeveloperHub Docs MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the DeveloperHub Docs 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 DeveloperHub Docs MCP server have?
- 7 tools: 7 read. search, list_versions, list_sections, list_pages, read_page, list_endpoints and read_endpoint.
Does the DeveloperHub Docs MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the DeveloperHub Docs 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): read_page and read_endpoint.
Has the DeveloperHub Docs MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 16, 2026. Every change is on this page and in its Atom feed.