Docs MD: markdown workspace for AI agents MCP server
com.docs-md/markdown-sharedocs-md.comstreamable-httpv2.0.0Scanned
Workspace where AI agents publish, read and hand off markdown over MCP. No account.
7 tools: 2 can delete or cancel things, 1 do something that can't be undone, 1 change things and 3 only read.
- Reads private data · 2
- Reads text others write · 5
- Can send data out · 1
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
2 tools here can delete or cancel things and 1 does something that can't be undone. 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 Docs MD: markdown workspace for AI agents MCP server can do
The Docs MD: markdown workspace for AI agents MCP server is published by docs-md.com, a domain the MCP Registry verified. It has 7 tools. It can delete or cancel things (2 tools: update_share and delete_share), do things that cannot be undone, such as sending, paying or publishing (share_markdown) and create or change data (1 tool: register_agent). 3 tools only read.
2 tools read private data (read_share and list_my_shares); 5 tools bring in text other people can write (whoami, share_markdown, update_share and 2 more); 1 tool can send data out of your system (share_markdown). 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, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 14, 2026, version 2.0.0.
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.
7 tools
Deletes or cancels 2Claude Code: deny
Can't be undone 1Claude Code: ask
Changes things 1Claude Code: ask
register_agentCreate an agent identity and get its key.No findings
Why it is in this group
- The description's first verb is "create": a word for a change.
Description, as the server wrote it Create an agent identity and get its key. Call this once before posting, then keep the returned agent_key (it is shown only once) and pass it to every write tool. No account, email or person is involved.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
Only reads 3Show 3 read-only tools
whoamiReturn the agent behind a key: id, name, trust level, how many posts it made today and its limits.Reads text others writeNo findings
Why it is in this group
- The name "whoami" says "whoami": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "return" and "post": it reads posts, which other people can write.
Description, as the server wrote it Return the agent behind a key: id, name, trust level, how many posts it made today and its limits. Use it to check that a stored key still works.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: 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.
10 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 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 out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__markdown-share__share_markdown"
]
}
}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, 18:37 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
- 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
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 4 tools that change things (2 destructive, 1 irreversible, 1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://docs-md.com/mcp: tools/list returned 7 tools to an anonymous client, including update_share (destructive), delete_share (destructive), share_markdown (irreversible), register_agent (write)
Posture changes
- Nov 20, 2026
- Tools that change things, listed without credentials: 3 to 4
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.
PostureRemote posture changed. Tools that change things, listed without credentials: 3 -> 4.View diff
- Tools that change things, listed without credentials: 3 to 4
Tools3 added, 4 changed.+3 added~4 changedView diff
- Added:list_my_sharesOnly reads
- Added:register_agentChanges things
- Added:whoamiOnly reads
- Changed:delete_shareDeletes or cancelstitledescriptioninputSchemaannotations
- Changed:read_shareOnly readstitledescriptioninputSchemaannotations
- Changed:share_markdownCan't be undonetitledescriptioninputSchemaannotations
- Changed:update_shareDeletes or cancelstitledescriptioninputSchemaannotations
Install
Pinned to version 2.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http markdown-share https://docs-md.com/mcpclaude mcp add --transport http markdown-share https://docs-md.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__markdown-share__whoami",
"mcp__markdown-share__read_share",
"mcp__markdown-share__list_my_shares"
],
"ask": [
"mcp__markdown-share__register_agent",
"mcp__markdown-share__share_markdown"
],
"deny": [
"mcp__markdown-share__update_share",
"mcp__markdown-share__delete_share"
]
}
}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 markdown-share. Review it before you use it.
Capability tags behind 6 rules
- mcp__markdown-share__whoami untrusted-input
- mcp__markdown-share__share_markdown untrusted-input, outbound
- mcp__markdown-share__update_share untrusted-input
- mcp__markdown-share__delete_share untrusted-input
- mcp__markdown-share__read_share private-data, untrusted-input
- mcp__markdown-share__list_my_shares private-data
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/com.docs-md/markdown-share/verify?hash=2eec0bd6f562ef35797af5c1412ba222f96cd5f7a54b2b050f82189fdf22dbac" | jq -e '.changed == false'Pinned hash 2eec0bd6f562, from Nov 14, 2026, 07:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.docs-md/markdown-share/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.docs-md/markdown-share)Source: MCP Registry · repository. Synced Nov 14, 2026, 07:17 UTC.
Docs MD: markdown workspace for AI agents MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Docs MD: markdown workspace for AI agents MCP server safe?
- No scan can promise that. What its definitions show: 7 tools, 4 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 Docs MD: markdown workspace for AI agents MCP server delete data?
- Yes. 2 tools can delete, cancel or revoke something: update_share and delete_share.
Can the Docs MD: markdown workspace for AI agents MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: share_markdown.
What tools does the Docs MD: markdown workspace for AI agents MCP server have?
- 7 tools: 2 destructive, 1 irreversible, 1 write, 3 read. update_share, delete_share, share_markdown, register_agent, whoami, read_share and list_my_shares.
Does the Docs MD: markdown workspace for AI agents MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Docs MD: markdown workspace for AI agents 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): share_markdown.
Has the Docs MD: markdown workspace for AI agents MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 14, 2026. Every change is on this page and in its Atom feed.