Mihenk AI MCP server
com.mihenkai/mihenkmihenkai.comstreamable-httpv1.0.1Scanned
Measured crypto KOL data: real reach, organic token interest, chain reports, post archive.
5 tools: 3 change things and 2 only read.
- Reads private data · 0
- Reads text others write · 2
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
3 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 Mihenk AI MCP server can do
The Mihenk AI MCP server is published by mihenkai.com, a domain the MCP Registry verified. It has 5 tools. It can create or change data (3 tools: organic_interest, ecosystem_report and kol_basket), but cannot delete data. 2 tools only read.
2 tools bring in text other people can write (kol_lookup and evidence_search).
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 17, 2026, version 1.0.1.
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.
5 tools
Changes things 3Claude Code: ask
ecosystem_reportWho among measured KOLs talks about a chain (base, solana, ethereum, bsc, near, arbitrum, hyperliquid, …), its most-discussed tokens, and the KOLs whose posts were followed by more…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.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Who among measured KOLs talks about a chain (base, solana, ethereum, bsc, near, arbitrum, hyperliquid, …), its most-discussed tokens, and the KOLs whose posts were followed by more trading volume. Window 7, 30 or 90 days.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: KOL report for a chain
kol_basketThe spot coins a KOL promoted in the last 7, 30 or 90 days, with the median 24 h move after their posts.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.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it The spot coins a KOL promoted in the last 7, 30 or 90 days, with the median 24 h move after their posts. Not a recommendation; it shows what the KOL promoted and what followed.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Coins a KOL promoted lately
organic_interestWhich measured KOLs talked about a token, how many views those posts got and how much was organic (posts that 3+ accounts published with the same text count as coordinated).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.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Which measured KOLs talked about a token, how many views those posts got and how much was organic (posts that 3+ accounts published with the same text count as coordinated). Window 7, 30 or 90 days.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Organic KOL interest in a token
Only reads 2Show 2 read-only tools
evidence_searchArchived posts of measured KOLs with the exact post time, including posts later deleted from X.Reads text others writeNo findings
Why it is in this group
- The name "evidence_search" says "search": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "post": it reads posts, which other people can write.
Description, as the server wrote it Archived posts of measured KOLs with the exact post time, including posts later deleted from X. Give a handle, words (or a $ticker), or both. Returns at most 10 records with links and record hashes.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Search the KOL evidence archive
kol_lookupMihenk's measurement of one X account: Mihenk score (0-10), real reach (typical views per post), followers, region, 90-day call record (share of calls that went the call's way with…Reads text others writeNo findings
Why it is in this group
- The name "kol_lookup" says "lookup": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "post": it reads posts, which other people can write.
Description, as the server wrote it Mihenk's measurement of one X account: Mihenk score (0-10), real reach (typical views per post), followers, region, 90-day call record (share of calls that went the call's way within 24 h) and the last 5 calls.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Look up a crypto KOL
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 or outbound.
- 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 out0
- 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 16, 2026, 14:19 UTC, unchanged since Nov 16, 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
- 3
- 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 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://app.mihenkai.com/mcp: tools/list returned 5 tools to an anonymous client, including organic_interest (write), ecosystem_report (write), kol_basket (write)
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.
Tools4 changed.~4 changedView diff
- Changed:ecosystem_reportChanges thingsinputSchema
- Changed:evidence_searchOnly readsinputSchema
- Changed:kol_basketChanges thingsinputSchema
- Changed:organic_interestChanges thingsinputSchema
Install
Pinned to version 1.0.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http mihenk https://app.mihenkai.com/mcpclaude mcp add --transport http mihenk https://app.mihenkai.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__mihenk__kol_lookup",
"mcp__mihenk__evidence_search"
],
"ask": [
"mcp__mihenk__organic_interest",
"mcp__mihenk__ecosystem_report",
"mcp__mihenk__kol_basket"
],
"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 mihenk. Review it before you use it.
Capability tags behind 2 rules
- mcp__mihenk__kol_lookup untrusted-input
- mcp__mihenk__evidence_search 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/com.mihenkai/mihenk/verify?hash=918cab9dcb5905949cfcf5df255a0f877dfb54c48982e0030dcab30f61bfd17e" | jq -e '.changed == false'Pinned hash 918cab9dcb59, from Nov 17, 2026, 08:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.mihenkai/mihenk/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.mihenkai/mihenk)Source: MCP Registry · repository. Synced Nov 17, 2026, 08:17 UTC.
Mihenk AI MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Mihenk AI MCP server safe?
- No scan can promise that. What its definitions show: 5 tools, 3 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 Mihenk AI MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Mihenk AI 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 Mihenk AI MCP server have?
- 5 tools: 3 write, 2 read. organic_interest, ecosystem_report, kol_basket, kol_lookup and evidence_search.
Does the Mihenk AI MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Mihenk AI MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Mihenk AI MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 17, 2026. Every change is on this page and in its Atom feed.