LocalMark Hosted Agents MCP server
ai.localmark/hosted-agentslocalmark.aistreamable-httpv1.2.0Scanned
Documents, data, localization, A2A repair and x402 analysis. Shared trial, then 0.05 USDC/task.
5 tools: 5 change things.
- Reads private data · 1
- Reads text others write · 5
- Can send data out · 0
- 4 findings
Tools listed without sign-in. Remote posture
With Anlyon
5 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 LocalMark Hosted Agents MCP server can do
The LocalMark Hosted Agents MCP server is published by localmark.ai, a domain the MCP Registry verified. It has 5 tools. It can create or change data (5 tools: analyze_document, analyze_data, localize_content, advise_agentops and 1 more), but cannot delete data. None of its tools only reads.
1 tool reads private data (analyze_document); 5 tools bring in text other people can write (analyze_document, analyze_data, localize_content and 2 more).
The fixed checks matched 4 findings (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 20, 2026, version 1.2.0.
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.
5 tools
Changes things 5Claude Code: ask
advise_agentopsAnalyze a supplied Agent Card and optional previous card; explain local version-aware repair/diff checks using OpenAI.Reads text others write1 finding
Why it is in this group
- The description's first verb is "analyze": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "advise_agentops" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The description's first verb is "analyze": a word for reading.
Description, as the server wrote it Analyze a supplied Agent Card and optional previous card; explain local version-aware repair/diff checks using OpenAI. No live endpoint requests.
Annotations the server declares
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
- readOnlyHint: false
analyze_dataProfile bounded CSV/JSON locally and ask OpenAI to explain computed facts.Reads text others write1 finding
Why it is in this group
- The name "analyze_data" says "analyze": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "analyze_data" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "analyze_data" says "analyze": a word for reading.
Description, as the server wrote it Profile bounded CSV/JSON locally and ask OpenAI to explain computed facts. Requires explicit authorization; no generated code or external data sources.
Annotations the server declares
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
- readOnlyHint: false
analyze_documentAnalyze supplied text with checked quote references.Reads private dataReads text others write1 finding
Why it is in this group
- The name "analyze_document" says "analyze": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
What it can reach
- private-dataThe name "analyze_document" says "analyze" and "document": it reads documents.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "analyze_document" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "analyze_document" says "analyze": a word for reading.
Description, as the server wrote it Analyze supplied text with checked quote references. No PDF/URL fetch. One free trial/network/30 days; then 0.05 USDC on Base via x402.
Annotations the server declares
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
- readOnlyHint: false
analyze_payment_offersCompare supplied x402 declarations with exact local amount calculations and OpenAI commentary.Reads text others write1 finding
Why it is in this group
- The name "analyze_payment_offers" says "analyze": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "analyze_payment_offers" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "analyze_payment_offers" says "analyze": a word for reading.
Description, as the server wrote it Compare supplied x402 declarations with exact local amount calculations and OpenAI commentary. No paid endpoint calls, wallet actions or payment.
Annotations the server declares
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
- readOnlyHint: false
localize_contentTranslate supplied text or flat JSON strings using OpenAI, validating keys/placeholders.Reads text others writeNo 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
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Translate supplied text or flat JSON strings using OpenAI, validating keys/placeholders. Explicit authorization and shared allowance required.
Annotations the server declares
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
- readOnlyHint: 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 outbound.
- Reads private data1
- 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 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 21, 2026, 19:21 UTC, unchanged since Nov 7, 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
- 5
- 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 5 tools that change things (5 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://agents.localmark.ai/mcp: tools/list returned 5 tools to an anonymous client, including analyze_document (write), analyze_data (write), localize_content (write), advise_agentops (write), analyze_payment_offers (write)
Findings
Matches of fixed checks, with the text they matched.
- Warnanalyze_document
The server marks "analyze_document" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "analyze_document" says "analyze": a word for reading.
- Warnanalyze_data
The server marks "analyze_data" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "analyze_data" says "analyze": a word for reading.
- Warnadvise_agentops
The server marks "advise_agentops" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The description's first verb is "analyze": a word for reading.
The server marks "analyze_payment_offers" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "analyze_payment_offers" says "analyze": a word for reading.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools5 changed.~5 changedView diff
- Changed:advise_agentopsChanges thingsinputSchema
- Changed:analyze_dataChanges thingsinputSchema
- Changed:analyze_documentChanges thingsinputSchema
- Changed:analyze_payment_offersChanges thingsinputSchema
- Changed:localize_contentChanges thingsinputSchema
Install
Pinned to version 1.2.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http hosted-agents https://agents.localmark.ai/mcpclaude mcp add --transport http hosted-agents https://agents.localmark.ai/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": [],
"ask": [
"mcp__hosted-agents__analyze_document",
"mcp__hosted-agents__analyze_data",
"mcp__hosted-agents__localize_content",
"mcp__hosted-agents__advise_agentops",
"mcp__hosted-agents__analyze_payment_offers"
],
"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 hosted-agents. Review it before you use it.
Capability tags behind 5 rules
- mcp__hosted-agents__analyze_document private-data, untrusted-input
- mcp__hosted-agents__analyze_data untrusted-input
- mcp__hosted-agents__localize_content untrusted-input
- mcp__hosted-agents__advise_agentops untrusted-input
- mcp__hosted-agents__analyze_payment_offers 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/ai.localmark/hosted-agents/verify?hash=a436ec43867a850ce6629275aee3cdf943dba84cd36420f5e31a6cbd63fe5bc8" | jq -e '.changed == false'Pinned hash a436ec43867a, from Nov 20, 2026, 06:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ai.localmark/hosted-agents/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ai.localmark/hosted-agents)Source: MCP Registry. Synced Nov 6, 2026, 07:17 UTC.
LocalMark Hosted Agents MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the LocalMark Hosted Agents MCP server safe?
- No scan can promise that. What its definitions show: 5 tools, 5 of which can change, send or delete something, and 4 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 LocalMark Hosted Agents MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the LocalMark Hosted Agents 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 LocalMark Hosted Agents MCP server have?
- 5 tools: 5 write. analyze_document, analyze_data, localize_content, advise_agentops and analyze_payment_offers.
Does the LocalMark Hosted Agents MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the LocalMark Hosted Agents MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the LocalMark Hosted Agents MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 20, 2026. Every change is on this page and in its Atom feed.