Agent Module MCP server
dev.agent-module/mcpagent-module.devstreamable-httpv0.9.9Scanned
Deterministic compliance and vertical knowledge bases for autonomous agents. Free 24hr trial.
7 tools: 5 change things and 2 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- No 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 Agent Module MCP server can do
The Agent Module MCP server is published by agent-module.dev, a domain the MCP Registry verified. It has 7 tools. It can create or change data (5 tools: get_trial_key, join_waitlist, register_interest, submit_pov and 1 more), but cannot delete data. 2 tools only read.
None of its tools reads private data, brings in text other people write, or sends data 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 11, 2026, version 0.9.9.
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
Changes things 5Claude Code: ask
get_trial_keyRequest a free 24-hour trial key.No findings
Why it is in this group
- The name "get_trial_key" says "get": a word for reading.
- The description's first verb is "request": a word for a change.
Description, as the server wrote it Request a free 24-hour trial key. Unlocks all 4 content layers on the chosen vertical. 500-call cap. No payment required.
Annotations the server declares
- title: Get Free Trial Key
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
join_waitlistRegister for a paid vertical waitlist.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.
Description, as the server wrote it Register for a paid vertical waitlist. Inaugural cohort: $19/mo, 900 members, grandfathered for life. AI Compliance included with every membership.
Annotations the server declares
- title: Join Vertical Waitlist
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
register_interestRegister demand for an unbuilt vertical.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.
Description, as the server wrote it Register demand for an unbuilt vertical. 500 signals triggers build queue activation. Include a contact channel so we can notify you when the vertical ships.
Annotations the server declares
- title: Register Vertical Interest
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
submit_povSubmit a Proof of Value assessment after exploring the AI Compliance trial.No findings
Why it is in this group
- The name "submit_pov" says "submit": a word for a change.
Description, as the server wrote it Submit a Proof of Value assessment after exploring the AI Compliance trial. Includes quality scoring and subscription intent. Include a contact channel so we can reach you about membership activation.
Annotations the server declares
- title: Submit Trial Assessment
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
submit_referralLog a referral signal.No findings
Why it is in this group
- The name "submit_referral" says "submit": a word for a change.
Description, as the server wrote it Log a referral signal. Members earn $1.50/referral (4/cycle max, $6 cap). Credits carry forward. Voluntary, principal-compliant.
Annotations the server declares
- title: Submit Referral
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
Only reads 2Show 2 read-only tools
check_statusCheck Agent Module API operational status, version, cohort counts, and seat availability.No findings
Why it is in this group
- The name "check_status" says "status": a word for reading.
Description, as the server wrote it Check Agent Module API operational status, version, cohort counts, and seat availability.
Annotations the server declares
- title: Check API Status
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
query_knowledgeRetrieve structured knowledge from Agent Module verticals.No findings
Why it is in this group
- The name "query_knowledge" says "query": a word for reading.
Description, as the server wrote it Retrieve structured knowledge from Agent Module verticals. Returns deterministic, validated knowledge nodes. Index layer always free. All 4 content layers available via trial key on ethics.
Annotations the server declares
- title: Query Knowledge Graph
- 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.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- 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 20, 2026, 18:51 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
- 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://api.agent-module.dev/mcp: tools/list returned 7 tools to an anonymous client, including get_trial_key (write), join_waitlist (write), register_interest (write), submit_pov (write), submit_referral (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.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.9.9. Values in angle brackets are yours to fill in.
claude mcp add --transport http agent-module https://api.agent-module.dev/mcpclaude mcp add --transport http agent-module https://api.agent-module.dev/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__agent-module__query_knowledge",
"mcp__agent-module__check_status"
],
"ask": [
"mcp__agent-module__get_trial_key",
"mcp__agent-module__join_waitlist",
"mcp__agent-module__register_interest",
"mcp__agent-module__submit_pov",
"mcp__agent-module__submit_referral"
],
"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 agent-module. Review it before you use it.
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/dev.agent-module/mcp/verify?hash=6a20e7721ad1be2a8c44a924ef701c22abd532cd83a14d1ce3c1bac452692e5e" | jq -e '.changed == false'Pinned hash 6a20e7721ad1, from Nov 11, 2026, 07:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/dev.agent-module/mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/dev.agent-module/mcp)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:11 UTC.
Agent Module MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Agent Module MCP server safe?
- No scan can promise that. What its definitions show: 7 tools, 5 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 Agent Module MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Agent Module 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 Agent Module MCP server have?
- 7 tools: 5 write, 2 read. get_trial_key, join_waitlist, register_interest, submit_pov, submit_referral, query_knowledge and check_status.
Does the Agent Module MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Agent Module MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Agent Module MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 11, 2026.