AgentGuard by Audiscape MCP server
com.audiscape.agentguard/agentguardagentguard.audiscape.comstreamable-httpv3.0.0Scanned
Stops runaway AI agent loops and token burn. Checks each tool call before it runs. No signup.
4 tools: 3 change things and 1 only read.
- Reads private data · 0
- Reads text others write · 1
- Can send data out · 0
- 1 finding
Sign-in required, no OAuth metadata. 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 AgentGuard by Audiscape MCP server can do
The AgentGuard by Audiscape MCP server is published by agentguard.audiscape.com, a domain the MCP Registry verified. It has 4 tools. It can create or change data (3 tools: guard_check_session, audit_domain and create_checkout_session), but cannot delete data. 1 tool only reads.
1 tool brings in text other people can write (get_remediation_preview).
The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.
Its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 14, 2026, version 3.0.0.
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.
4 tools
Changes things 3Claude Code: ask
audit_domainRun a live HTTP audit against a public domain and return score, grade and report URL.No findings
Why it is in this group
- The description's first verb is "run": a word for a change.
Description, as the server wrote it Run a live HTTP audit against a public domain and return score, grade and report URL.
create_checkout_sessionReturn a Stripe checkout link for the remediation pack for a domain.No findings
Why it is in this group
- The name "create_checkout_session" says "create": a word for a change.
Description, as the server wrote it Return a Stripe checkout link for the remediation pack for a domain.
guard_check_sessionCall before each tool call your agent makes.1 finding
Why it is in this group
- The description's first verb is "call": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "guard_check_session" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "call": a word for a change.
Description, as the server wrote it Call before each tool call your agent makes. Send the calls so far and the one you are about to make, get back allowed true or false with the reason. Catches identical and near-repeat loops (same file, URL or command), re-reads of finished items, failing-tool retry streaks and USD or token caps before spend. Free, no account, arguments are not stored, nothing is executed. Smallest valid call: {"calls":[],"next":{"tool":"bash"}}
Annotations the server declares
- title: Loop and budget guard
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 1Show 1 read-only tool
get_remediation_previewReturn the remediation preview and scorecard URL for a domain.Reads text others writeNo findings
Why it is in this group
- The name "get_remediation_preview" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "return" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it Return the remediation preview and scorecard URL for a domain.
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 write1
- 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, 14:21 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
- 404
- tools/list served without credentials
- no
- Tools that change things, listed without credentials
- 0
- Protocol version
- not observed
- 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
The probe stopped: initialize answered HTTP 404.
Posture changes
- Nov 16, 2026
- HTTP status of an anonymous initialize: 200 to 404
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 3 to 0
- Protocol version: 2025-06-18 to none
Findings
Matches of fixed checks, with the text they matched.
The server marks "guard_check_session" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "call": a word for a change.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. HTTP status of an anonymous initialize: 200 -> 404; tools/list served without credentials: yes -> no; Tools that change things, listed without credentials: 3 -> 0 (and 1 more).View diff
- HTTP status of an anonymous initialize: 200 to 404
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 3 to 0
- Protocol version: 2025-06-18 to none
Tools1 changed.~1 changedView diff
- Changed:guard_check_sessionChanges thingstitledescriptioninputSchemaannotations
Install
Pinned to version 3.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http agentguard https://agentguard.audiscape.com/mcpclaude mcp add --transport http agentguard https://agentguard.audiscape.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__agentguard__get_remediation_preview"
],
"ask": [
"mcp__agentguard__guard_check_session",
"mcp__agentguard__audit_domain",
"mcp__agentguard__create_checkout_session"
],
"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 agentguard. Review it before you use it.
Capability tags behind 1 rule
- mcp__agentguard__get_remediation_preview 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.audiscape.agentguard/agentguard/verify?hash=4bd8745b7fa7372bf900bb3930cfb55f2afc8274224f6330d7212fe50c830b9c" | jq -e '.changed == false'Pinned hash 4bd8745b7fa7, from Nov 14, 2026, 19:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.audiscape.agentguard/agentguard/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.audiscape.agentguard/agentguard)Source: MCP Registry. Synced Nov 1, 2026, 19:17 UTC.
AgentGuard by Audiscape MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the AgentGuard by Audiscape MCP server safe?
- No scan can promise that. What its definitions show: 4 tools, 3 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the AgentGuard by Audiscape MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the AgentGuard by Audiscape 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 AgentGuard by Audiscape MCP server have?
- 4 tools: 3 write, 1 read. guard_check_session, audit_domain, create_checkout_session and get_remediation_preview.
Does the AgentGuard by Audiscape MCP server need sign-in or OAuth?
- Its remote endpoint did not answer the last anonymous look.
Does the AgentGuard by Audiscape MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the AgentGuard by Audiscape 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.