Agent Guardian — MCP Contract Auditor
io.github.neat-cyber/agent-guardianneat-cyberstreamable-httpv0.8.0Scanned
Audit MCP tool contracts and compatibility; includes owned-service HTTP check demos.
6 tools: 4 change things and 2 only read.
- Reads private data · 0
- Reads text others write · 1
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
4 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 Guardian — MCP Contract Auditor can do
The Agent Guardian — MCP Contract Auditor is published by the GitHub account neat-cyber. It has 6 tools. It can create or change data (4 tools: audit_mcp_contracts, ecosystem_catalog, check_demo and check_live), but cannot delete data. 2 tools only read.
1 tool brings in text other people can write (live_history).
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 15, 2026, version 0.8.0.
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.
6 tools
Changes things 4Claude Code: ask
audit_mcp_contractsAudit supplied MCP tools/list descriptors and compare with optional previous_tools to flag likely breaking changes.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 Audit supplied MCP tools/list descriptors and compare with optional previous_tools to flag likely breaking changes. No network requests or storage of your schemas. Returns structured findings and a SHA-256 fingerprint.
check_demoRun a controlled synthetic health check and store its result.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 controlled synthetic health check and store its result. NOT an external service probe.
check_livePerform a real HTTP check ONLY against Guardian's own fixed test target.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 Perform a real HTTP check ONLY against Guardian's own fixed test target. Globally rate-limited to one check per minute. Not third-party monitoring.
ecosystem_catalogDiscover project-owned complementary MCP tools useful for a specific agent task.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 Discover project-owned complementary MCP tools useful for a specific agent task. No automatic call, login, payment or referral tracking.
Only reads 2Show 2 read-only tools
demo_historyRead measured synthetic check history over the last 24 hours.No findings
Why it is in this group
- The description's first verb is "read": a word for reading.
Description, as the server wrote it Read measured synthetic check history over the last 24 hours. NOT independent uptime monitoring.
live_historyRead real HTTP observations of Guardian's own test target from the last 24 hours, including sample size, availability, and latency.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "read": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "read" and "http": it reads web pages, which anyone can write.
Description, as the server wrote it Read real HTTP observations of Guardian's own test target from the last 24 hours, including sample size, availability, and latency.
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 15, 2026, 13:19 UTC, unchanged since Nov 15, 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
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 4 tools that change things (4 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://agent-guardian.saromy-export.workers.dev/mcp: tools/list returned 6 tools to an anonymous client, including audit_mcp_contracts (write), ecosystem_catalog (write), check_demo (write), check_live (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.
Tools2 added.+2 addedView diff
- Added:audit_mcp_contractsChanges things
- Added:ecosystem_catalogChanges things
Install
Pinned to version 0.8.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http agent-guardian https://agent-guardian.saromy-export.workers.dev/mcpclaude mcp add --transport http agent-guardian https://agent-guardian.saromy-export.workers.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-guardian__live_history",
"mcp__agent-guardian__demo_history"
],
"ask": [
"mcp__agent-guardian__audit_mcp_contracts",
"mcp__agent-guardian__ecosystem_catalog",
"mcp__agent-guardian__check_demo",
"mcp__agent-guardian__check_live"
],
"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-guardian. Review it before you use it.
Capability tags behind 1 rule
- mcp__agent-guardian__live_history 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/io.github.neat-cyber/agent-guardian/verify?hash=255d02c707d329c2050f56324b32a01b115221c8027fda1de331954270503d75" | jq -e '.changed == false'Pinned hash 255d02c707d3, from Nov 15, 2026, 12:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.neat-cyber/agent-guardian/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.neat-cyber/agent-guardian)Source: MCP Registry. Synced Nov 15, 2026, 13:17 UTC.
Agent Guardian — MCP Contract Auditor: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Agent Guardian — MCP Contract Auditor safe?
- No scan can promise that. What its definitions show: 6 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 Agent Guardian — MCP Contract Auditor delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Agent Guardian — MCP Contract Auditor 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 Guardian — MCP Contract Auditor have?
- 6 tools: 4 write, 2 read. audit_mcp_contracts, ecosystem_catalog, check_demo, check_live, live_history and demo_history.
Does the Agent Guardian — MCP Contract Auditor need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Agent Guardian — MCP Contract Auditor send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Agent Guardian — MCP Contract Auditor changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 15, 2026. Every change is on this page and in its Atom feed.