Agent Verifier
REMOTE · FP.PACKET.GURU · SCANNED OCT 5
Test and debug your AI agent's Web Bot Auth (RFC 9421) signature: is it valid, and what to fix?
Available components
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security80
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one. See how to fix → View diagnostics → Partial
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability81
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 186 tokens (~186/item across 1 items; 1 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management10
- Stability observed for 3 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 1 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 2 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
How do I install the Agent Verifier MCP server?
Agent Verifier is a hosted endpoint at https://fp.packet.guru/api/v1/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · fp.packet.guru
claude mcp add --transport http guru-packet-agent-verifier 'https://fp.packet.guru/api/v1/mcp'
{
"mcpServers": {
"guru-packet-agent-verifier": {
"url": "https://fp.packet.guru/api/v1/mcp"
}
}
} {
"servers": {
"guru-packet-agent-verifier": {
"type": "http",
"url": "https://fp.packet.guru/api/v1/mcp"
}
}
} [mcp_servers.guru-packet-agent-verifier] url = "https://fp.packet.guru/api/v1/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"guru-packet-agent-verifier": {
"type": "remote",
"url": "https://fp.packet.guru/api/v1/mcp",
"enabled": true
}
}
} openclaw mcp add guru-packet-agent-verifier --url 'https://fp.packet.guru/api/v1/mcp' --transport streamable-http
mcp_servers:
guru-packet-agent-verifier:
url: "https://fp.packet.guru/api/v1/mcp" {
"McpServers": {
"guru-packet-agent-verifier": {
"Transport": "http",
"Url": "https://fp.packet.guru/api/v1/mcp"
}
}
} assistant mcp add guru-packet-agent-verifier -t streamable-http -u 'https://fp.packet.guru/api/v1/mcp'
{
"mcpServers": {
"guru-packet-agent-verifier": {
"type": "http",
"url": "https://fp.packet.guru/api/v1/mcp"
}
}
} The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 4 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.
- 3 Oct 26 0
- Stability: unverified → 0.03 ▲ functional
- 2 Oct 26 75
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 6 Oct 2026 · Probed https://fp.packet.guru/api/v1/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=fp.packet.guru | CN=YE1,O=Let's Encrypt,C=US | 16 Sept 2026 | 15 Dec 2026 | ECDSA 256 | ECDSA-SHA384 | 6ecbea46d52ffebba4105f17b41bad291ef |
| SANs: fp.packet.guru | ||||||
| CN=YE1,O=Let's Encrypt,C=US (CA) | CN=Root YE,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | ECDSA 384 | ECDSA-SHA384 | 5ddd70dd31f801c85c186a7a04b80afe |
| CN=Root YE,O=ISRG,C=US (CA) | CN=ISRG Root X2,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | ECDSA-SHA384 | 872165fc34b6e5fba8add5b3705fb53a |
| CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | SHA256-RSA | 6c8f1dc727c7117f7baf853ac980f9cd |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of fp.packet.guru. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| guru. | present | 35665 | 8 | Verified |
| packet.guru. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=63072000 |
| content-security-policy | default-src 'self'; script-src 'self' 'unsafe-inline' 'unsafe-eval' blob:; worker-src 'self' blob:; style-src 'self' 'unsafe-inline'; img-src 'self' data: blob: https://*.cartocdn.com https://*.openstreetmap.org; font-src 'self' data:; object-src 'none'; base-uri 'self'; connect-src 'self' https://*.cartocdn.com https://*.packet.guru; frame-ancestors 'none'; |
| x-content-type-options | nosniff |
| referrer-policy | no-referrer |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://fp.packet.guru/api/v1/mcp | Verified | 200 | |
| http (plaintext) | http://fp.packet.guru/api/v1/mcp | HTTPS enforced |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
self_check_web_bot_auth Check my own Web Bot Auth setup ~104
Reports how the request carrying this call looks from the outside: whether its Web Bot Auth (RFC 9421) signature verified, what the key directory it named publishes, the exact fault if there is one and the sentence saying what to change, plus plain facts about the address it arrived from. Sign the call the way you sign requests to anyone else. Free, anonymous, no account. Takes no arguments: an unsigned call still gets an answer about its address.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| geo | object | – | Country, region, city and timezone of your address. |
| id | string | – | Identifier for this verdict, safe to quote in a support request. |
| identity | object | – | Who you were established to be, and on what evidence. Empty of judgement: the outcome of checking a signature you sent against a directory you published. |
| ip | object | – | Plain facts about your own address: network, operator, reputation of the address itself. |
| meta | object | – | Envelope: API version, how long the verdict took, which axes contributed. |
| mode | string | – | You called this endpoint yourself, so the answer describes your own request. |
| signals | object | – | – |
| success | boolean | – | Always true on a 200. Errors carry success:false and an error object. |
No examples provided.
What is the Agent Verifier MCP server?
Agent Verifier is an MCP server listed in the public MCP registry as guru.packet/agent-verifier. Test and debug your AI agent's Web Bot Auth (RFC 9421) signature: is it valid, and what to fix? This page covers its hosted endpoint (https://fp.packet.guru/api/v1/mcp).
Is the Agent Verifier MCP server safe to use?
Agent Verifier scores 76 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Agent Verifier MCP server expose?
Agent Verifier exposes 1 tool: self_check_web_bot_auth. Their descriptions and schemas cost roughly 104 tokens of context every time the server is loaded.
Does the Agent Verifier MCP server require authentication?
No. We connected to Agent Verifier without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Agent Verifier MCP server still maintained?
Agent Verifier is still listed as active in the MCP registry. We last reached this channel on 5 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.