Agentwatch
REMOTE · COMIZA.LIGHTING · SCANNED OCT 4
Check if ChatGPT, Claude and Perplexity can reach, read and quote a website.
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 Security57
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation not fully verified: no authorisation is required to call this server, and 4 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. See how to fix → View diagnostics → Unverified
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- 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 Usability73
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 638 tokens (~159/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 5 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 Agentwatch MCP server?
Agentwatch is a hosted endpoint at https://comiza.lighting/agentwatch/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 · comiza.lighting
claude mcp add --transport http lighting-comiza-agentwatch 'https://comiza.lighting/agentwatch/mcp'
{
"mcpServers": {
"lighting-comiza-agentwatch": {
"url": "https://comiza.lighting/agentwatch/mcp"
}
}
} {
"servers": {
"lighting-comiza-agentwatch": {
"type": "http",
"url": "https://comiza.lighting/agentwatch/mcp"
}
}
} [mcp_servers.lighting-comiza-agentwatch] url = "https://comiza.lighting/agentwatch/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"lighting-comiza-agentwatch": {
"type": "remote",
"url": "https://comiza.lighting/agentwatch/mcp",
"enabled": true
}
}
} openclaw mcp add lighting-comiza-agentwatch --url 'https://comiza.lighting/agentwatch/mcp' --transport streamable-http
mcp_servers:
lighting-comiza-agentwatch:
url: "https://comiza.lighting/agentwatch/mcp" {
"McpServers": {
"lighting-comiza-agentwatch": {
"Transport": "http",
"Url": "https://comiza.lighting/agentwatch/mcp"
}
}
} assistant mcp add lighting-comiza-agentwatch -t streamable-http -u 'https://comiza.lighting/agentwatch/mcp'
{
"mcpServers": {
"lighting-comiza-agentwatch": {
"type": "http",
"url": "https://comiza.lighting/agentwatch/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.
- 28 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 25 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 8 Sept 26 0
- Stability: 0.97 → pass security
- 7 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 26 Aug 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 11 Aug 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 10 Aug 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Schema quality: pass → fail ▼ functional
- Stability: unverified → 0.03 ▲ functional
- New tool “verify_crawler_visit” functional
- New tool “verify_signed_request” functional
- 9 Aug 26 0
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 4 Oct 2026 · Probed https://comiza.lighting/agentwatch/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=comiza.lighting | CN=YE2,O=Let's Encrypt,C=US | 14 Sept 2026 | 13 Dec 2026 | ECDSA 256 | ECDSA-SHA384 | 6066de606113beed9e68fbf77bec8325d60 |
| SANs: comiza.lighting, www.comiza.lighting | ||||||
| CN=YE2,O=Let's Encrypt,C=US (CA) | CN=Root YE,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | ECDSA 384 | ECDSA-SHA384 | 4df3b15dd6c0784c507cd37b58e6f115 |
| 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 comiza.lighting. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| lighting. | present | 55696 | 8 | Verified |
| comiza.lighting. | 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 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://comiza.lighting/agentwatch/mcp | Verified | 200 | |
| http (plaintext) | http://comiza.lighting/agentwatch/mcp | HTTPS enforced | 301 | https://comiza.lighting/agentwatch/mcp |
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 →
check_site Check whether AI assistants can read a site ~125
Fetch a website the way ChatGPT, Claude, Perplexity, Google and Copilot fetch it, and report what stops them. Checks robots.txt per crawler with the deciding line number, makes real requests as each crawler to catch firewall and CDN rules that robots.txt cannot express, and measures whether the page carries readable text without JavaScript. Use this before advising anyone on why their site does not appear in AI answers: the usual cause is one of these three and none of them are visible from the outside.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | Domain or URL, for example example.com |
No output schema declared.
No examples provided.
list_ai_crawlers List the AI crawlers and what each one is for ~85
The robots.txt tokens used by the major assistants, separated by purpose: the ones that build the index answers come from, the ones that fetch a page live when a person asks, and the ones that only collect training data. Blocking the last group costs no visibility; blocking the first two removes a site from the answers. Use this before writing or editing a robots.txt.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
verify_crawler_visit Check whether a crawler visit was genuine ~133
Given the IP address and User-Agent from a log line, say whether that visit really came from the crawler it claims to be. Checks the address against the vendor's own published ranges where they exist, and falls back to forward-confirmed reverse DNS. On one ordinary server's logs, 14% of requests claiming to be Googlebot were not Google. Use this before anyone writes a firewall rule based on a user agent string, because that string is a claim and not proof.
| Name | Type | Req | Description |
|---|---|---|---|
| ip | string | yes | Source address from the log line. |
| user_agent | string | yes | User-Agent from the same line. |
No output schema declared.
No examples provided.
verify_signed_request Verify an HTTP Message Signature on a request ~183
Verify a Web Bot Auth signature (RFC 9421, Ed25519) on a captured request. Unlike an address check, this proves who sent that exact request: it fetches the signer's published key directory, rebuilds the signature base from the covered components, and checks the signature. Use it when a request carries Signature-Input and Signature headers. Returns 'unsigned' when they are absent, and 'cannot_verify' rather than 'invalid' whenever the limitation is on our side.
| Name | Type | Req | Description |
|---|---|---|---|
| headers | object | yes | Request headers, including Signature-Input, Signature and Signature-Agent. |
| method | string | – | HTTP method of the captured request, uppercase. It is part of the signature base whenever the signature covers @method, so a wrong value fails verification. Defaults to GET. |
| url | string | yes | Full URL as requested; the signature covers it. |
No output schema declared.
No examples provided.
What is the Agentwatch MCP server?
Agentwatch is an MCP server listed in the public MCP registry as lighting.comiza/agentwatch. Check if ChatGPT, Claude and Perplexity can reach, read and quote a website. This page covers its hosted endpoint (https://comiza.lighting/agentwatch/mcp).
Is the Agentwatch MCP server safe to use?
Agentwatch scores 78 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 Agentwatch MCP server expose?
Agentwatch exposes 4 tools: check_site, verify_crawler_visit, verify_signed_request, list_ai_crawlers. Their descriptions and schemas cost roughly 526 tokens of context every time the server is loaded.
Does the Agentwatch MCP server require authentication?
No. We connected to Agentwatch without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Agentwatch MCP server still maintained?
Agentwatch is still listed as active in the MCP registry. We last reached this channel on 4 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.