Canonsheet
REMOTE · CANONSHEET.KANEKY.DEV · SCANNED SEP 29
Consistent prompts for one human character across image and video models. Paid per call, x402.
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 Security51
- 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 1 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 enforcement could not be verified: the plaintext port answered with HTTP 404, which proves neither a plaintext path nor enforcement. View diagnostics → Unverified
- 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 Usability59
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 354 tokens (~354/item across 1 items; 1 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 Management17
- Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage96
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 88% of tool parameters carry a description.Partial
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 supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
How do I install the Canonsheet MCP server?
Canonsheet is a hosted endpoint at https://canonsheet.kaneky.dev/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 · canonsheet.kaneky.dev
claude mcp add --transport http dev-kaneky-canonsheet 'https://canonsheet.kaneky.dev/mcp'
{
"mcpServers": {
"dev-kaneky-canonsheet": {
"url": "https://canonsheet.kaneky.dev/mcp"
}
}
} {
"servers": {
"dev-kaneky-canonsheet": {
"type": "http",
"url": "https://canonsheet.kaneky.dev/mcp"
}
}
} [mcp_servers.dev-kaneky-canonsheet] url = "https://canonsheet.kaneky.dev/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"dev-kaneky-canonsheet": {
"type": "remote",
"url": "https://canonsheet.kaneky.dev/mcp",
"enabled": true
}
}
} openclaw mcp add dev-kaneky-canonsheet --url 'https://canonsheet.kaneky.dev/mcp' --transport streamable-http
mcp_servers:
dev-kaneky-canonsheet:
url: "https://canonsheet.kaneky.dev/mcp" {
"McpServers": {
"dev-kaneky-canonsheet": {
"Transport": "http",
"Url": "https://canonsheet.kaneky.dev/mcp"
}
}
} assistant mcp add dev-kaneky-canonsheet -t streamable-http -u 'https://canonsheet.kaneky.dev/mcp'
{
"mcpServers": {
"dev-kaneky-canonsheet": {
"type": "http",
"url": "https://canonsheet.kaneky.dev/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 +1
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 26 Sept 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.
- 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
- 24 Sept 26 59
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 29 Sept 2026 · Probed https://canonsheet.kaneky.dev/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=kaneky.dev | CN=YE1,O=Let's Encrypt,C=US | 3 Aug 2026 | 1 Nov 2026 | ECDSA 256 | ECDSA-SHA384 | 578fd9cc7528e586dac66fb8ffbbe2190e5 |
| SANs: *.kaneky.dev, kaneky.dev | ||||||
| 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 canonsheet.kaneky.dev. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| dev. | present | 60074 | 8 | Verified |
| kaneky.dev. | 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; includeSubDomains; preload |
| content-security-policy | default-src 'self' https: data: blob: 'unsafe-inline' 'unsafe-eval'; frame-ancestors 'self'; base-uri 'self'; object-src 'none' |
| x-content-type-options | nosniff |
| x-frame-options | SAMEORIGIN |
| referrer-policy | strict-origin-when-cross-origin |
| permissions-policy | geolocation=(), microphone=(self), camera=(self), payment=(), usb=() |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://canonsheet.kaneky.dev/mcp | Verified | 200 | |
| http (plaintext) | http://canonsheet.kaneky.dev/mcp | Inconclusive | 404 |
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 →
build_character_prompts ~276
Build a consistent prompt set for one human character: a canonical image prompt with every appearance fact labelled, negative prompts that stop traits like glasses or a cane from vanishing, a video prompt, and optionally a contact sheet that holds everything fixed and walks one axis. Works with any image or video model. Text keeps wardrobe and framing stable; for the same FACE across images, generate the canonical frame once and pass it back as a reference image (has_reference). Paid per call over x402: the first attempt answers HTTP 402 with the price. Invalid arguments are refused before any payment.
| Name | Type | Req | Description |
|---|---|---|---|
| appearance | object | – | The canon. Every prompt carries it verbatim. At least one field, or a trait, is required. |
| choices | object | – | The shot. Unset axes use neutral defaults. |
| custom_traits | array | – | – |
| has_reference | boolean | – | True when a canonical image will be attached; the prompts then defer the face to it. |
| name | string | – | What to call the character in the prompt. Optional. |
| traits | object | – | Details models tend to drop. Include a key only if the character has it. |
| video | object | – | The clip. |
| walk_axis | string | – | Return a contact sheet: one prompt per option of this axis, everything else held. |
No output schema declared.
No examples provided.
What is the Canonsheet MCP server?
Canonsheet is an MCP server listed in the public MCP registry as dev.kaneky/canonsheet. Consistent prompts for one human character across image and video models. Paid per call, x402. This page covers its hosted endpoint (https://canonsheet.kaneky.dev/mcp).
Is the Canonsheet MCP server safe to use?
Canonsheet scores 61 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 Canonsheet MCP server expose?
Canonsheet exposes 1 tool: build_character_prompts. Their descriptions and schemas cost roughly 276 tokens of context every time the server is loaded.
Does the Canonsheet MCP server require authentication?
No. We connected to Canonsheet without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Canonsheet MCP server still maintained?
Canonsheet is still listed as active in the MCP registry. We last reached this channel on 29 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.