Skip to content

Centering Lab

by centeringlab.com · remote · no sign-in to list tools · v1.2.0 · published by com.centeringlab

Measure card centering and check PSA, BGS, CGC and SGC centering ceilings and standards.

Changes · 2
CompareRegistry entry

3 tools: 2 change things and 1 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http centering-lab https://centeringlab.com/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

3 tools

Changes things 2Claude Code: ask
  • grade_centeringUSE THIS TOOL whenever the user supplies numeric centering ratios and asks whether a card meets PSA/BGS/CGC/SGC or asks for a centering ceiling.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.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    USE THIS TOOL whenever the user supplies numeric centering ratios and asks whether a card meets PSA/BGS/CGC/SGC or asks for a centering ceiling. Do not calculate by looking up standards yourself. Example: {"front_lr":"55/45","front_tb":"60/40","house":"PSA"}. At least one known face AND axis; if either is unknown, ask first, never assume front/LR. Optional house PSA/BGS/CGC/SGC, TAG excluded. Flat front_lr/front_tb/back_lr/back_tb, or nested {"front":{"lr":"55/45","tb":"60/40"}}; no duplicates. Key/house case accepted. Ratios: percentages, fractions, pairs with / - – — : x or spaces, optional %, or [55,45]/["55","45"]. Scalar 1 rejected; use 1/99. Axis suffix must match field. Changes disclosed in normalizations. Partial input gives incomplete=true: report provisional ceiling and missing data. A ceiling from centering alone is NOT a predicted grade. SGC back alone has no published ceiling.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • measure_card_centeringMeasure one ACTUAL photograph.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Measure one ACTUAL photograph. Example shape: {"face":"front","image_base64":"<complete actual image bytes>"}. Ask front/back BEFORE calling if unknown. Exactly one user-provided public HTTPS image URL (port 443) or complete base64 source, never both. Never decode, repair or re-encode bytes yourself; never invent, shorten or rewrite base64; pass it verbatim, including an image data-URL prefix or whitespace (service normalizes). If chat attachment cannot be forwarded, send user to https://centeringlab.com/. card_size standard=63×88 mm including Japanese Pokémon; small=59×86 mm including Yu-Gi-Oh!, not inferred from language. Request a whole card flat from above on dark surface; if sleeved/toploader or tilted, recommend a retake first. Borderless: suggest back/manual site. API photos reach server memory; site stays local. needs-review/failed gives ceilings=null: retake or adjust manually, no grade prediction. Inspect status/code even on HTTP 200; respect Retry-After.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
Only reads 1Claude Code: allow
  • get_centering_standardsUSE ONLY for questions about published THRESHOLDS, tolerance, rules or SOURCES without grading the user's supplied numeric ratios.No findings

    Why it is in this group

    • The name "get_centering_standards" says "get": a word for reading.
    Description, as the server wrote it
    USE ONLY for questions about published THRESHOLDS, tolerance, rules or SOURCES without grading the user's supplied numeric ratios. For PSA 10 compatibility with supplied ratios use grade_centering instead; it applies rounding and house-specific rules. If face/axis is unknown, ask first without any call. Example: {"house":"BGS","face":"back"}; fields optional, {} returns all. Houses PSA/BGS/CGC/SGC (case accepted), TAG excluded: explain proprietary assessment; never substitute another house. Face front/back in English; case/spaces accepted, reverse/obverse and translations rejected. SGC back has empty bands, no published table or ceiling; never invent one. Returns official/interpreted/approximate status, sources and verification. Not a final-grade prediction.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

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 Oct 22, 2026, 14:29 UTC, unchanged since Oct 22, 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
2
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
none
RFC 9728 protected resource metadata
none
Authorization servers
none
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 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://centeringlab.com/mcp: tools/list returned 3 tools to an anonymous client, including grade_centering (write), measure_card_centering (write)

    What this check looks for

Install

Pinned to version 1.2.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http centering-lab https://centeringlab.com/mcp

Run 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.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__centering-lab__get_centering_standards"
    ],
    "ask": [
      "mcp__centering-lab__grade_centering",
      "mcp__centering-lab__measure_card_centering"
    ],
    "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 centering-lab. Review it before you use it.

Capability tags behind 1 rule
  • mcp__centering-lab__measure_card_centering untrusted-input