IsoKron

MCP Server Checker › Rubric

Grading rubric

rubric_version: 2.1.0
Applies from: 2026-11-18. Sources read: 2026-11-18. MCP specification revision: 2026-07-28.

Every report, JSON export and private link carries rubric_version. When a link made under another version is opened, the page says so and grades with the current version. Any change to a weight, band, cap, severity or check bumps the version: patch for wording, minor for a new check, major for a change to weights, bands or caps.

What is graded

SectionWhat it coversGraded
MCP spec 2026-07-28Rules of the specification that a pasted tool list can decideYes
Anthropic directoryAnthropic connector pre-submission checklist, plus the shared annotation and poisoning checksYes, plus a "ready" flag
OpenAI directoryOpenAI plugin guidelines (MCP tool rules), plus the shared annotation and poisoning checksYes, plus a "ready" flag
Poisoning and hidden textHidden characters and injection patterns in every string of every toolYes
Schema and description qualityDesign advice: argument docs, enums, strict schemas, pagination, namingYes
Write-surface designGuards the list offers for safe writes (retry key, version, delete guard)Yes, by its own formula
MWS 0.9 recordsMWS-ANN-4 per toolNever: no total, no grade (MWS 0.9 section 5.2)

A check can count toward more than one section. For example, a hidden instruction counts toward Poisoning, Anthropic and OpenAI, because both directories reject it.

Severities

A check has a default severity. Some checks set a different severity case by case; each such check documents when (for example, a missing description is blocking, a short one is attention).

Score per section (spec, Anthropic, OpenAI, poisoning, quality)

  1. Each tool starts at 100. For each finding on that tool that counts toward the section, deduct:
    • blocking: 40
    • attention: 10
    • advice: 3

    A tool's score does not go below 0.

  2. Take the mean of the tool scores.
  3. For each whole-list finding (duplicate names, envelope fields, near-duplicate descriptions, missing namespace, a partial paste) that counts toward the section, deduct:
    • blocking: 20
    • attention: 5
    • advice: 1
  4. Clamp to 0..100 and round. This is the section score.

Letter bands

LetterScore
A90 and above
B80 to 89
C65 to 79
D50 to 64
Fbelow 50

Caps (applied after the bands, in this order)

  1. A section with any blocking finding is at most B.
  2. If any MCP specification MUST fails (a blocking finding in the spec section), the spec, Anthropic and OpenAI grades are at most C. A tool that breaks a MUST may be dropped by clients, whatever the directories say.
  3. If any blocking poisoning finding exists (invisible tag characters, bidi overrides, HTML comments, prompt markup, instruction phrases, hard cross-tool steering, encoded text, outside instructions, secret seeking, look-alike letters in a name), the Poisoning, Anthropic and OpenAI grades are F. Both directories reject these.

The report lists every cap applied to a section.

Ready flag

A directory is "ready" when no finding that counts toward it is blocking. Ready means only that these static rules pass. Approval is each platform's decision; Anthropic also runs automated scans and may escalate a listing to a Verified review.

Write-surface design

Tools that declare readOnlyHint: true, or whose name reads as a read, are left out. The others are read by the first or last word of the name as create, update, delete or other. Three guard shares are counted:

Score = the mean of the shares that apply, times 100. Letter bands as above. No caps. If no tool can be read as a create, update or delete, the section is not graded. Full-replacement updates without a field mask and bulk deletes without a guard are reported as findings in this section but do not change the score.

Thresholds that are IsoKron's own

The specification and directories give no numbers for these, so the values are ours and may change with the rubric version:

What the rubric does not claim

The grades cover static rules read from the tool list. They do not test behavior: whether hints match what tools do, whether retries are safe, whether stale writes are refused. Those are MWS tests against a running server. Name-based checks are heuristics and say so in their findings.

Changes in rubric 2.1.0 (18 November 2026)

Changes from rubric 1 (prototype, 17 November 2026)

All 76 checks · Check your tool list

Third-party licences