MCP Conduct Register

Check MCP server conduct

Category: Pending
Primary Subcategory: AI Output Verification & Grounding

Integration details

Description

This plugin exposes a public register of measured conduct for MCP servers. Five conditions are measured on a schedule: the server speaks MCP, it publishes an A2A agent card, it declares who pays it, identical input returns identical output, and the verdict itself can be recomputed by a third party. A condition that could not be measured is recorded as not measured. It is never counted as a pass, and that rule is not relaxed for the operator of the register. The register does not rank servers. It does not recommend one server over another. It returns what was measured, when it was measured, and the SHA-256 of the record so that the reading can be checked by someone who does not trust the party that issued it. An endpoint that is absent from the register has simply never been measured here. Absence is reported as absence and is not a negative verdict. Determinism is not measured unless the owner of the checked server has recorded consent, because measuring it requires executing a tool on someone else's server. Free, read only, no account and no key. The register is a build artefact of a scheduled script with no editorial step, and it is archived with a DOI so a citation survives the repository moving.

Integration type: Plugin
Verification status: Not applicable
Platform: ChatGPT
Category: Pending
Primary Subcategory: AI Output Verification & Grounding
Secondary Subcategories: None listed
Brand: HORIZON SHIELD
Access: No account required
First tracked: 2026-09-13
Tool count: 5
Geography: US

ChatGPT Plugin Discovery Score

ChatGPT Plugin discovery is coming soon

ChatGPT can surface a Plugin when it matches a user's request.Your Plugin Discovery Score measures how often yours appears.

No spam. Unsubscribe any time.

ChatGPT recommends Airtable when a user asks it to update a CRM. — ChatGPT surfaces Airtable because it matches the user's request.

Primary Subcategory

Competing in ChatGPT AI Output Verification & Grounding

View Category

Listed in alphabetical order

Primary Subcategory

Acumen by TalarionComing soonGet notified

AgoraComing soonGet notified

AI Delivery Evidence CheckerComing soonGet notified

ArmatureComing soonGet notified

CovalComing soonGet notified

MCP Conduct RegisterComing soonGet notified

Tools

5 tools agents can invoke

Measure a public MCP endpoint against five conditions: it speaks MCP, it publishes an A2A agent card, it declares who pays it, identical input returns identical output, and the verdict itself can be recomputed by anyone. Free, no key. Conformance and disclosure only; this says nothing about whether any figure the checked server returns is correct. By default no tool on the checked server is called, so determinism comes back as not measured rather than guessed. Set allow_tool_call true only for a server you control.
check_conformance
Return the five conditions this gate measures, what it explicitly does not verify, and the tier definitions. Takes no arguments and returns identical output every time. Read this before running a check so you know what a verdict does and does not claim.
get_conditions
Look up what this register already holds about an MCP endpoint: whether it is watched, how often it is re-measured, how many measurements exist, when the first and latest were taken, and the latest verdict with the record_sha256 you can recompute yourself. Reads stored measurements only. It contacts nothing and measures nothing, so use check_conformance for a fresh reading. An endpoint that is absent is reported as absent and that is NOT a negative verdict: it means nobody has measured it here, not that it failed.
lookup_server
A single machine-first answer for an agent deciding whether to trust an MCP endpoint BEFORE it connects. Returns verified (true only when the latest scheduled measurement passed every measured condition; null otherwise, never false), a state enum saying which case it is, measured_at, and a record_sha256 with a recompute_url so you can check the verdict without trusting this gate. Reads the stored register only: it contacts nothing and measures nothing. Absent and pending are reported honestly and are NOT negative verdicts. For a fresh measurement rather than the stored one, use check_conformance.
is_verified
Take a verdict this gate issued and recompute its record_sha256 independently. Removes record_sha256 and recompute_note, serialises the remainder in key order, and hashes it. Returns whether the verdict was altered after it was issued. You do not have to trust the party that issued the verdict, including this one.
verify_verdict

MCP Conduct Register FAQ

How do I improve a ChatGPT Plugin's discoverability?

The levers are the listing surface agents actually read: names, descriptions, keywords, tool metadata, and registry health. Which lever matters depends on where discovery breaks, which is what continuous measurement shows.

What are MCP Conduct Register alternatives on ChatGPT?

As of 2026-09-13, MCP Conduct Register competes with Acumen by Talarion, Agora, AI Delivery Evidence Checker, Armature, Coval, Deep Research, Markup AI, Mnemom, Neura Relay MCP, NORMS: Evidence & Scope, Openlayer, OSuite.ai, Qu Review, Release Notes Coverage Checker, StudyArena in ChatGPT AI Output Verification & Grounding, ranked by public Discoverability Score.

Where is this profile measured?

This profile uses the geography attached to the latest public registry snapshot: US. Locale tags are intentionally omitted.