mcp server
Decide Policy Notaries
Fail-closed refund, cancellation, return, and trial checks for 100 US subscription vendors.
Description as published by the maintainer. Source
- version 1.3.1
- active
active — Most recent push to the repository was 2026-08-08.
What this server can do
4 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.
cancellation_penalty(plan, region, vendor, billing_cadence)- Evaluate whether cancelling a US consumer subscription incurs a penalty or lock. Returns UNKNOWN when billing cadence is required or the policy needs manual review. Required: vendor, region, plan.
refund_eligibility(plan, region, vendor, days_since_purchase, qualifying_conditions_met)- Evaluate a US consumer subscription refund against versioned source-backed rules. Returns UNKNOWN when required conditions are absent or the vendor requires approval or manual policy review. Required: vendor, days_since_purchase, region, plan.
return_eligibility(plan, region, vendor, days_since_purchase, qualifying_conditions_met)- Evaluate whether a US consumer subscription purchase can be reversed under versioned source-backed rules. Returns UNKNOWN when required conditions are absent or manual review is required. Required: vendor, days_since_purchase, region, plan.
trial_terms(plan, region, vendor, offer_confirmed, observed_trial_days, observed_auto_converts, observed_card_required)- Evaluate a live US consumer subscription trial offer. Supply observed availability, duration, card, and auto-conversion facts; the tool returns UNKNOWN instead of inferring current offers from static data. Required: vendor, region, plan.
Last successful function declaration observed on . Source: https://policy.decide.fyi/api/mcp. We list what the server declared; we do not call any of these functions.
Endpoint status observed on . Source: https://policy.decide.fyi/api/mcp.
Signals
These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.
| Signal | Value | What it measures | Window | Observed | Source |
|---|---|---|---|---|---|
| GitHub stars | 1 | Number of GitHub accounts that bookmarked this repository since it was created. It is a bookmark count, not installs, not active users and not quality. | cumulative, all time | GitHub | |
| Last commit | 2026-08-08 | Date of the most recent push to any branch. This is the strongest cheap indicator of whether the project is still maintained. | point in time | GitHub | |
| Open issues | 45 | Open issues plus open pull requests, as GitHub counts them together. A high number can mean an active project or an abandoned one. | as of fetch | GitHub | |
| Latest published version | 1.3.1 | Latest version string the maintainer published to the registry. | as of fetch | Model Context Protocol | |
| Registry record last updated | 2026-07-16 | When the registry record was last updated by its maintainer. | point in time | Model Context Protocol | |
| First listed in the MCP Registry | 2026-07-16 | Date this server was first published to the official MCP Registry. Not a usage or quality measure. | point in time | Model Context Protocol | |
| repository status | active | The repository exists on GitHub and is not archived. This says nothing about how recently it was worked on. | as of fetch | GitHub | |
| mcp tools declared | 4 tools | Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. | as of probe | policy.decide.fyi | |
| mcp endpoint status | ok | The server listed 4 functions when asked. | as of probe | policy.decide.fyi |
Where to get it
Related, by what their authors tagged them
-
DeskCrew
— last commit 2026-08-06, shares customer-support
Agent-native helpdesk where AI agents run support tickets and pay per action in USDC via x402.
-
Help Scout MCP Server
— last commit 2026-08-01, shares customer-support
Search Help Scout conversations, customers, organizations, threads, and inboxes with AI assistants
These share tags the maintainers applied themselves, such as customer-support. Common tags like "mcp" or "ai" are ignored for this: agreeing with six hundred other projects is not a similarity.
This is not a recommendation and not a test result. It is a map of what the authors said their work is about.
How the author describes it
Topics the maintainer set on GitHub: ai-agents, customer-support, mcp, model-context-protocol, policy-automation, refunds, returns.
This record as data
Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.
GET /api/v1/entries/mcp_server.json