# io.github.serg-tanichev/email-spam-tester > Test an email before it goes out: a disposable address, 41 checks with RFC citations, a fix plan. - name: io.github.serg-tanichev/email-spam-tester - version: 1.0.0 - connection class: R0 (autonomous) - trust: 91/100 - quality: 79/100 (good) - owner: not claimed - descriptor: https://api.protogrid.dev/v1/servers/io.github.serg-tanichev%2Femail-spam-tester - tools: https://api.protogrid.dev/v1/servers/io.github.serg-tanichev%2Femail-spam-tester/tools **An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe. ## Connection (mcpServers) ```json { "mcpServers": { "email-spam-tester": { "type": "http", "url": "https://email-spam-tester.com/mcp" } } } ``` ## Trust - hygiene: 100 - liveness: 100 - freshness: 85 - provenance: 80 - drivers: +repository +namespace-matches-repo +reachable +uptime-100% ~updated-33d-ago - Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. ## Quality 79/100 (good) ### protocol: 88 (weight 25) - pass `protocol.modern`: supports 2026-07-28 (server/discover) - pass `protocol.stateless`: answers without a session - pass `protocol.transport`: streamable HTTP - warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use ### authorization: n/a (weight 15) - n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth - n/a `auth.secret_in_url`: no templated URL ### tool hygiene: 100 (weight 30) - pass `tools.descriptions`: every tool has a description - pass `tools.description_length`: descriptions are concise - pass `tools.schemas`: every tool has an object input schema - pass `tools.annotations`: 4 of 4 tools declare readOnlyHint or destructiveHint - pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint - pass `tools.token_cost`: about 1,050 tokens to load every tool - pass `tools.api_dump`: tools are not a one-to-one API dump ### stability: 25 (weight 15) - warn `stability.changes`: 19 tool changes in 30 days - fail `stability.rug_pull`: 2 tools kept their name but changed most of their description in 30 days; review before trusting them ### dependencies: n/a (weight 15) - n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package - tools: 4, about 1,050 tokens to load them all - tool set hash: 746e3fc86a4c4b604736be119718acab - tools last changed: 2026-10-12T07:20:32.624Z - badge: [![protogrid quality](https://protogrid.dev/badge/io.github.serg-tanichev/email-spam-tester.svg)](https://protogrid.dev/servers/io.github.serg-tanichev/email-spam-tester) - Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. ### Tool changes - 2026-10-12 `get_message_source` changed (description, inputSchema) - before: The message exactly as it was received: headers, both bodies, source. Useful when a finding points at a header and the agent needs to see what it actually sent rather than what it believes it sent, or to find the confirmation link in a welcome letter. - after: The message exactly as it was received: headers, both bodies, source. Useful when a finding points at a header and the agent needs to see what it actually sent rather than what it believes it sent. The message is kept for an hour after it arrives and then deleted; within that hour anyone with the slug can read it. After that only the report remains. - 2026-10-12 `get_report` changed (description, inputSchema, outputSchema) **meaning changed** - before: Read a report by its slug without waiting, with provider placement so far. Works for one-hour tests and for letters in the person's series mailboxes. - after: Read a report by its slug without waiting, with provider placement so far. The report stays at its link for good and anyone with the link can read it: the checks, the score, the fix plan, and the subject and sender of the email. - 2026-10-12 `wait_for_report` changed (outputSchema) - 2026-10-12 `get_test_address` changed (outputSchema) - 2026-09-30 `close_series_mailbox` removed - Stop collecting letters at a permanent mailbox. Only when the person asks. Letters that arrive afterwards are dropped unread. Reports already made stay until they expire, and opening a mailbox for the same domain again brings the same address back. - 2026-09-30 `write_fix_plan` removed - Ask for the AI verdict and fix plan of one letter in a series mailbox. Letters in a series are checked automatically, but the AI plan is written only on request. It takes about a minute; get_report shows it when ready. One-hour tests get their plan automatically and do not need this. - 2026-09-30 `get_series_letters` removed - The letters a permanent mailbox received, newest first, with their scores and the problems that recur across the series. - 2026-09-30 `list_series_mailboxes` removed - The person's permanent mailboxes, with how many letters each received. - 2026-09-30 `open_series_mailbox` removed - A permanent address that checks every letter sent to it, for a series. For mail that comes as a sequence rather than one draft: sign the address up to the person's own newsletter, welcome series or shop, or add it to a campaign's recipient list, and every letter that arrives gets the full check. The address stays the same for this domain; asking again returns it. Letters are private to this ChatGPT user; read them with get_series_letters. - 2026-09-30 `get_test_address` changed (inputSchema) Full history: https://api.protogrid.dev/v1/servers/io.github.serg-tanichev%2Femail-spam-tester/changes ## Remotes - https://email-spam-tester.com/mcp (streamable-http, auth none, reachable true, uptime30d 1) ## Packages _none_ ## Tools (4) - `get_message_source`: The message exactly as it was received: headers, both bodies, source. Useful when a finding points at a header and the agent needs to see what it actually sent rather than what it believes it sent. The message is kept for an hour after it arrives and then deleted; within that hour anyone with the slug can read it. After that only the report remains. - `get_report`: Read a report by its slug without waiting, with provider placement so far. The report stays at its link for good and anyone with the link can read it: the checks, the score, the fix plan, and the subject and sender of the email. - `get_test_address`: Reserve a single-use address to send a draft email to, for a full check. Returns the address and the URL its report will appear at. The address accepts exactly one message and expires after an hour. The email has to be sent by the person, from the platform or mailbox they really send from: half the checks read what that platform adds. The report covers 42 checks (SPF, DKIM, DMARC, reverse DNS, TLS, blocklists, content, links, the Gmail and Yahoo bulk-sender rules) and a plan of what to fix. lang is decided now because the message arrives minutes later over SMTP, which carries no hint of who is waiting for it. What wait_for_report returns quotes check lines in English whatever it is set to; the person following report_url sees their own language. - `wait_for_report`: Wait until the message arrives and has been analysed, then summarise it. Call it after the email has been sent to the address from get_test_address. Blocks rather than returning "not ready yet": an agent told to poll writes a sleep loop and usually gives up before the analysis finishes. Provider placement keeps filling in for up to 30 minutes after the report; get_report reads the latest.