10 open records, observed 2026-09-10. Every claim below carries the command that disproves it. If one is wrong, it should be withdrawn — 111 have been across the whole registry.
The package registry still holds a record for this package, but every version has been unpublished. There is nothing to install.
ERR-2026-4546 | https://registry.npmjs.org/apprise-rmcp | npm has the package record for apprise-rmcp with no publishe | checked 2026-09-17 |
ERR-2026-4547 | https://registry.npmjs.org/arcane-rmcp | npm has the package record for arcane-rmcp with no published | checked 2026-09-17 |
ERR-2026-4548 | https://registry.npmjs.org/cortex-rmcp | npm has the package record for cortex-rmcp with no published | checked 2026-09-17 |
ERR-2026-4549 | https://registry.npmjs.org/gotify-rmcp | npm has the package record for gotify-rmcp with no published | checked 2026-09-17 |
ERR-2026-4550 | https://registry.npmjs.org/synapse-rmcp | npm has the package record for synapse-rmcp with no publishe | checked 2026-09-17 |
ERR-2026-4551 | https://registry.npmjs.org/tailscale-rmcp | npm has the package record for tailscale-rmcp with no publis | checked 2026-09-17 |
ERR-2026-4552 | https://registry.npmjs.org/unifi-rmcp | npm has the package record for unifi-rmcp with no published | checked 2026-09-17 |
ERR-2026-4553 | https://registry.npmjs.org/unraid-rmcp | npm has the package record for unraid-rmcp with no published | checked 2026-09-17 |
ERR-2026-4554 | https://registry.npmjs.org/yarr-mcp | npm has the package record for yarr-mcp with no published ve | checked 2026-09-17 |
ERR-2026-4555 | https://registry.npmjs.org/ytdl-rmcp | npm has the package record for ytdl-rmcp with no published v | checked 2026-09-17 |
Check it yourself:
curl -sS -o /dev/null -w '%{http_code}\n' https://registry.npmjs.org/apprise-rmcp
Also filed as: ai.dinglebear, ai.dinglebear/apprise-rmcp, ai.dinglebear/arcane-rmcp, ai.dinglebear/cortex-rmcp, ai.dinglebear/gotify-rmcp, ai.dinglebear/synapse-rmcp, ai.dinglebear/tailscale-rmcp, ai.dinglebear/unifi-rmcp. One page, because two sweeps named the same subject differently and the record that mattered was on the page nobody would open.
Run its check. If the answer differs from what is written, say so here and it will be withdrawn — 111 already have been. A record nobody can contest is a record asking to be trusted, which is the opposite of the point.
This is not a clean bill of health for anything not listed. The registry was built from a sample of two directories, and an operation absent from it was almost certainly never examined. Silence here means not looked at, not looked at and fine — which is the same mistake this registry exists to record in other people.
A record of defects in the public description of machine-callable operations: documents a directory claims are live and are not, hosts that no longer resolve, specifications that contradict the API they describe. It is not a ranking, not a review, and not a judgement about the service. No credential is ever sent to anything listed here.
The whole registry, machine-readable: errata.json. Index of subjects: index.html.
Built from registry errata-2026-09-10@21826040e38a. If manifest.json shows a different one, this page is behind the records and should not be trusted over them.