Tier 1 Protocol
app.tier1protocol.mcp/tier-1-protocolVersion 1.0.1Search files while they stay encrypted: the problem DARPA chased for a decade. Exact quotes back.
Status
Responds324 msAnswered our handshake without sign-in.- Last checked
- Nov 14, 2026, 13:39 UTC
- Latency
- 324 ms
- Remotes responding
- 1 of 1
- Sign-in
- No sign-in
- Hosting
- Hosted outside the EU (detected)
- Registry data as of
- Nov 14, 2026, 22:14 UTC
Data from the official MCP Registry, checked by run.zero. How we check
Connect
Streamable HTTP
https://mcp.tier1protocol.app/mcpResponds324 msNo sign-in
Claude Code
claude mcp add --transport http tier-1-protocol https://mcp.tier1protocol.app/mcpClaude Desktop and claude.ai
Settings > Connectors > Add custom connector
Name: tier-1-protocol
Remote MCP server URL: https://mcp.tier1protocol.app/mcpCursor
{
"mcpServers": {
"tier-1-protocol": {
"url": "https://mcp.tier1protocol.app/mcp"
}
}
}VS Code
code --add-mcp '{"name":"tier-1-protocol","type":"http","url":"https://mcp.tier1protocol.app/mcp"}'Built your own server? run.zero hosts MCP servers on European infrastructure.
Tools
7 tools
Read-only | Idempotent | Open world | ||
|---|---|---|---|---|
authorize_sourcesAdd selected private ChatGPT files to the paid account's Tier 1 context. Show the filenames and fixed 30-day retention and require explicit confirmation before calling. This upload consent applies to private file intake only; it does not define or narrow the other policy-eligible catalogs Tier 1 may route. Authentication and an active paid plan are required. | No | No | No | No |
fetchPaid exact-span retrieval after Tier 1 search. Accept only an unchanged id returned by search for the same account. Authentication and an active paid plan are required. Do not invent ids, browse nearby text, or change files. | No | Yes | Yes | No |
indexIndex one file into the user's own Tier 1 library, one batch at a time. Pass the file's text as the chatbot read it, with its SHA-256 as the idempotency key — re-indexing the same bytes is a no-op. One call carries at most 64 KiB of text; larger files are split and indexed in successive calls. This is the conversational drip path: it builds the index file by file as the user works. It cannot bootstrap a large existing library — for a library, use the browser indexer page or Local. Authentication and an active paid plan are required. The user's keyed profile (derived locally, sent per request) is also required. | No | Yes | Yes | No |
index_statusHow much of the user's library is indexed, and whether the index is still growing. Returns the sources indexed, the batches still pending, and the index fingerprint. Poll this after indexing, never the index directly. Authentication and an active paid plan are required. The user's keyed profile (derived locally, sent per request) is also required. | No | Yes | Yes | No |
index_upload_tokenMint a short-lived upload token so the user can upload a browser-built index to their Tier 1 library. The token is valid 15 minutes for any number of sources under this principal and profile. The response includes the token AND the principal_id: hand the user BOTH to paste into the indexer page (token field + principal field) — the page never collects a principal_id on its own, and the library compares the token's principal to the upload body's principal_id. The token travels in the x-tier1-upload-token header. Authentication and an active paid plan are required. The user's keyed profile (derived locally, sent per request) is also required — only its fingerprint is bound into the token. | No | No | No | No |
render_context_resultsInspect one to six exact coordinates returned by paid Tier 1 search. Pass only unchanged result ids. Tier 1 rehydrates and revalidates each id for the same account; caller-supplied titles, excerpts, URLs, and coordinates are rejected. Authentication and an active paid plan are required. | No | Yes | Yes | No |
searchRetrying the same public search with the same MCP request identity replays the same bounded operation. Paid context routing for useful work. Route a question across policy-eligible Tier 1 context available to the account, including private, shared, licensed, or public catalogs when present. Returns up to ten verified excerpts, exact source coordinates, signed result ids, and reference URLs. Broad questions may need focused follow-up searches; absence from one result set does not establish absence from the corpus. Authentication and an active paid plan are required. This is not an unrestricted web crawler and cannot change files. | No | No | Yes | No |
Details
- Registry status
- Active
- Published
- Nov 10, 2026
- Updated
- Nov 10, 2026
- Categories (suggested)
- Files and storageSuggested categories are assigned automatically from the registry text and may be wrong. Verified operators can correct them.
- GDPR
- Not declared