Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Tier 1 Protocol

REMOTE · MCP.TIER1PROTOCOL.APP

Search files while they stay encrypted: the problem DARPA chased for a decade. Exact quotes back.

+3 this week 84 Trust /100

Last scanned (20 hours ago)

Scores higher than 84% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Search and Retrieval

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security97
  • The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
  • Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token. View diagnostics → Pass
  • HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
  • The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
  • DNSSEC is configured correctly; the domain's records validate against the full chain to the root. View diagnostics → Pass
  • The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents. View diagnostics → Partial
Transport & Reachability100
Schema Quality & AI Usability66
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1525 tokens (~217/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management37
  • Stability observed for 11 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
  • Supports UI / widget rendering.Pass
What we tested

Checks we ran (14)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol
  • Capabilities

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 21 Nov 26 +1
    • This server's schema is too large to store in full, so we cannot compare its tools day to day functional
  • 20 Nov 26 0
    • This server's schema is too large to store in full, so we cannot compare its tools day to day functional
  • 19 Nov 26 +1
    • This server's schema is too large to store in full, so we cannot compare its tools day to day functional
  • 18 Nov 26 0
    • This server's schema is too large to store in full, so we cannot compare its tools day to day functional
  • 17 Nov 26 +1
    • This server's schema is too large to store in full, so we cannot compare its tools day to day functional
  • 16 Nov 26 0
    • This server's schema is too large to store in full, so we cannot compare its tools day to day functional
  • 15 Nov 26 0
    • Schema quality: 1321 → 1525 ▼ functional
    • This server's schema is too large to store in full, so we cannot compare its tools day to day functional
  • 14 Nov 26 +1
    • This server's schema is too large to store in full, so we cannot compare its tools day to day functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://mcp.tier1protocol.app/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=tier1protocol.app CN=WE1,O=Google Trust Services,C=US 23 Oct 2026 21 Jan 2027 ECDSA 256 ECDSA-SHA256 173a22932eaf32210e05dfbbfcc1efa4
SANs: tier1protocol.app, mcp.tier1protocol.app, *.mcp.tier1protocol.app
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC secure

Validation of mcp.tier1protocol.app. — Secure

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
app. DS published 23684 8 Verified
tier1protocol.app. DS published 2371 13 Verified
mcp.tier1protocol.app. Verified address RRset verified with the apex keys
Authentication Enforced and verified

The endpoint asked for a token and published valid RFC 9728 metadata describing how to get one.

Result Enforced and verified
Enforced On tool calls
HTTP status 200

WWW-Authenticate challenge Bearer realm="OAuth", resource_metadata="https://mcp.tier1protocol.app/.well-known/oauth-protected-resource/mcp", error="invalid_token", error_description="Missing or invalid access token"

Bearer realm="OAuth", resource_metadata="https://mcp.tier1protocol.app/.well-known/oauth-protected-resource/mcp", error="invalid_token", error_description="Missing or invalid access token"
Header Value
strict-transport-security max-age=31536000; includeSubDomains; preload
x-content-type-options nosniff

Protected resource metadata

Document https://mcp.tier1protocol.app/.well-known/oauth-protected-resource/mcp
Retrieved Yes
Resource https://mcp.tier1protocol.app/mcp
Authorisation server https://mcp.tier1protocol.app

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://mcp.tier1protocol.app/mcp Verified 200
http (plaintext) http://mcp.tier1protocol.app/mcp HTTPS enforced 301 https://mcp.tier1protocol.app/mcp
MCP tools · 7 exposed · ~1,316 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
authorize_sources ~209

Add 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.

NameTypeReqDescription
authorization_confirmedbooleanyesMust be true only after the user explicitly confirms that Tier 1 may retain and route these files for 30 days.
filesarrayyesFiles the signed-in user selected in ChatGPT for Tier 1 to route.
profilestring–Optional keyed profile these files bind under, derived locally by the agent from the account key (profile_from_key_hex) and sent per request. The profile is key-equivalent: it is never stored or logg…
retention_daysnumberyesThe fixed retention period for this authorization.
NameTypeReqDescription
authorizedbooleanyes–
expiresAtstringyes–
filesarrayyes–
replayedbooleanyes–
totalBytesintegeryes–

No examples provided.

fetch ~84

Paid 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.

NameTypeReqDescription
idstringyesAn exact result id returned by a successful Tier 1 search for the same signed-in account. Never invent or alter this id.
NameTypeReqDescription
idstringyes–
metadataobject––
textstringyes–
titlestringyes–
urlstringyes–

No examples provided.

index ~396

Index 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.

NameTypeReqDescription
contentstringyesThe file's text, inline, as the chatbot read it. One batch carries at most 64 KiB of text (the current batch budget) — larger files are split and indexed in successive calls. This is the conversation…
content_hashstringyesSHA-256 of the source bytes, computed by the caller. This is the idempotency key: re-indexing the same bytes is a no-op and returns the existing result.
profilestringyesThe user's keyed profile, derived locally by the agent from the account key (profile_from_key_hex) and sent per request. The profile is key-equivalent: it is never stored or logged — only its fingerp…
source_labelstring–What the user calls this material ("my research paper," "the harbor project") — the human handle, stored with the manifest.
source_namestringyesThe file's name as the user knows it (e.g. harbor-renovation-notes.md).
NameTypeReqDescription
calls_remaining_today–yes–
ingestedintegeryes–
manifest_fingerprintstringyes–
protocolstringyes–
quota_remaining–yes–
replayedbooleanyes–
source_namestringyes–

No examples provided.

index_status ~96

How 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.

NameTypeReqDescription
profilestringyesThe user's keyed profile, sent per request. Only its fingerprint travels onward.
NameTypeReqDescription
calls_remaining_today–yes–
last_indexed_at–yes–
manifest_fingerprintstringyes–
pending_batchesintegeryes–
protocolstringyes–
quota_remaining–yes–
sources_indexedintegeryes–

No examples provided.

index_upload_token ~204

Mint 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.

NameTypeReqDescription
profilestringyesThe user's keyed profile, derived locally by the agent from the account key (profile_from_key_hex) and sent per request. Only its fingerprint travels onward — it is bound into the token, and the LIBR…
NameTypeReqDescription
expintegeryesUnix expiry (seconds) of the token.
expires_atstringyesISO-8601 expiry of the token.
principal_idstringyesThe authenticated principal_id. Paste it into the indexer page's principal field alongside the token — the page never collects it on its own, and the LIBRARY compares it to the upload body's principa…
profile_fingerprintstringyesSHA-256 of the profile, bound into the token and recorded by the LIBRARY on first write.
protocolstringyes–
tokenstringyesThe upload token. Paste it into the indexer page's upload-token field; it travels in the x-tier1-upload-token header. Valid 15 minutes for any number of sources under this principal and profile.

No examples provided.

render_context_results ~101

Inspect 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.

NameTypeReqDescription
idsarrayyesOne to six exact result ids returned by Tier 1 search for this signed-in account. Never pass caller-authored result objects.
NameTypeReqDescription
receiptobject––
resultsarrayyes–

No examples provided.

search ~226

Retrying 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.

NameTypeReqDescription
profilestring–Optional keyed profile for this search, derived locally by the agent from the account key (profile_from_key_hex) and sent per request. The profile is key-equivalent: it is never stored or logged — on…
querystringyesThe natural-language question to route across policy-eligible Tier 1 context. Eligible context may include private, shared, licensed, or public catalogs available to the paid account.
NameTypeReqDescription
receiptobject––
resultsarrayyes–

No examples provided.

Install

How do I install the Tier 1 Protocol MCP server?

Tier 1 Protocol is a hosted endpoint at https://mcp.tier1protocol.app/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · mcp.tier1protocol.app

# add to Claude Code
claude mcp add --transport http app-tier1protocol-mcp-tier-1-protocol 'https://mcp.tier1protocol.app/mcp'
Common questions

What is the Tier 1 Protocol MCP server?

Tier 1 Protocol is an MCP server listed in the public MCP registry as app.tier1protocol.mcp/tier-1-protocol. Search files while they stay encrypted: the problem DARPA chased for a decade. Exact quotes back. This page covers its hosted endpoint (https://mcp.tier1protocol.app/mcp).

Is the Tier 1 Protocol MCP server safe to use?

Tier 1 Protocol scores 84 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Tier 1 Protocol MCP server expose?

Tier 1 Protocol exposes 7 tools: search, authorize_sources, fetch, render_context_results, index, and 2 more. Their descriptions and schemas cost roughly 1,316 tokens of context every time the server is loaded.

Does the Tier 1 Protocol MCP server require authentication?

Yes. Tier 1 Protocol asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

Is the Tier 1 Protocol MCP server still maintained?

Tier 1 Protocol is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the Tier 1 Protocol MCP server?

VerifyMCP ran 14 checks on Tier 1 Protocol, covering TLS certificate, Authorization, HTTPS, HSTS header and 10 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.