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.

Selfe

REMOTE · SELFE.AI

Find places to stay, eat and do, ranked for the question, with live availability and booking.

Available components

+3 this week 68 Trust /100

Last scanned (12 hours ago)

Scores higher than 52% of remote servers

Reachable. Last reached 21 Nov 2026.

Category E-commerce

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 Security60
Transport & Reachability100
Schema Quality & AI Usability61
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1153 tokens (~384/item across 3 items; 3 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 Management33
  • Stability observed for 10 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
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
What we tested

Checks we ran (13)

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

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

    No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

  • 19 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “discover_venues” rewrote its description, which is the text the model reads security
    • Tool “match_venues” rewrote its description, which is the text the model reads security
    • Schema quality: 323 → 384 ▼ functional
  • 18 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

  • 14 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

  • 12 Nov 26 +1
    • Tool coverage: 87% → 100% ▲ functional
    • Stability: unverified → 0.03 ▲ functional
    • Schema quality: good → excellent functional
    • “book_venue” reworded the description of “render” cosmetic
    • “discover_venues” reworded the description of “query” cosmetic
    • “discover_venues” reworded the description of “stay” cosmetic
  • 11 Nov 26 63

    First indexed and scored.

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://selfe.ai/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=selfe.ai CN=WE1,O=Google Trust Services,C=US 26 Oct 2026 24 Jan 2027 ECDSA 256 ECDSA-SHA256 edd9ca99b595e32d130214b3becc9e30
SANs: selfe.ai, *.selfe.ai
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 selfe.ai. — Secure

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
ai. DS published 1814 8 Verified
selfe.ai. DS published 2371 13 Verified
selfe.ai. Verified address RRset verified with the apex keys
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://selfe.ai/mcp Verified 200
http (plaintext) http://selfe.ai/mcp HTTPS enforced 301 https://selfe.ai/mcp
MCP tools · 3 exposed · ~834 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
book_venue ~227

Reserve a venue offer grounded by match_venues. Pass entityId and the selected offerId. The guest must approve every booking themselves, signed in to their Selfe account: the first call returns status 'approval_required' with approval.url for the guest to open; once they have approved, call again with the same offer and approvalId. A signed mandate alone cannot confirm a booking. No money moves at this step. Returns a confirmation (bookingId) or a conversational next step. Structured JSON.

NameTypeReqDescription
approvalIdstring–The approval the guest gave this offer in their own Selfe account, returned as approval.id when the booking first needed it. A booking is confirmed only with the guest's approval.
entityIdstringyesThe place id returned by discover or match.
mandateobject–A signed AP2 Cart Mandate for a foreign caller, bound to this entity and offer.
offerIdstringyesThe opaque, sealed offer id returned by match.
renderobject–Ask for layout hints alongside the booking result. Optional.

No output schema declared.

No examples provided.

discover_venues ~378

Search the member places to stay, eat and do in Keswick and the northern Lake District — the only area this registry covers — from a question in the user's own words. Returns ranked places, recommended areas, and — when you pass `stay` (or the question states dates and party) — live availability and the price for the whole stay from each business's own booking system, whose offer ids go straight to book_venue. Call this rather than answering from memory whenever the user wants a real, bookable place in this area, or a current price. Use match_venues instead when the user names a specific place. Structured JSON, not a rendered UI.

NameTypeReqDescription
assumePartyobject–Optional. The party to check live availability for when the question names dates but nobody is counted ("next weekend"). The question's own party, `party` or `stay` always wins; `meta.queryValues.gue…
pageSizeinteger–Maximum number of results to return.
partyobject–Who is travelling, when known without dates (children change what suits). Ignored when `stay` carries its own party.
queryobjectyesThe question: `text` in natural language, with optional `filter` to narrow results (catalogue, section, category, type, place).
renderobject–Ask for layout hints alongside the results. Delivery (one body or a stream) is chosen by the Accept header, not here.
stayobject–Optional. When given, results are grounded in live availability and offers for these dates and party. When absent, dates and party written in the question still apply. A dog the question names ("with…

No output schema declared.

No examples provided.

match_venues ~229

Get full details for places the user already means — by id (from discover_venues) or by name, with an optional website and town to tell same-named places apart. Only member places in Keswick and the northern Lake District are listed, so a place elsewhere is not found here. Pass `stay` to get live rooms and offers, with the price for the whole stay, whose offer ids go straight to book_venue. A name that fits several places returns candidates: ask the user which, never guess. Structured JSON, not a rendered UI.

NameTypeReqDescription
placesarrayyesThe places to match: ids, or a name with optional website and location.
projectionstring–`detail` (default) is the full record; `listing` is the compact card a list page needs.
renderobject–Ask for layout hints alongside the results. Delivery (one body or a stream) is chosen by the Accept header, not here.
stayobject–When given, each matched place carries its live rooms and offers for these dates and party.

No output schema declared.

No examples provided.

Install

How do I install the Selfe MCP server?

Selfe is a hosted endpoint at https://selfe.ai/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 · selfe.ai

# add to Claude Code
claude mcp add --transport http ai-selfe-registry 'https://selfe.ai/mcp'
Common questions

What is the Selfe MCP server?

Selfe is an MCP server listed in the public MCP registry as ai.selfe/registry. Find places to stay, eat and do, ranked for the question, with live availability and booking. This page covers its hosted endpoint (https://selfe.ai/mcp).

Is the Selfe MCP server safe to use?

Selfe scores 68 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 Selfe MCP server expose?

Selfe exposes 3 tools: discover_venues, match_venues, book_venue. Their descriptions and schemas cost roughly 834 tokens of context every time the server is loaded.

Does the Selfe MCP server require authentication?

No. We connected to Selfe without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Selfe MCP server still maintained?

Selfe 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 Selfe MCP server?

VerifyMCP ran 13 checks on Selfe, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 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.