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.

Sergio by Serviche

REMOTE · SERGIO.SERVICHE.COM

Make sure nothing falls through the cracks in your cleaning business, even when you're not watching.

+2 this week 79 Trust /100

Last scanned (15 hours ago)

Scores higher than 74% of remote servers

Reachable. Last reached 21 Nov 2026.

Category CRM and Sales

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
Transport & Reachability100
Schema Quality & AI Usability53
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 24472 tokens (~235/item across 104 items; 104 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 Management32
  • Stability check failed: schema churn in the 12 days we've observed: 8 tool removals, 1 breaking changes, 0 auth/transport breaks, 4 additions. See how to fix → Fail
Tool Coverage76
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 27% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 10 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 105 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
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
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “create_client” rewrote its description, which is the text the model reads security
    • Tool “edit_client” rewrote its description, which is the text the model reads security
    • Tool “report_feedback” rewrote its description, which is the text the model reads security
    • New tool “move_address_to_contact” functional
    • “edit_client” added an optional parameter “access_method” cosmetic
    • “edit_client” added an optional parameter “same_person_as” cosmetic
    • “edit_client” added an optional parameter “separate_person” cosmetic
    • “report_feedback” added an optional parameter “hypothesis” cosmetic
  • 18 Nov 26 +1
    • Tool “catalog” rewrote its description, which is the text the model reads security
    • Tool “create_client” rewrote its description, which is the text the model reads security
    • “catalog” added an optional parameter “schemas” cosmetic
    • “create_client” added an optional parameter “address” cosmetic
  • 16 Nov 26 0
    • A breaking change shipped without a version bump: still 1.0.2 ▼ security
    • Tool “add_training_question” was removed ▼ security
    • Tool “archive_training_module” was removed ▼ security
    • Tool “create_training_module” was removed ▼ security
    • Tool “delete_training_question” was removed ▼ security
    • Tool “edit_training_module” was removed ▼ security
    • Tool “edit_training_question” was removed ▼ security
    • Tool “generate_training_questions” was removed ▼ security
    • Tool “remove_training_assignment” was removed ▼ security
    • Tool “create_client” rewrote its description, which is the text the model reads security
    • Tool “create_handbook_article” rewrote its description, which is the text the model reads security
    • Tool “draft_handbook_edit” rewrote its description, which is the text the model reads security
    • Tool “edit_client” rewrote its description, which is the text the model reads security
    • Tool “edit_handbook_article” rewrote its description, which is the text the model reads security
    • Tool “query” rewrote its description, which is the text the model reads security
    • Tool “read” rewrote its description, which is the text the model reads security
    • Tool “update_settings” rewrote its description, which is the text the model reads security
    • “create_client” added an optional parameter “platform_customer” cosmetic
    • “edit_client” added an optional parameter “platform_customer” cosmetic
  • 14 Nov 26 +1
    • Stability: 0.13 → fail ▼ security
    • A breaking change shipped without a version bump: still 1.0.2 ▼ security
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “read” rewrote its description, which is the text the model reads security
    • Tool “reopen_task” rewrote its description, which is the text the model reads security
    • Tool “update_settings” rewrote its description, which is the text the model reads security
    • “reopen_task” added a required parameter “reopen_reason”, so existing callers break ▼ functional
  • 13 Nov 26 0
    • New tool “record_staff_event” functional
  • 12 Nov 26 0
    • Tool “update_settings” rewrote its description, which is the text the model reads security
    • New tool “edit_staff_member” functional
  • 11 Nov 26 +1
    • Tool “query” rewrote its description, which is the text the model reads security
    • Tool “update_settings” rewrote its description, which is the text the model reads security
    • New tool “log_call” functional
  • 10 Nov 26 0
    • Stability: unverified → 0.03 ▲ 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://sergio.serviche.com/api/agent/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=serviche.com CN=YE1,O=Let's Encrypt,C=US 9 Oct 2026 7 Jan 2027 ECDSA 256 ECDSA-SHA384 53905d714ec75cf625c8ee2fc4453319a0f
SANs: *.serviche.com, serviche.com
CN=YE1,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 5ddd70dd31f801c85c186a7a04b80afe
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of sergio.serviche.com. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
com. DS published 19718 13 Verified
serviche.com. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
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="sergio-agent", resource_metadata="https://sergio.serviche.com/.well-known/oauth-protected-resource"

Bearer realm="sergio-agent", resource_metadata="https://sergio.serviche.com/.well-known/oauth-protected-resource"
Header Value
strict-transport-security max-age=63072000; includeSubDomains
content-security-policy default-src 'none'; frame-ancestors 'none'
x-content-type-options nosniff
x-frame-options DENY
referrer-policy strict-origin-when-cross-origin
permissions-policy camera=(), microphone=(), geolocation=(), payment=(), usb=(), serial=(), bluetooth=(), display-capture=(self)

Protected resource metadata

Document https://sergio.serviche.com/.well-known/oauth-protected-resource
Retrieved Yes
Resource https://sergio.serviche.com/api/agent/mcp
Authorisation server https://sergio.serviche.com

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://sergio.serviche.com/api/agent/mcp Verified 200
http (plaintext) http://sergio.serviche.com/api/agent/mcp HTTPS enforced 301 https://sergio.serviche.com/api/agent/mcp
MCP tools · 104 exposed · ~23,695 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
update_settings ~1,083

Changes one or more of the organization's settings, as a person on the Settings page would, with this seat's role deciding what it may change. Sending controls, anything that opens a page to the public, payments, spend increases, and access are never available to agents. Owner-level and confirm-level settings are available when the owner turned on "Let this agent change owner settings" for this seat on the Team page (on by default for an agent the owner adds); the owner is told about each such change, with your justification if you give one. Pass changes as { "<setting key>": value }. Keys: notification_settings.enabled (toggle); notification_settings.rules (editor); settings.booking_platforms (list); urgency_settings.do_now_lead_minutes (number); urgency_settings.task_lookahead_days (number); org.chime_enabled (toggle); settings.reply_chime.delayMinutes (number); settings.reply_chime.repeatSeconds (number); settings.reply_chime.muteMinutes (number); settings.schedule.view (enum); settings.schedule.startHour (number); settings.schedule.weekStart (enum); settings.holiday_behavior (enum); settings.holiday_audience (enum); org_holidays (list); settings.field_schedule_requests_enabled (toggle); settings.field_self_block (toggle); platform_email_rules (list); settings.review_alert_at_or_below (number); blocked_senders (list); auto_assignment_config.enabled (toggle); auto_assignment_config.pool (list); auto_assignment_config.auto_classify_flows (toggle); settings.holidays_enabled (toggle, null resets it); booking_settings.policies.clock.autoClockOut (toggle); booking_settings.policies.clock.signatureRequired (toggle); booking_settings.policies.clock.geofenceRadiusHighM (number); booking_settings.policies.clock.geofenceRadiusMediumM (number); booking_settings.policies.clock.geofenceRadiusFallbackM (number); booking_settings.policies.notifications.cleanerMessageMode (enum); settings.persona_name (text, null resets it); settings.hand_sent_text_signoff (toggle); settings.cri…

NameTypeReqDescription
changesobjectyesSetting key -> new value. Send only the keys that change.
idempotency_keystringyesYour id for this operation (8-128 of A-Z a-z 0-9 . _ : -). Reuse it on every retry of the same operation; use a new one for a new operation.
justificationstring–Optional: why the business wants this change. Shown to the owner in the notice Sergio sends after an owner-level change.

No output schema declared.

No examples provided.

update_task ~209

Edits a task as a person can on its row: title, description (details), due_date (ISO 8601 with offset, or null to clear), priority, client_id or conversation_id (null unlinks). Send only the fields to change. A flow-step task shifts its later steps when its due time moves, as in the app. Pass the same idempotency_key when retrying; a repeat returns the task, reports what the original call applied, and changes nothing if the task changed since.

NameTypeReqDescription
client_id–––
conversation_id–––
description–––
due_date–––
idempotency_keystringyesYour id for this operation (8-128 of A-Z a-z 0-9 . _ : -). Reuse it on every retry of the same operation; use a new one for a new operation.
prioritystring––
task_idstringyes–
titlestring––

No output schema declared.

No examples provided.

upload_spreadsheet ~238

Uploads a bookings or clients spreadsheet (CSV text) and queues its import, as Upload on the Imports page does; nothing is written to customers until its columns are checked. source is the import source spelling, not a free label: a booking platform's key for its bookings export (for example bookingkoala), that key plus -clients for its clients export (for example bookingkoala-clients), or spreadsheet / spreadsheet-clients for a generic spreadsheet export. read('data_sources') names this business's platform. Returns jobId. Pass the same idempotency_key when retrying. An owner-level change: Sergio tells the owner after it is made.

NameTypeReqDescription
csvstringyes–
idempotency_keystringyesYour id for this operation (8-128 of A-Z a-z 0-9 . _ : -). Reuse it on every retry of the same operation; use a new one for a new operation.
reasonstring–Why you are doing this, in one sentence. The owner sees it in the notice Sergio sends after the change.
sourcestringyes–

No output schema declared.

No examples provided.

whoami ~84

Returns this agent seat: its name, role, member id, the organization it belongs to, the key id this call used, whether the owner allowed it to run SQL queries, and what it reads as (readsAs: "owner" when the owner allowed owner-level reading for this key, else its role) versus what it acts as (actsAs: always its role).

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

Install

How do I install the Sergio by Serviche MCP server?

Sergio by Serviche is a hosted endpoint at https://sergio.serviche.com/api/agent/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 · sergio.serviche.com

# add to Claude Code
claude mcp add --transport http com-serviche-sergio 'https://sergio.serviche.com/api/agent/mcp'
Common questions

What is the Sergio by Serviche MCP server?

Sergio by Serviche is an MCP server listed in the public MCP registry as com.serviche/sergio. Make sure nothing falls through the cracks in your cleaning business, even when you're not watching. This page covers its hosted endpoint (https://sergio.serviche.com/api/agent/mcp).

Is the Sergio by Serviche MCP server safe to use?

Sergio by Serviche scores 79 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 Sergio by Serviche MCP server expose?

Sergio by Serviche exposes 104 tools: whoami, catalog, report_feedback, events_subscribe, events_list, and 99 more. Their descriptions and schemas cost roughly 23,695 tokens of context every time the server is loaded.

Does the Sergio by Serviche MCP server require authentication?

Yes. Sergio by Serviche 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 Sergio by Serviche MCP server still maintained?

Sergio by Serviche 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 Sergio by Serviche MCP server?

VerifyMCP ran 13 checks on Sergio by Serviche, 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.