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.

Servana

REMOTE · SERVANA.AI

Search and message local service vendors (cleaning, med spa, yoga, personal training) by city.

Available components

0 this week 80 Trust /100

Last scanned (22 hours ago)

Scores higher than 77% of remote servers

Reachable. Last reached 21 Nov 2026.

Category CRM and Sales

Recent critical change

Authorization (9 Nov 2026). See the changelog before you install this server.

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 Security63
Transport & Reachability100
Schema Quality & AI Usability79
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 2097 tokens (~209/item across 10 items; 8 tools + 2 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 Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage95
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 84% 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 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities73
  • Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
  • 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.

  • 9 Nov 26 0
    • Authorization: unverified → fail ▼ critical
    • Injection markers: unverified → pass ▲ security
    • Stability: unverified → pass ▲ security
    • HSTS header: unverified → pass ▲ security
    • Transport: fail → pass ▲ security
    • MCP protocol: unverified → fail ▼ functional
    • Endpoint reachability: unreachable → reachable ▲ functional
    • Tool coverage: unverified → 100 ▲ functional
    • Schema quality: unverified → 100 ▲ functional
  • 8 Nov 26 0
    • Endpoint reachability: reachable → unreachable ▼ security
    • Authorization: fail → unverified ▼ security
    • Stability: pass → unverified ▼ security
    • Tool safety: pass → unverified ▼ security
    • HSTS header: pass → unverified ▼ security
    • Transport: pass → fail ▼ security
    • Schema quality: 100 → unverified ▼ functional
    • Capabilities: fail → unverified ▼ functional
    • Tool coverage: 100 → unverified ▼ functional
  • 6 Nov 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 10 Oct 26 0
    • Tool coverage: 100% → 84% ▼ functional
    • Schema quality: 235 → 209 ▲ functional
    • First check of Capabilities: pass functional
    • First check of Schema quality: 100 functional
  • 2 Oct 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “estimate_service_request” rewrote its description, which is the text the model reads security
    • Tool “get_vendor” rewrote its description, which is the text the model reads security
    • Tool “search_services” rewrote its description, which is the text the model reads security
    • Tool “search_vendors” rewrote its description, which is the text the model reads security
    • Tool “send_message_to_vendor” rewrote its description, which is the text the model reads security
    • Schema quality: 147 → 235 ▼ functional
    • “estimate_service_request” reworded the description of “city” cosmetic
    • “estimate_service_request” reworded the description of “service” cosmetic
    • “estimate_service_request” reworded the description of “state” cosmetic
    • “search_services” reworded the description of “query” cosmetic
    • “search_vendors” reworded the description of “city” cosmetic
    • “search_vendors” reworded the description of “service” cosmetic
    • “search_vendors” reworded the description of “state” cosmetic
    • “send_message_to_vendor” reworded the description of “message” cosmetic
  • 28 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 26 Sept 26 0
    • Stability: 0.97 → pass security
  • 25 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → 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://servana.ai/api/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=servana.ai CN=WE1,O=Google Trust Services,C=US 7 Oct 2026 5 Jan 2027 ECDSA 256 ECDSA-SHA256 12c5238e4fd894690e693acb91d6de0d
SANs: servana.ai, *.servana.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 insecure

Validation of servana.ai. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
ai. DS published 1814 8 Verified
servana.ai. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
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
Header Value
strict-transport-security max-age=31536000; includeSubDomains
x-content-type-options nosniff
x-frame-options SAMEORIGIN
referrer-policy strict-origin-when-cross-origin
permissions-policy camera=(), microphone=(), geolocation=()

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://servana.ai/api/mcp Verified 200
http (plaintext) http://servana.ai/api/mcp HTTPS enforced 301 https://servana.ai/api/mcp
MCP tools · 8 exposed · ~1,818 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
check_enquiry_replies ~94

Use this when the user asks whether a business answered an enquiry sent earlier in this conversation with send_message_to_vendor. Pass the enquiry_refs that send_message_to_vendor returned. Returns, per business, whether it replied and the latest reply. Do not use for enquiries sent outside this conversation or without a ref; never guess a ref.

NameTypeReqDescription
enquiry_refsarrayyesThe enquiry_refs returned by send_message_to_vendor

No output schema declared.

No examples provided.

estimate_service_request ~318

Use this when the user asks what a local service costs in a city (e.g. 'how much is a deep clean in NYC?'). Returns a rough range from Servana businesses' posted rates with a confidence level ('high' = 5+ local priced businesses, 'medium' = 2-4, 'low' = 0-1, then a category-wide median) and an explanation naming the sample. Always call it an estimate, never a quote: each business sets its own price. Do not use for one business's prices; use get_vendor.

NameTypeReqDescription
citystringyesCity name or slug (e.g. 'new-york', 'tampa', 'los-angeles'). For New York City use 'new-york'.
hoursnumber–Optional: estimated hours needed, if known. Overrides job_size for hourly-rate services.
job_sizestring–Rough size of the job. Defaults to 'medium'.
servicestringyesService category slug: 'cleaning-and-organizing' (house cleaning, decluttering), 'laundry-washing' (wash and fold), 'med-spa' (botox, facials, skincare), 'yoga', 'personal-training', 'photography', '…
statestringyesUS state, as a name or slug (e.g. 'new-york', 'florida'). Two-letter codes like 'NY' also work.

No output schema declared.

No examples provided.

get_vendor ~81

Use this when the user asks about one specific business from search_vendors results or a servana.ai page: its services, prices, rating, claim status, and whether it accepts messages from AI assistants. Do not use to search for businesses.

NameTypeReqDescription
vendor_slugstringyesThe vendor's slug from search_vendors results or a servana.ai vendor URL

No output schema declared.

No examples provided.

prepare_quote_request ~253

Use this when the user wants quotes or availability from 1 to 3 Servana businesses (slugs from search_vendors). It shows a quote request form with the details those businesses need (date, area, size and so on), pre-filled with what the user already said, so the user can check and send it. Prefer this over writing a free-text message. It sends nothing. Do not use for businesses that were not returned by search_vendors.

NameTypeReqDescription
customer_emailstring–The user's email, if they gave it
customer_namestring–The user's name, if they gave it
detailsobject–What the user already said, keyed by field: date_window, time_window, area, home_size, job_details, frequency, session_goal, session_count, treatment, shoot_type, duration, people_count, load_size, b…
notesstring–Anything else the user wants to say
servicestring–Service category slug, e.g. 'cleaning-and-organizing'
vendor_slugsarrayyes1 to 3 business slugs from search_vendors

No output schema declared.

No examples provided.

request_quote ~179

Use this when the user approved a structured quote request to 1 to 3 Servana businesses (usually from the prepare_quote_request form). Servana formats the details the businesses asked for and emails the user their replies. If details are missing it returns which ones; ask the user, never invent. Do not use to book or pay; Servana does neither.

NameTypeReqDescription
customer_emailstringyes–
customer_namestringyes–
customer_phonestring––
detailsobjectyesField values keyed by: date_window, time_window, area, home_size, job_details, frequency, session_goal, session_count, treatment, shoot_type, duration, people_count, load_size, budget
notesstring––
servicestring–Service category slug
vendor_slugsarrayyes–

No output schema declared.

No examples provided.

search_services ~185

Use this when the user describes a local service they want done in person (e.g. 'someone to fold my laundry', 'deep clean my apartment', 'a trainer who comes to my home') and you need Servana's category slug for search_vendors or estimate_service_request. Skip it if the request clearly fits one of these slugs: 'cleaning-and-organizing' (house cleaning, decluttering), 'laundry-washing' (wash and fold), 'med-spa' (botox, facials, skincare), 'yoga', 'personal-training', 'photography', 'home-services' (handyman, home upkeep), 'personal-services'. Do not use for online products, emergencies, or medical, legal or financial advice.

NameTypeReqDescription
querystringyesShort description of the task the user needs done (a task, not a category name)

No output schema declared.

No examples provided.

search_vendors ~373

Use this when the user wants to find, compare or hire a local business for an in-person service in a US city: house cleaners, laundry, med spas, yoga teachers, personal trainers, photographers, home services. Returns real businesses listed on Servana with rating, pricing when posted, claim status and a page URL. If it returns no results, tell the user Servana has no listed business for that yet; never invent one. Pass the user's specific need in `need` (e.g. decluttering, deep clean, packages) so the best-fitting businesses come first. Nearby towns are searched together (e.g. Nocatee with Ponte Vedra). Do not use for businesses outside the US or for services Servana does not list (use search_services if unsure).

NameTypeReqDescription
citystringyesCity name or slug (e.g. 'new-york', 'tampa', 'los-angeles'). For New York City use 'new-york'.
needstring–The user's specific need in their own words, e.g. 'declutter and organize a cluttered house, best packages'. Ranks businesses whose own description matches it first; never invents a match.
servicestring–Optional service category slug: 'cleaning-and-organizing' (house cleaning, decluttering), 'laundry-washing' (wash and fold), 'med-spa' (botox, facials, skincare), 'yoga', 'personal-training', 'photog…
statestringyesUS state, as a name or slug (e.g. 'new-york', 'florida'). Two-letter codes like 'NY' also work.

No output schema declared.

No examples provided.

send_message_to_vendor ~335

Use this when the user has chosen a Servana business and asks you to contact it, request a quote, or ask about availability. It sends the user's enquiry to the business; Servana emails the user when the business replies. Pass customer_name and customer_email when the user gave them. To ask several businesses at once (up to 3), put the extra slugs in also_vendor_slugs. Keep the enquiry_refs it returns for check_enquiry_replies. Before calling, show the user the exact message and get their approval, and include their name and an email or phone number. Do not use to confirm a booking or take payment (Servana does neither), or for businesses marked as not accepting AI-assistant messages.

NameTypeReqDescription
also_vendor_slugsarray–Optional: up to 2 more Servana businesses (slugs from search_vendors) to send the same enquiry to. Only when the user asked to contact several businesses and approved the one message for all of them.
customer_emailstring–The user's email, as they gave it. Servana emails the user a link to read the business's reply. Never invent one.
customer_namestring–The user's name, as they gave it. Needed so the business knows who is asking.
customer_phonestring–Optional phone number, only if the user gave one.
messagestringyesThe enquiry: what the user needs, when and where, plus the user's name and preferred contact (email or phone) so the business can reply
vendor_slugstringyesThe vendor's slug

No output schema declared.

No examples provided.

Install

How do I install the Servana MCP server?

Servana is a hosted endpoint at https://servana.ai/api/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 · servana.ai

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

What is the Servana MCP server?

Servana is an MCP server listed in the public MCP registry as ai.servana/servana. Search and message local service vendors (cleaning, med spa, yoga, personal training) by city. This page covers its hosted endpoint (https://servana.ai/api/mcp).

Is the Servana MCP server safe to use?

Servana scores 80 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 Servana MCP server expose?

Servana exposes 8 tools: search_services, search_vendors, get_vendor, estimate_service_request, send_message_to_vendor, and 3 more. Their descriptions and schemas cost roughly 1,818 tokens of context every time the server is loaded.

Does the Servana MCP server require authentication?

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

Is the Servana MCP server still maintained?

Servana 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 Servana MCP server?

VerifyMCP ran 14 checks on Servana, 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.