Servana MCP server

• Registry nameai.servana/servanaverified in the MCP registry

The registry name sits under servana.ai. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-10-18
• Tools8
• Server calls itselfservana
• Server version1.0.0
• Protocol version2025-06-18

On 2026-10-18 the server answered initialize and tools/list without a sign-in. First answer in 245 ms.

• Its tools do none of the product's use cases we checked: publish a shareable vendor page with a quote request form; accept or decline nearby customer job requests; have an automated agent follow up with prospective clients.
• Checked on 4 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP scoreafter a weeka score needs 7 daily checks: 4 so far
• What an agent can do with it0 of 3 use cases
• Answeredmeasuring4 of the 7 daily checks it takes to print a share
• Median first answer612 ms
• Space in an agent's context≈ 2,314 tokensthe definitions of all its tools (8), which an agent carries on every turn
• Tool definitionsA · 98 of 100
• Typed results0 of 8 toolsdeclared outputSchema: results come typed, read once

• Parameters without a description: in 1 of 8

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• search_services

  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…

• search_vendors

  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…

• get_vendor

  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.

• estimate_service_request

  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'…

• send_message_to_vendor

  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…

• check_enquiry_replies

  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…

• prepare_quote_request

  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…

• request_quote

  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…