Polargate MCP server

• Registry nameai.polargate/polargateverified in the MCP registry

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

• Stateanswerschecked 2026-10-27
• Tools8
• Server calls itselfpolargate
• Server version1.0.1
• Protocol version2025-06-18

On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 1530 ms.

• Its tools do none of the product's use cases we checked: Build a custom internal portal to replace shared spreadsheets; Turn guest requests into tickets for hotel operations; Make a website readable by AI assistants and search engines.

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 score64 of 100answers 94 · does the job 0 · definitions 71 · context 100 · connects 100
• What an agent can do with it0 of 3 use cases
• Answered100% of days7 of 7 daily checks
• Median first answer1551 ms
• Space in an agent's context≈ 831 tokensthe definitions of all its tools (8), which an agent carries on every turn
• Tool definitionsC · 71 of 100
• Typed results0 of 8 toolsdeclared outputSchema: results come typed, read once

• Parameters without a description: in 6 of 8
• Not saying whether it only reads or can destroy: 8 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 (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). 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 →

• list_services

  The three service lines (build, grow, care) and every capability under them, with what each includes, the typical timeline, who works on it and how it is priced.

• get_pricing

  How Polargate engages: every model (Discovery Sprint, fixed-price projects, Care, Grow, the AI visibility audit) with what it includes, who it is for and how it is billed. Polargate does not publish prices: each engagement gets a fixed…

• list_cases

  Projects Polargate has delivered, with the client where the client agreed to be named, measured outcomes, the stack and a link to the live site. Filter by industry or service line.

• get_case

  The full case study for one project, including the markdown of the page. Use list_cases first to find the slug.

• search_site

  Find pages by words in their title or description, across all three languages. Returns the page URL and its markdown twin.

• get_page

  The full text of any page on polargate.ai, as markdown. Give the route, for example /pricing or /es/work/hotel-marien.

• list_products

  Products Polargate makes and owns, as opposed to work for clients. PolarJay (https://polarjay.com) is Polargate's AI visibility product: it measures what ChatGPT, Gemini, Perplexity, Claude and Google's AI Overviews say about a company…

• how_to_start

  How to engage Polargate: what the brief asks, the answer time, the languages spoken and where the work is done from.