AppFinder MCP server

• Registry nametech.appfinder/appfinderverified in the MCP registry

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

• Stateanswerschecked 2026-11-01
• Tools9
• Server calls itselfappfinder
• Server version1.0.0
• Protocol version2025-06-18

On 2026-11-01 the server answered initialize and tools/list without a sign-in. First answer in 665 ms.

• Its tools do every use case we checked: search for software by describing the job needed; compare two tools side by side; find alternatives to a tool you already know.
• Checked on 1 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: 1 so far
• What an agent can do with it3 of 3 use cases
• Answeredmeasuring1 of the 7 daily checks it takes to print a share
• Median first answer671 ms
• Space in an agent's context≈ 1,403 tokensthe definitions of all its tools (9), which an agent carries on every turn
• Tool definitionsA · 100 of 100
• Typed results0 of 9 toolsdeclared outputSchema: results come typed, read once

• Every tool passes all six checks.

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 →

• recommend_apps

  Ranks the apps in the AppFinder directory against a plain-language request and explains each pick with cited facts (what fits, what's missing, which apps a must-have rules out), plus one follow-up question that would narrow the list.

• search_apps

  Full-text search of the directory by name, keyword or job (most relevant first).

• get_app

  One app's listing: description, categories, pricing, platforms, features, integrations, rating and its facts with sources.

• compare_apps

  Side by side: pricing, and the features, integrations and platforms both apps have or only one has.

• find_alternatives

  Apps that do what an app does (same category, most shared features first), and what buyers who wanted to replace it chose.

• list_categories

  The directory's categories with how many apps each lists.

• category_demand

  The public demand report of a category: the share of buyers who asked the advisor for each feature, integration, security need and budget in the last 90 days (anonymous totals), and how many listed apps answer each.

• check_listing

  Whether a website already has a published AppFinder listing, and its page. Call this before prepare_listing.

• prepare_listing

  For a maker who wants to list their own app: fills in AppFinder's submission form from what they told you plus the app's website, and returns a private link. The person opens it, signs in, reviews every field and submits; nothing is…