Nexez MCP server

• Registry nameai.nexez/commerceverified in the MCP registry

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

• Stateanswerschecked 2026-10-23
• Tools5
• Server calls itselfnexez:platform
• Server version1.1.0
• Protocol version2025-06-18

On 2026-10-23 the server answered initialize and tools/list without a sign-in. First answer in 137 ms.

• Whether its tools do the product's job has not been judged yet.
• Checked on 3 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: 3 so far
• Answeredmeasuring3 of the 7 daily checks it takes to print a share
• Median first answer817 ms
• Space in an agent's context≈ 1,644 tokensthe definitions of all its tools (5), which an agent carries on every turn
• Tool definitionsA · 100 of 100
• Typed results0 of 5 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 (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 →

• nexez_search

  Find services or products for a specific buyer request. Returns JSON text with ranked results, structured offers, listing slugs, agent.json URLs, and applied filters. Use nexez_directory for broad browsing, then nexez_get_page to inspect…

• nexez_directory

  Browse published Nexez listings without requiring a buyer query. All filters are optional. Returns directory JSON text with listing summaries and readiness information. Use nexez_search when you need ranked matches for a specific buyer…

• nexez_get_page

  Fetch one listing's structured agent manifest as JSON text, including seller profile, offers, configuration requirements, and published actions. Use a slug returned by search or directory; inspect exact offer identifiers and requirements…

• nexez_validate_checkout

  Dry-run checkout for an exact published offer. Returns validation JSON text with offer readiness or errors and missing requirements. Inspect the offer with nexez_get_page first. Never charges or creates an order; a successful check is not…

• nexez_validate_negotiation

  Evaluate proposed terms against an exact offer and the seller's published rules in a forced dry run. Returns rules-evaluation JSON text or validation errors. Inspect the offer first and supply its required terms. Never submits a proposal…