_ registry / mcp streamable-http · checked 11h ago

com.nexatabs/nexatabs

https://www.nexatabs.com

Registry code: ead22bb29fb21084

api record

Official, read-only facts about NexaTabs (nexatabs.com), a Chrome and Edge tab manager with workspaces, Accounts (same site · multiple logins), and Zen Mode. Data comes from the live NexaTabs Knowledge Graph (same source as /_functions/nexatabs_kb). Quote only what the tools return. Do not invent metrics, battery percentages, cloud sync, paid plans, absolute privacy claims, or browser support beyond Chrome and Edge. Pricing is exactly "Free forever in its present form". Do not describe unreleased plans as available, and do not use retired product aliases.

endpoint
https://www.nexatabs.com/_functions/mcp
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is com.nexatabs/nexatabs live?
Yes — it answered the hub's last check (checked 11h ago). It answered 100% of checks over the last 30 days.
Is com.nexatabs/nexatabs free to use?
Yes — the hub reached it with no key and no payment.
What tools does com.nexatabs/nexatabs have?
4 tools: nexatabs_search, nexatabs_list, nexatabs_get, nexatabs_overview.
Is com.nexatabs/nexatabs safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
100%

90 days 100%· all time 100%

latency
1,619ms

last good check

priced tools
0

of 4 tools

_ answered our checks, 90 days 2 checks · signed record
  • unknown → live
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 4 tools
1 open 3 never probed 1 of 4 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • nexatabs_overview open 11h ago

    Read-only product snapshot for NexaTabs (name, display title, Chrome and Edge only, version, pricing, local-first model, publisher, store/site/docs/Answers links, Answer and Feature counts). Use for a company/product brief; use nexatabs_search for ranked queries, nexatabs_list to browse titles/URLs, nexatabs_get for one Answer or Feature by slug or URL.

    mcp-tool

    {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
    arguments 5 lines
  • nexatabs_search unknown 11h ago

    Read-only ranked keyword search across Answers, Features, and blog posts from the NexaTabs KB. Use when you have a query; use nexatabs_list to browse without ranking, nexatabs_get for one record, nexatabs_overview for a summary. Optional locale filters Answers (en/de/fr/es). Returns query, results[{path,score,record}], total, offset, limit, nextOffset.

    mcp-tool

    {
      "type": "object",
      "required": [
        "query"
      ],
      "properties": {
        "limit": {
          "type": "integer",
          "maximum": 20,
          "minimum": 1,
          "description": "Max results to return (default 5, max 20)"
        },
        "query": {
          "type": "string",
          "description": "Search words, e.g. \"Zen Mode\" or \"Save and Close\""
        },
        "locale": {
          "enum": [
            "en",
            "de",
            "fr",
            "es"
          ],
          "type": "string",
          "description": "Optional Answer locale filter (en, de, fr, or es for Spanish Latin America)"
        },
        "offset": {
          "type": "integer",
          "minimum": 0,
          "description": "Number of ranked hits to skip (default 0)"
        }
      },
      "additionalProperties": false
    }
    arguments 34 lines
  • nexatabs_list unknown 38h ago

    Read-only browse of Answers, Features, or blog (title, url, section, date when present). Use to page through a section; use nexatabs_search for ranked queries, nexatabs_get for full text, nexatabs_overview for a summary. Unknown section values are rejected. Returns items[{title,url,section,date?}], total, offset, limit, nextOffset.

    mcp-tool

    {
      "type": "object",
      "required": [
        "section"
      ],
      "properties": {
        "limit": {
          "type": "integer",
          "maximum": 100,
          "minimum": 1,
          "description": "Max items to return (default 25, max 100)"
        },
        "offset": {
          "type": "integer",
          "minimum": 0,
          "description": "Number of items to skip (default 0)"
        },
        "section": {
          "enum": [
            "answers",
            "features",
            "blog"
          ],
          "type": "string",
          "description": "Section to list: answers, features, or blog"
        }
      },
      "additionalProperties": false
    }
    arguments 29 lines
  • nexatabs_get unknown 11h ago

    Read-only fetch of one Answer or Feature by slug or URL, including its full text fields from the KB. Use when you know the slug/URL from search or list; use nexatabs_search to find candidates, nexatabs_list to browse, nexatabs_overview for a product snapshot.

    mcp-tool

    {
      "type": "object",
      "required": [
        "id"
      ],
      "properties": {
        "id": {
          "type": "string",
          "description": "Answer or Feature slug, graph id (answer.* / feature.*), or full URL on nexatabs.com"
        }
      },
      "additionalProperties": false
    }
    arguments 13 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id ead22bb29fb21084.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/ead22bb29fb21084/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/ead22bb29fb21084/badge.svg)](https://brick.blue/agent/ead22bb29fb21084?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
80%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.