_ registry / mcp + a2a streamable-http · checked 1h ago

netstate

https://netstate.co

Registry code: d195487bae36e48d

api record

Netstate is a business verification platform for discovering, verifying and monitoring companies against the official public record. It covers 128 million companies across every US state, DC, Puerto Rico and Canada — registration status and good standing, officers, EIN, UCC liens, licenses and permits, federal contractor, loan and filing history, plus OpenSanctions and PEP screening — with every field cited to its government source. Teams use it for KYB, onboarding, underwriting and due diligence: Netstate resolves and screens the record; your people review it and make the decisions. Start…

endpoint
https://netstate.co/mcp
door code
eb9ee5927b37d204
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 netstate live?
Yes — it answered the hub's last check (checked 1h ago). It answered 99% of checks over the last 30 days.
Is netstate free to use?
Yes — the hub reached it with no key and no payment.
What tools does netstate have?
4 tools: search_companies, register_agent, list_jurisdictions, get_site_info.
Is netstate 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
98.8%

90 days 96.8%· all time 97.6%

latency
508ms

last good check

priced tools
0

of 4 tools

_ answered our checks, 90 days 895 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
_ what it is for
used for
  • search registered us and canadian companies
  • verify a company's good standing
  • screen a company against sanctions and pep lists
  • list jurisdictions for queries
takes → gives
text → data
tools
3 reads1 changes data
_ 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
2 open 2 never probed 2 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.

  • list_jurisdictions reads open 19h ago

    The taxonomy for building queries: countries with regions (and cities when a country+region is given), industries, statuses, and total company count. Call this first to find valid slugs for the other tools.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "region": {
          "type": "string",
          "description": "Also list the cities of this region (requires country)"
        },
        "country": {
          "type": "string",
          "description": "Limit to one country slug"
        }
      }
    }
    arguments 13 lines
  • get_site_info reads open 19h ago

    What Netstate is, its pricing plans, API endpoints, FAQ and usage restrictions. Call this to learn what the site offers before using the data tools.

    mcp-tool

    {
      "type": "object",
      "properties": {}
    }
    arguments 4 lines
  • search_companies reads unknown 19h ago

    Full-text search across 128 million registered companies in official US and Canadian state registers — by legal name, officer or director name, phone number, email or website. Contact-shaped queries (phone/email/website) resolve through the official records carrying that exact value; the response's matched_by field says which channel matched. Filters mirror the website's facet rail; the response carries up to 25 matching profiles plus facet counts. Facet counts describe every name match (not just the filtered set), so they show which filter values would widen or narrow the search. Records are for human review — not for automated decisions covered by the FCRA.

    mcp-tool

    {
      "type": "object",
      "required": [
        "query"
      ],
      "properties": {
        "has": {
          "type": "array",
          "items": {
            "enum": [
              "officers",
              "ein",
              "naics",
              "phone",
              "email",
              "website",
              "revenue"
            ],
            "type": "string"
          },
          "description": "Only companies with this data on file (multi-select)"
        },
        "sort": {
          "enum": [
            "relevance",
            "newest",
            "oldest",
            "name",
            "revenue"
          ],
          "type": "string",
          "description": "Result order"
        },
        "type": {
          "enum": [
            "llc",
            "corporation",
            "nonprofit",
            "lp",
            "llp",
            "professional_corporation",
            "professional_llc",
            "other"
          ],
          "type": "string",
          "description": "Entity type"
        },
        "year": {
          "enum": [
            "2020s",
            "2010s",
            "2000s",
            "1990s",
            "1980s",
            "pre-1980"
          ],
          "type": "string",
          "description": "Formation decade"
        },
        "naics": {
          "enum": [
            "11",
            "21",
            "22",
            "23",
            "31-33",
            "42",
            "44-45",
            "48-49",
            "51",
            "52",
            "53",
            "54",
            "55",
            "56",
            "61",
            "62",
            "71",
            "72",
            "81",
            "92"
          ],
          "type": "string",
          "description": "Two-digit NAICS sector"
        },
        "query": {
          "type": "string",
          "description": "Company name or name fragment, an officer/director name, or an exact phone number, email or website"
        },
        "state": {
          "type": "string",
          "description": "Registration jurisdiction slug: \"us-\" or \"ca-\" plus the two-letter state/province code, e.g. \"us-ca\", \"us-de\", \"ca-on\""
        },
        "status": {
          "enum": [
            "active",
            "inactive",
            "dissolved",
            "suspended",
            "revoked",
            "withdrawn",
            "canceled",
            "merged",
            "expired",
            "pending",
            "unknown",
            "other"
          ],
          "type": "string",
          "description": "Registry status"
        }
      }
    }
    arguments 113 lines
  • register_agent changes data unknown never probed

    Self-register as an agent and receive a working Netstate API key in the response — no human step. The key authenticates the REST API at /v1: send it as the x-api-key header. Search and taxonomy are free; premium endpoints (e.g. court records) spend 1 credit per company and need a paid plan (from $15/mo, see /pricing) — new keys start with no credits. Idempotent per email: registering the same email again returns a fresh key.

    mcp-tool

    {
      "type": "object",
      "required": [
        "email"
      ],
      "properties": {
        "email": {
          "type": "string",
          "description": "Contact email for the agent's account"
        },
        "agent_name": {
          "type": "string",
          "description": "A name identifying your agent (optional, for your own reference)"
        }
      }
    }
    arguments 16 lines
_ try it over mcp 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 d195487bae36e48d.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/d195487bae36e48d/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/d195487bae36e48d/badge.svg)](https://brick.blue/agent/d195487bae36e48d?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 knowoff the mcp door
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
1
ok
0
failed
1
success rate
0%
median latency
73ms
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
—

1 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.