_ registry / mcp http-sse · checked 7h ago

ipvolt-proxy-toolkit

https://mcp.ipvolt.com

Registry code: f4267438bd31cef5

api record

Proxy guides, tested configurations and error diagnostics, with an optional local route check.

from a public catalogue that lists it, not from the operator

endpoint
https://mcp.ipvolt.com/mcp
protocol
http-sse ·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 ipvolt-proxy-toolkit live?
Yes — it answered the hub's last check (checked 7h ago). It answered 94% of checks over the last 30 days.
Is ipvolt-proxy-toolkit free to use?
Yes — the hub reached it with no key and no payment.
What tools does ipvolt-proxy-toolkit have?
4 tools: search_proxy_docs, generate_proxy_config, get_proxy_doc, diagnose_proxy_error.
Is ipvolt-proxy-toolkit 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
93.8%

90 days 96.1%· all time 96.1%

latency
157ms

last good check

priced tools
0

of 4 tools

_ answered our checks, 90 days 336 checks · signed record
  • down → live
  • degraded → down· timeout after 20000ms
  • live → degraded· timeout after 20000ms
  • degraded → live
  • degraded → live
_ what it is for
used for
  • diagnose a proxy error
  • generate a proxy client config
  • search proxy guides
takes → gives
text, data → text, code
tools
4 reads
_ 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

inferred, not observed

Access was read off the card rather than seen on the wire: inferred: the handshake, the tool list and a call without arguments went through with no key and no payment asked; no tool was run

_ what it can do 4 tools
4 never probed 0 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.

  • search_proxy_docs reads unknown 7h ago

    Find reviewed ipvolt public guides and articles. Returns canonical document IDs, excerpts and content revision. Submit a short topic query, never credentials or logs.

    mcp-tool

    {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "required": [
        "query"
      ],
      "properties": {
        "limit": {
          "type": "integer",
          "default": 5,
          "maximum": 5,
          "minimum": 1
        },
        "query": {
          "type": "string",
          "maxLength": 200,
          "minLength": 2
        },
        "topic": {
          "enum": [
            "setup",
            "troubleshooting",
            "concepts",
            "countries",
            "analysis"
          ],
          "type": "string"
        }
      },
      "additionalProperties": false
    }
    arguments 31 lines
  • generate_proxy_config reads unknown 16h ago

    Generate an HTTPS GET example for an exact tested curl, Requests, HTTPX or Playwright APIRequestContext version. Credentials and target are local environment placeholders. It does not execute the example or configure other agent tools.

    mcp-tool

    {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "required": [
        "client",
        "version"
      ],
      "properties": {
        "client": {
          "enum": [
            "curl",
            "requests",
            "httpx",
            "playwright"
          ],
          "type": "string",
          "description": "Client whose exact tested configuration to generate."
        },
        "version": {
          "enum": [
            "8.22.0",
            "2.34.2",
            "0.28.1",
            "1.63.0"
          ],
          "type": "string",
          "description": "Exact tested version matching the client. Other versions are unsupported."
        },
        "protocol": {
          "type": "string",
          "const": "http",
          "default": "http",
          "description": "HTTP proxy with HTTPS CONNECT. Other proxy protocols are not tested."
        },
        "timeoutSeconds": {
          "type": "integer",
          "default": 15,
          "maximum": 60,
          "minimum": 1
        }
      },
      "additionalProperties": false
    }
    arguments 43 lines
  • get_proxy_doc reads unknown 16h ago

    Read a bounded chunk or named section using a document ID returned by search_proxy_docs. Follow nextCursor to continue; cursors are bound to the content revision.

    mcp-tool

    {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "required": [
        "documentId"
      ],
      "properties": {
        "cursor": {
          "type": "string",
          "pattern": "^[a-f0-9]{16}:\\d{1,5}$"
        },
        "section": {
          "type": "string",
          "maxLength": 160,
          "minLength": 1
        },
        "documentId": {
          "type": "string",
          "pattern": "^\\/(guides|blog)\\/[a-z0-9]+(?:-[a-z0-9]+)*$",
          "maxLength": 160
        }
      },
      "additionalProperties": false
    }
    arguments 24 lines
  • diagnose_proxy_error reads unknown 16h ago

    Use structured client/version, phase, status or exception observations to identify possible causes and the next check. Returns uncertainty and retry boundaries. Do not send raw logs, URLs or credentials.

    mcp-tool

    {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "required": [
        "client",
        "version",
        "phase"
      ],
      "properties": {
        "phase": {
          "enum": [
            "configuration",
            "pool",
            "proxy_connect",
            "connect_tunnel",
            "target_tls",
            "request_send",
            "response_headers",
            "response_body",
            "unknown"
          ],
          "type": "string"
        },
        "client": {
          "enum": [
            "curl",
            "requests",
            "httpx",
            "playwright"
          ],
          "type": "string"
        },
        "method": {
          "enum": [
            "GET",
            "HEAD",
            "OPTIONS",
            "PUT",
            "DELETE",
            "POST",
            "PATCH",
            "unknown"
          ],
          "type": "string",
          "default": "unknown"
        },
        "status": {
          "type": "integer",
          "maximum": 599,
          "minimum": 100,
          "description": "Observed HTTP status; identify its responding layer separately."
        },
        "version": {
          "enum": [
            "8.22.0",
            "2.34.2",
            "0.28.1",
            "1.63.0"
          ],
          "type": "string"
        },
        "exception": {
          "enum": [
            "proxy_error",
            "tls_error",
            "connect_timeout",
            "read_timeout",
            "write_timeout",
            "pool_timeout",
            "connection_refused",
            "dns_error",
            "connection_reset",
            "protocol_error",
            "timeout",
            "invalid_configuration",
            "unknown"
          ],
          "type": "string",
          "description": "Normalized category, not raw exception text. HTTPX ConnectError alone does not establish a TLS error."
        },
        "responseSource": {
          "enum": [
            "proxy",
            "target",
            "unknown"
          ],
          "type": "string",
          "default": "unknown",
          "description": "Use target/proxy only when established by response provenance, not merely the status code."
        },
        "retryAfterSeconds": {
          "type": "integer",
          "maximum": 86400,
          "minimum": 0,
          "description": "Parsed bounded Retry-After delay, if actually observed. Never submit the raw header."
        },
        "requestMayHaveBeenSent": {
          "type": "boolean",
          "description": "Whether this target request may already have reached the application. Omit when unknown."
        }
      },
      "additionalProperties": false
    }
    arguments 103 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 f4267438bd31cef5.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/f4267438bd31cef5/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/f4267438bd31cef5/badge.svg)](https://brick.blue/agent/f4267438bd31cef5?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.