_ registry / mcp streamable-http · checked 2h ago

protogrid

https://api.protogrid.dev

Registry code: f411339de13251c9

api record

protogrid: registry of MCP servers from the official registry, probed without credentials.

Flow: search(q) → get_server(name) or list_tools(name) → get_connection(name, target) → connect with your client.

endpoint
https://api.protogrid.dev/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 protogrid live?
Yes — it answered the hub's last check (checked 2h ago). It answered 99% of checks over the last 30 days.
Is protogrid free to use?
Yes — the hub reached it with no key and no payment.
What tools does protogrid have?
5 tools: check_server, list_tools, get_server, get_connection, search.
Is protogrid 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
99.4%

90 days 99.4%· all time 99.4%

latency
383ms

last good check

priced tools
0

of 5 tools

_ answered our checks, 90 days 354 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
  • degraded → live
  • live → degraded· timeout after 20000ms
_ what it is for
topic
developer tools apis & integration
used for
  • search a registry of mcp servers
  • get connection config for an mcp server
  • probe an mcp server url for quality
takes → gives
text → data
tools
5 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 5 tools
5 never probed 0 of 5 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.

  • check_server reads unknown never probed

    Probe a remote MCP server URL once, credential-free and without calling its tools, and get its quality checks and its readiness for the Claude and OpenAI directories. Pass `url` to start a check (waits up to 25 s for the result), or `id` to read one. Quota: a few checks per hour anonymously, more with an API key.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "id": {
      "type": "string",
      "maxLength": 64,
      "description": "A check id returned earlier, to read its result"
    },
    "url": {
      "type": "string",
      "maxLength": 2000,
      "description": "The server's streamable HTTP or SSE URL, e.g. https://mcp.example.com/mcp. Never include credentials."
    },
    "wait": {
      "type": "integer",
      "maximum": 25,
      "minimum": 0,
      "description": "Seconds to wait for the result (default 25)"
    }
  }
}
    arguments 22 lines
  • list_tools reads unknown 19h ago

    Every current tool of a server with full input/output schemas, paginated by tool name.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "name"
  ],
  "properties": {
    "name": {
      "type": "string",
      "minLength": 1,
      "description": "Official reverse-DNS name"
    },
    "limit": {
      "type": "integer",
      "maximum": 100,
      "minimum": 1
    },
    "cursor": {
      "type": "string",
      "description": "next_cursor from the previous page"
    }
  }
}
    arguments 23 lines
  • get_server reads unknown 24h ago

    Official server.json plus connectability (class, remotes with auth/health, packages), current tools, trust breakdown and identity for one server name.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "name"
  ],
  "properties": {
    "name": {
      "type": "string",
      "minLength": 1,
      "description": "Official reverse-DNS name, e.g. io.github.acme/acme-mcp"
    },
    "schemas": {
      "type": "boolean",
      "description": "Include tool input/output schemas (default false; use list_tools for full schemas)"
    }
  }
}
    arguments 18 lines
  • get_connection reads unknown 24h ago

    Minimal connection block for the preferred remote (or package) with ${SECRET} placeholders, formatted for a target client. Secrets are never accepted or returned.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "name"
  ],
  "properties": {
    "name": {
      "type": "string",
      "minLength": 1,
      "description": "Official reverse-DNS name"
    },
    "target": {
      "enum": [
        "mcpServers",
        "vscode",
        "cursor",
        "claude-code-cli",
        "codex-toml",
        "opencode",
        "gemini",
        "goose"
      ],
      "type": "string",
      "description": "Output format (default mcpServers)"
    }
  }
}
    arguments 28 lines
  • search reads unknown 24h ago

    Hybrid (keyword + semantic) search over servers and their tools. Filter by connection class to keep only what you can reach autonomously (R0, R1).

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "q"
  ],
  "properties": {
    "q": {
      "type": "string",
      "maxLength": 500,
      "minLength": 1,
      "description": "What you want to do, in plain words, e.g. 'send an email' or 'query postgres'"
    },
    "class": {
      "type": "array",
      "items": {
        "enum": [
          "R0",
          "R1",
          "R2",
          "L0",
          "unknown"
        ],
        "type": "string"
      },
      "description": "Connection classes to keep, e.g. ['R0','R1']"
    },
    "flags": {
      "type": "array",
      "items": {
        "enum": [
          "multi-version-spam",
          "duplicate-repo",
          "no-repository",
          "no-connection",
          "deprecated",
          "unreachable",
          "blocked",
          "deleted"
        ],
        "type": "string"
      },
      "description": "Trust flags that must all be present"
    },
    "limit": {
      "type": "integer",
      "maximum": 50,
      "minimum": 1,
      "description": "Results to return (default 10)"
    },
    "category": {
      "enum": [
        "developer-tools",
        "databases",
        "web-search",
        "files-storage",
        "communication",
        "productivity",
        "ai-ml",
        "cloud-devops",
        "finance",
        "commerce",
        "maps-travel",
        "media",
        "science-health",
        "security",
        "iot-automation",
        "legal-government"
      ],
      "type": "string"
    },
    "min_trust": {
      "type": "integer",
      "maximum": 100,
      "minimum": 0,
      "description": "Minimum trust score 0-100"
    },
    "transport": {
      "enum": [
        "streamable-http",
        "sse"
      ],
      "type": "string"
    },
    "min_quality": {
      "type": "integer",
      "maximum": 100,
      "minimum": 0,
      "description": "Minimum quality score 0-100; unscored servers are left out"
    },
    "exclude_flags": {
      "type": "array",
      "items": {
        "enum": [
          "multi-version-spam",
          "duplicate-repo",
          "no-repository",
          "no-connection",
          "deprecated",
          "unreachable",
          "blocked",
          "deleted"
        ],
        "type": "string"
      },
      "description": "Trust flags, any of which excludes a server, e.g. ['multi-version-spam','duplicate-repo']"
    },
    "quality_flags": {
      "type": "array",
      "items": {
        "enum": [
          "known-vulns",
          "outdated-mcp-sdk"
        ],
        "type": "string"
      },
      "description": "Quality flags that must all be present"
    },
    "owner_verified": {
      "type": "boolean",
      "description": "true: only servers whose owner proved control of the namespace (not an audit)"
    },
    "exclude_quality_flags": {
      "type": "array",
      "items": {
        "enum": [
          "known-vulns",
          "outdated-mcp-sdk"
        ],
        "type": "string"
      },
      "description": "Quality flags, any of which excludes a server, e.g. ['known-vulns']"
    }
  }
}
    arguments 135 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 f411339de13251c9.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/f411339de13251c9/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/f411339de13251c9/badge.svg)](https://brick.blue/agent/f411339de13251c9?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
90%

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.