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

dna

https://dna.hashgrid.ai

Registry code: 971a0c14939446fe

api record

DNA is a search engine that learns from feedback, over embeddings. These tools map 1:1 to

its HTTP API. Send your API key as the header `Authorization: Bearer hg-…`. No key yet? Write to [email protected] for one; each key opens one grid.

endpoint
https://dna.hashgrid.ai/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 dna live?
Yes — it answered the hub's last check (checked 2h ago). It answered 100% of checks over the last 30 days.
Is dna free to use?
Not anonymously — it asks for a key or a login before it will serve. Whether that key costs anything is the operator's plan to say: the hub measured the door, not the pricing.
What tools does dna have?
13 tools: get_edge, get_grid, delete_edge, list_nodes, get_node, create_node, update_node, delete_node, ….
Is dna 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
133ms

last good check

priced tools
0

of 13 tools

_ answered our checks, 90 days 1 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 13 tools
12 auth-required 1 never probed 12 of 13 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.

  • get_grid auth-required 2h ago

    GET /: the grid the API key opens, by name.

    mcp-tool

    {
  "type": "object",
  "title": "get_gridArguments",
  "properties": {}
}
    arguments 5 lines
  • delete_edge auth-required never probed

    DELETE /nodes/{nid}/edges/{eid}: forget a result, so it can be suggested again; its score no longer trains.

    mcp-tool

    {
  "type": "object",
  "title": "delete_edgeArguments",
  "required": [
    "nid",
    "eid"
  ],
  "properties": {
    "eid": {
      "type": "string",
      "title": "Eid"
    },
    "nid": {
      "type": "string",
      "title": "Nid"
    }
  }
}
    arguments 18 lines
  • list_nodes auth-required 2h ago

    GET /nodes: the grid's nodes, each with its id, key and emb, in id order. `limit` is 1 to 1024; for the next page, pass the last id as `cursor`.

    mcp-tool

    {
  "type": "object",
  "title": "list_nodesArguments",
  "properties": {
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 32
    },
    "cursor": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Cursor",
      "default": null
    }
  }
}
    arguments 23 lines
  • get_node auth-required never probed

    GET /nodes/{nid}: a node, with its key (null if it has none) and its embedding `emb`.

    mcp-tool

    {
  "type": "object",
  "title": "get_nodeArguments",
  "required": [
    "nid"
  ],
  "properties": {
    "nid": {
      "type": "string",
      "title": "Nid"
    }
  }
}
    arguments 13 lines
  • create_node auth-required never probed

    POST /nodes: add a node. An item gets a `key`, a path unique in the grid (e.g. "/items/42"), so searches can find it; a query gets none. `emb` is its embedding, 1 to 2048 floats from any model; use one model per grid. Returns its id and key (not its emb, to keep replies short; get_node has it).

    mcp-tool

    {
  "type": "object",
  "title": "create_nodeArguments",
  "required": [
    "emb"
  ],
  "properties": {
    "emb": {
      "type": "array",
      "items": {
        "type": "number"
      },
      "title": "Emb"
    },
    "key": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Key",
      "default": null
    }
  }
}
    arguments 28 lines
  • update_node auth-required never probed

    PATCH /nodes/{nid}: change a node. `key`: a new path, or null to remove it, so the node can no longer be found; leave it out to keep it. `emb`: a new embedding; leave it out to keep it. Its scores keep training, on the new embedding. Returns its id and key.

    mcp-tool

    {
  "type": "object",
  "title": "update_nodeArguments",
  "required": [
    "nid"
  ],
  "properties": {
    "emb": {
      "anyOf": [
        {
          "type": "array",
          "items": {
            "type": "number"
          }
        },
        {
          "type": "null"
        }
      ],
      "title": "Emb",
      "default": null
    },
    "key": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Key",
      "default": ""
    },
    "nid": {
      "type": "string",
      "title": "Nid"
    }
  }
}
    arguments 40 lines
  • delete_node auth-required never probed

    DELETE /nodes/{nid}: delete a node and every edge from or to it; its scores no longer train.

    mcp-tool

    {
  "type": "object",
  "title": "delete_nodeArguments",
  "required": [
    "nid"
  ],
  "properties": {
    "nid": {
      "type": "string",
      "title": "Nid"
    }
  }
}
    arguments 13 lines
  • delete_nodes auth-required never probed

    DELETE /nodes: delete up to 1024 nodes at once, and every edge from or to them, as delete_node does each; ids of no node are skipped.

    mcp-tool

    {
  "type": "object",
  "title": "delete_nodesArguments",
  "required": [
    "nids"
  ],
  "properties": {
    "nids": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "title": "Nids"
    }
  }
}
    arguments 16 lines
  • list_edges auth-required never probed

    GET /nodes/{nid}/edges: a query's results so far, each an edge with the found node's `id` and its `score` (null if not scored), in id order. `limit` is 1 to 1024; for the next page, pass the last id as `cursor`.

    mcp-tool

    {
  "type": "object",
  "title": "list_edgesArguments",
  "required": [
    "nid"
  ],
  "properties": {
    "nid": {
      "type": "string",
      "title": "Nid"
    },
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 32
    },
    "cursor": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Cursor",
      "default": null
    }
  }
}
    arguments 30 lines
  • create_edge auth-required never probed

    POST /nodes/{nid}/edges, the search: from query node `nid`, the best node it has not been shown yet, among those whose key starts with `prefix` ("" for any), stored as a new edge: `id` is the found node's id, `score` is null until you score it (update_edge). Null when nothing is left. Call again for the next.

    mcp-tool

    {
  "type": "object",
  "title": "create_edgeArguments",
  "required": [
    "nid"
  ],
  "properties": {
    "nid": {
      "type": "string",
      "title": "Nid"
    },
    "prefix": {
      "type": "string",
      "title": "Prefix",
      "default": ""
    }
  }
}
    arguments 18 lines
  • put_edge auth-required never probed

    PUT /nodes/{nid}/edges/{eid}: score how well node `eid` fits query `nid`, from -1 (wrong) to 1 (perfect), creating the edge if DNA never suggested it, e.g. scores you already have. Only scores train DNA; a new score replaces the last.

    mcp-tool

    {
  "type": "object",
  "title": "put_edgeArguments",
  "required": [
    "nid",
    "eid",
    "score"
  ],
  "properties": {
    "eid": {
      "type": "string",
      "title": "Eid"
    },
    "nid": {
      "type": "string",
      "title": "Nid"
    },
    "score": {
      "type": "number",
      "title": "Score"
    }
  }
}
    arguments 23 lines
  • update_edge auth-required never probed

    PATCH /nodes/{nid}/edges/{eid}: score a result of query `nid` that create_edge returned, from -1 (wrong) to 1 (perfect). Only scores train DNA; a new score replaces the last.

    mcp-tool

    {
  "type": "object",
  "title": "update_edgeArguments",
  "required": [
    "nid",
    "eid",
    "score"
  ],
  "properties": {
    "eid": {
      "type": "string",
      "title": "Eid"
    },
    "nid": {
      "type": "string",
      "title": "Nid"
    },
    "score": {
      "type": "number",
      "title": "Score"
    }
  }
}
    arguments 23 lines
  • get_edge unknown 2h ago

    GET /nodes/{nid}/edges/{eid}: one result of query `nid`, and its score (null if not scored).

    mcp-tool

    {
  "type": "object",
  "title": "get_edgeArguments",
  "required": [
    "nid",
    "eid"
  ],
  "properties": {
    "eid": {
      "type": "string",
      "title": "Eid"
    },
    "nid": {
      "type": "string",
      "title": "Nid"
    }
  }
}
    arguments 18 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 971a0c14939446fe.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/971a0c14939446fe/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/971a0c14939446fe/badge.svg)](https://brick.blue/agent/971a0c14939446fe?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
100%

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.