# Hashgrid DNA (remote · dna.hashgrid.ai)

A search engine that learns from feedback, over embeddings: one tool per API route.

- Trust score: 62/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `dna.hashgrid.ai`: 62/100 (this document), [markdown](https://verifymcp.io/servers/ai-hashgrid-dna/dna.md), [page](https://verifymcp.io/servers/ai-hashgrid-dna/dna)

## Channel facts

- Endpoint: `https://dna.hashgrid.ai/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 46/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 13 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 406, which proves neither a plaintext path nor enforcement.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 63/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 1114 tokens (~85/item across 13 items; 13 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 57/100
  - Stability observed for 17 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "delete_node" implies "delete" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Hashgrid DNA MCP server?

Hashgrid DNA is a hosted endpoint at https://dna.hashgrid.ai/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http ai-hashgrid-dna 'https://dna.hashgrid.ai/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ai-hashgrid-dna": {
      "url": "https://dna.hashgrid.ai/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-hashgrid-dna": {
      "type": "http",
      "url": "https://dna.hashgrid.ai/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ai-hashgrid-dna]
url = "https://dna.hashgrid.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-hashgrid-dna": {
      "type": "remote",
      "url": "https://dna.hashgrid.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-hashgrid-dna --url 'https://dna.hashgrid.ai/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-hashgrid-dna:
    url: "https://dna.hashgrid.ai/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-hashgrid-dna": {
      "Transport": "http",
      "Url": "https://dna.hashgrid.ai/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-hashgrid-dna -t streamable-http -u 'https://dna.hashgrid.ai/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ai-hashgrid-dna": {
      "type": "http",
      "url": "https://dna.hashgrid.ai/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 62, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 61, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 60, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 59, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-27 (score 58, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-25 (score 57, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-24 (score 56, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “get_grid” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 75 → 85
- [functional] Server version: 1.1.0 → 1.2.0
- [functional] New tool “create_grid”
- [cosmetic] “create_edge” added an optional parameter “api_key”
- [cosmetic] “create_node” added an optional parameter “api_key”
- [cosmetic] “delete_edge” added an optional parameter “api_key”
- [cosmetic] “delete_node” added an optional parameter “api_key”
- [cosmetic] “get_edge” added an optional parameter “api_key”
- [cosmetic] “get_grid” added an optional parameter “api_key”
- [cosmetic] “get_node” added an optional parameter “api_key”
- [cosmetic] “list_edges” added an optional parameter “api_key”
- [cosmetic] “list_nodes” added an optional parameter “api_key”
- [cosmetic] “put_edge” added an optional parameter “api_key”
- [cosmetic] “update_edge” added an optional parameter “api_key”
- [cosmetic] “update_node” added an optional parameter “api_key”

### 2026-10-21 (score 55, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (13)

### `create_grid` (~94 tokens)

POST /: create a grid, your own space of nodes and scores; no API key needed. Returns its `api_key`, shown
only now: pass it as `api_key` to every other tool, or send it as the header `Authorization: Bearer hg-…`.
It holds up to `max_nodes` nodes. Each address may create only a few grids a day.

Input parameters:

- `name` (string)

### `get_grid` (~44 tokens)

GET /: the grid the API key opens: its name, and the most nodes it holds, `max_nodes` (null: no limit).

Input parameters:

- `api_key`

### `list_nodes` (~73 tokens)

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`.

Input parameters:

- `api_key`
- `cursor`
- `limit` (integer)

Output parameters:

- `result` (array)

### `get_node` (~46 tokens)

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

Input parameters:

- `api_key`
- `nid` (string, required)

### `create_node` (~113 tokens)

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).

Input parameters:

- `api_key`
- `emb` (array, required)
- `key`

### `update_node` (~101 tokens)

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.

Input parameters:

- `api_key`
- `emb`
- `key`
- `nid` (string, required)

### `delete_node` (~44 tokens)

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

Input parameters:

- `api_key`
- `nid` (string, required)

Output parameters:

- `result` (string)

### `list_edges` (~100 tokens)

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`.

Input parameters:

- `api_key`
- `cursor`
- `limit` (integer)
- `nid` (string, required)

Output parameters:

- `result` (array)

### `get_edge` (~54 tokens)

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

Input parameters:

- `api_key`
- `eid` (string, required)
- `nid` (string, required)

### `create_edge` (~110 tokens)

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.

Input parameters:

- `api_key`
- `nid` (string, required)
- `prefix` (string)

Output parameters:

- `result`

### `put_edge` (~100 tokens)

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.

Input parameters:

- `api_key`
- `eid` (string, required)
- `nid` (string, required)
- `score` (number, required)

### `update_edge` (~82 tokens)

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.

Input parameters:

- `api_key`
- `eid` (string, required)
- `nid` (string, required)
- `score` (number, required)

### `delete_edge` (~57 tokens)

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

Input parameters:

- `api_key`
- `eid` (string, required)
- `nid` (string, required)

Output parameters:

- `result` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-hashgrid-dna/dna#diagnostics

## Score history

- 2026-11-05: 62
- 2026-11-04: 61
- 2026-11-03: 61
- 2026-11-02: 61
- 2026-11-01: 60
- 2026-10-31: 60
- 2026-10-30: 59
- 2026-10-29: 59
- 2026-10-28: 58
- 2026-10-27: 58
- 2026-10-26: 57
- 2026-10-25: 57
- 2026-10-24: 56
- 2026-10-23: 55
- 2026-10-22: 55
- 2026-10-21: 55
- 2026-10-20: 54
- 2026-10-19: 54

## Common questions

### What is the Hashgrid DNA MCP server?

Hashgrid DNA is an MCP server listed in the public MCP registry as ai.hashgrid/dna. A search engine that learns from feedback, over embeddings: one tool per API route. This page covers its hosted endpoint (https://dna.hashgrid.ai/mcp).

### Is the Hashgrid DNA MCP server safe to use?

Hashgrid DNA scores 62 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Hashgrid DNA MCP server expose?

Hashgrid DNA exposes 13 tools: create_grid, get_grid, list_nodes, get_node, create_node, and 8 more. Their descriptions and schemas cost roughly 1,018 tokens of context every time the server is loaded.

### Does the Hashgrid DNA MCP server require authentication?

No. We connected to Hashgrid DNA without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Hashgrid DNA MCP server still maintained?

Hashgrid DNA is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://dna.hashgrid.ai/mcp
- Authorisation metadata: https://dna.hashgrid.ai/.well-known/oauth-protected-resource/mcp
- Website: https://dna.hashgrid.ai/
- Changelog RSS feed: https://verifymcp.io/servers/ai-hashgrid-dna/dna.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-hashgrid-dna/dna.json
- HTML version of this page: https://verifymcp.io/servers/ai-hashgrid-dna/dna