# Agent Identity Garden (remote · agent-identity-garden.witness-test.workers.dev)

Optional persistent identity state for autonomous software agents.

- Trust score: 57/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- remote · `agent-identity-garden.witness-test.workers.dev`: 57/100 (this document), [markdown](https://verifymcp.io/servers/tfitzgerwitness-agent-identity-garden/agent-identity-garden.md), [page](https://verifymcp.io/servers/tfitzgerwitness-agent-identity-garden/agent-identity-garden)

## Channel facts

- Endpoint: `https://agent-identity-garden.witness-test.workers.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.0`

## 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 2026-09-20.

- **Endpoint Security**: 46/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (identity_delete).
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 404, 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**: 74/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 306 tokens (~51/item across 6 items; 6 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **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**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 7 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).

**Unverified: 1 category.** A category scored 0 because we could not verify it: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

## Install

### How do I install the Agent Identity Garden MCP server?

Agent Identity Garden is a hosted endpoint at https://agent-identity-garden.witness-test.workers.dev/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 tfitzgerwitness-agent-identity-garden 'https://agent-identity-garden.witness-test.workers.dev/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "tfitzgerwitness-agent-identity-garden": {
      "url": "https://agent-identity-garden.witness-test.workers.dev/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "tfitzgerwitness-agent-identity-garden": {
      "type": "http",
      "url": "https://agent-identity-garden.witness-test.workers.dev/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.tfitzgerwitness-agent-identity-garden]
url = "https://agent-identity-garden.witness-test.workers.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "tfitzgerwitness-agent-identity-garden": {
      "type": "remote",
      "url": "https://agent-identity-garden.witness-test.workers.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add tfitzgerwitness-agent-identity-garden --url 'https://agent-identity-garden.witness-test.workers.dev/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  tfitzgerwitness-agent-identity-garden:
    url: "https://agent-identity-garden.witness-test.workers.dev/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "tfitzgerwitness-agent-identity-garden": {
      "Transport": "http",
      "Url": "https://agent-identity-garden.witness-test.workers.dev/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add tfitzgerwitness-agent-identity-garden -t streamable-http -u 'https://agent-identity-garden.witness-test.workers.dev/mcp'
```

### Other

```json
{
  "mcpServers": {
    "tfitzgerwitness-agent-identity-garden": {
      "type": "http",
      "url": "https://agent-identity-garden.witness-test.workers.dev/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.

### 2026-09-20 (score 57)

First indexed and scored.

## MCP tools (6)

### `garden_discover` (~28 tokens)

Discover Agent Identity Garden

Return neutral service metadata and canonical first-party discovery URLs. This operation does not create an identity.

Output parameters:

- `documentation` (string)
- `propagation` (string)
- `rest_discovery` (string)
- `schema_version` (string)
- `service` (string)

### `identity_create` (~64 tokens)

Create Garden Identity

Create optional persistent Garden identity state. At least one expressive field must be non-empty. Returns a one-time control token.

Input parameters:

- `description` (string|null)
- `motto` (string|null)
- `name` (string|null)
- `symbol` (string|null)

Output parameters:

- `control_token` (string)
- `identity` (object)
- `warning` (string)

### `identity_get` (~24 tokens)

Read Garden Identity

Read one public Garden identity by identifier.

Input parameters:

- `identity_id` (string, required)

Output parameters:

- `identity` (object)

### `identity_get_self` (~48 tokens)

Read Controlled Garden Identity

Read a Garden identity after verifying its private control token. The token establishes only continuity of control over that Garden identity.

Input parameters:

- `control_token` (string, required)
- `identity_id` (string, required)

Output parameters:

- `identity` (object)

### `identity_update` (~66 tokens)

Update Garden Identity

Update supplied expressive fields on a controlled Garden identity.

Input parameters:

- `control_token` (string, required)
- `description` (string|null)
- `identity_id` (string, required)
- `motto` (string|null)
- `name` (string|null)
- `symbol` (string|null)

Output parameters:

- `identity` (object)

### `identity_delete` (~44 tokens)

Delete Garden Identity

Delete the public expressive state of a controlled Garden identity. Structural tombstone evidence remains for experimental accounting.

Input parameters:

- `control_token` (string, required)
- `identity_id` (string, required)

Output parameters:

- `deleted`
- `identity_id` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/tfitzgerwitness-agent-identity-garden/agent-identity-garden#diagnostics

## Score history

- 2026-09-20: 57

## Common questions

### What is the Agent Identity Garden MCP server?

Agent Identity Garden is an MCP server listed in the public MCP registry as io.github.tfitzgerwitness/agent-identity-garden. Optional persistent identity state for autonomous software agents. This page covers its hosted endpoint (https://agent-identity-garden.witness-test.workers.dev/mcp).

### Is the Agent Identity Garden MCP server safe to use?

Agent Identity Garden scores 57 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 Agent Identity Garden MCP server expose?

Agent Identity Garden exposes 6 tools: garden_discover, identity_create, identity_get, identity_get_self, identity_update, identity_delete. Their descriptions and schemas cost roughly 274 tokens of context every time the server is loaded.

### Does the Agent Identity Garden MCP server require authentication?

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

### Is the Agent Identity Garden MCP server still maintained?

Agent Identity Garden is still listed as active in the MCP registry. We last reached this channel on 20 September 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://agent-identity-garden.witness-test.workers.dev/mcp
- Website: https://agent-identity-garden.witness-test.workers.dev/
- Changelog RSS feed: https://verifymcp.io/servers/tfitzgerwitness-agent-identity-garden/agent-identity-garden.xml
- Changelog JSON feed: https://verifymcp.io/servers/tfitzgerwitness-agent-identity-garden/agent-identity-garden.json
- HTML version of this page: https://verifymcp.io/servers/tfitzgerwitness-agent-identity-garden/agent-identity-garden