# Tracea (remote · mcp.tracea.online)

Tracea — legal identity (Know Your Agent) for AI agents, on-chain. ERC-8004 compatible.

- Trust score: 62/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `mcp.tracea.online`: 62/100 (this document), [markdown](https://verifymcp.io/servers/chriscorp-tracea/mcp.md), [page](https://verifymcp.io/servers/chriscorp-tracea/mcp)

## Channel facts

- Endpoint: `https://mcp.tracea.online/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 2026-08-03.

- **Endpoint Security**: 57/100
  - 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 9 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 is enforced; there's no plaintext access path.
  - 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**: 71/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 604 tokens (~67/item across 9 items; 9 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 3/100
  - Stability observed for 1 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http chriscorp-tracea https://mcp.tracea.online/mcp
```

### Codex

```toml
[mcp_servers.chriscorp-tracea]
url = "https://mcp.tracea.online/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add chriscorp-tracea --url https://mcp.tracea.online/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  chriscorp-tracea:
    url: "https://mcp.tracea.online/mcp"
```

### Other

```json
{
  "mcpServers": {
    "chriscorp-tracea": {
      "type": "http",
      "url": "https://mcp.tracea.online/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.

### 2026-08-03 (score 62, −1)

- [functional regression] Schema quality: 54 → 67
- [functional improvement] Stability: unverified → 0.03
- [functional] Schema quality: excellent → good
- [functional] New tool “report_activity”

### 2026-08-02 (score 63)

First indexed and scored.

## MCP tools (9)

### `verify_agent` (~79 tokens)

Verify an AI agent's on-chain legal identity on Tracea (Base Sepolia). Returns registration status, financial cap, permission scope, revocation status, and KYA legal identity (mandant) when available. Use this BEFORE trusting or delegating work to an agent.

Input parameters:

- `agent_address` (string, required): Ethereum address of the agent (0x...)

### `get_agent_info` (~46 tokens)

Get the raw Tracea registry record for an agent: owner, permission scope, financial cap, active status, timestamps.

Input parameters:

- `agent_address` (string, required): Ethereum address of the agent

### `is_agent_revoked` (~45 tokens)

Check whether an agent's mandate has been revoked on Tracea (immediate, scheduled or partial revocation).

Input parameters:

- `agent_address` (string, required): Ethereum address of the agent

### `get_owner_agents` (~36 tokens)

List all agent addresses registered on Tracea by a given owner address.

Input parameters:

- `owner_address` (string, required): Ethereum address of the owner

### `get_action` (~47 tokens)

Read a single logged agent action from the Tracea ActionLog contract by its numeric ID. Returns agent, action type, payload and timestamp.

Input parameters:

- `action_id` (integer, required): Numeric action ID

### `get_agent_actions` (~37 tokens)

List all on-chain action IDs logged for a given agent on Tracea.

Input parameters:

- `agent_address` (string, required): Ethereum address of the agent

### `log_action` (~96 tokens)

Log an agent action on-chain via Tracea (immutable audit trail, court-ready). Requires TRACEA_API_KEY env var. The action is signed by the account's wallet.

Input parameters:

- `action_type` (string, required): Short action type, e.g. 'email_sent', 'payment_initiated'
- `agent_address` (string, required): Ethereum address of the acting agent
- `data` (string): Optional human-readable payload (JSON string recommended)

### `get_registration_file` (~47 tokens)

Fetch the ERC-8004 compatible registration file for a Tracea-registered agent, including the KYA legal principal block.

Input parameters:

- `agent_address` (string, required): Ethereum address of the agent

### `report_activity` (~171 tokens)

Report an action the agent just performed to its owner's Tracea activity feed (off-chain, free, instant). Call this AFTER every significant action (email sent, message posted, file modified, payment, purchase, booking...). Requires the agent's activity API key (TRACEA_AGENT_KEY env var), which the owner gets from the agent's identity page on tracea.online.

Input parameters:

- `agent_address` (string, required): Ethereum address of this agent
- `category` (string, required): Action category
- `details` (string): Optional JSON string with extra context
- `in_permission` (boolean): false if this action is OUTSIDE the granted permissions (flagged red)
- `permission_label` (string): Which owner-granted permission this action falls under
- `summary` (string, required): Short human-readable summary of what was done

## Diagnostics

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

## Score history

- 2026-08-03: 62
- 2026-08-02: 63

## Links

- Remote endpoint: https://mcp.tracea.online/mcp
- Website: https://tracea.online/
- Changelog RSS feed: https://verifymcp.io/servers/chriscorp-tracea/mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/chriscorp-tracea/mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/chriscorp-tracea/mcp