# Forge AI Accountability (remote · demo.forgeorbital.com)

Demo of Forge decision accountability on fictional Acme Mutual: signed, replayable records.

- Trust score: 66/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `demo.forgeorbital.com`: 66/100 (this document), [markdown](https://verifymcp.io/servers/forgeorbital-forge-ai-accountability/demo.md), [page](https://verifymcp.io/servers/forgeorbital-forge-ai-accountability/demo)

## Channel facts

- Endpoint: `https://demo.forgeorbital.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.30.0`

## 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**: 14/100
  - TLS not yet verified: we couldn't open a connection to check the certificate.
  - Authorisation not yet verified: we couldn't confirm whether this endpoint requires it.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS not yet verified: we couldn't read the response headers to check for it.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 0/100
  - Transport check failed: declared streamable-http, but we couldn't connect to verify it.
- **Schema Quality & AI Usability**: 0/100
  - Schema not yet verified: we couldn't read the endpoint's schema, or could read only part of its tool list.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 0/100
  - Tool coverage not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.
- **Tool Safety**: 0/100
  - Tool safety not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.
- **Capabilities**: 0/100
  - Capabilities not yet verified: we couldn't read the endpoint's capabilities.

**Unverified: 5 categories.** Categories scored 0 because we could not verify them: 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 Forge AI Accountability MCP server?

Forge AI Accountability is a hosted endpoint at https://demo.forgeorbital.com/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 forgeorbital-forge-ai-accountability 'https://demo.forgeorbital.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "forgeorbital-forge-ai-accountability": {
      "url": "https://demo.forgeorbital.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "forgeorbital-forge-ai-accountability": {
      "type": "http",
      "url": "https://demo.forgeorbital.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.forgeorbital-forge-ai-accountability]
url = "https://demo.forgeorbital.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "forgeorbital-forge-ai-accountability": {
      "type": "remote",
      "url": "https://demo.forgeorbital.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add forgeorbital-forge-ai-accountability --url 'https://demo.forgeorbital.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  forgeorbital-forge-ai-accountability:
    url: "https://demo.forgeorbital.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "forgeorbital-forge-ai-accountability": {
      "Transport": "http",
      "Url": "https://demo.forgeorbital.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add forgeorbital-forge-ai-accountability -t streamable-http -u 'https://demo.forgeorbital.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "forgeorbital-forge-ai-accountability": {
      "type": "http",
      "url": "https://demo.forgeorbital.com/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.

### 2026-11-04 (score 66, 0)

- [security regression] Endpoint reachability: reachable → unreachable
- [security regression] Authorization: partial → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] TLS certificate: pass → unverified
- [security regression] Stability: 0.03 → unverified
- [security regression] HSTS header: pass → unverified
- [security regression] Transport: pass → fail
- [functional regression] Capabilities: pass → unverified
- [functional regression] Schema quality: 0 → unverified
- [functional regression] Tool coverage: 100 → unverified

### 2026-11-03 (score 66, +1)

- [security] Tool “review_agent_workflow” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 71 → 90
- [functional improvement] Stability: unverified → 0.03

### 2026-11-02 (score 65)

First indexed and scored.

## MCP tools (7)

### `list_scenarios` (~36 tokens)

List demo scenarios

Lists the five sample scenarios for the fictional Acme Mutual Insurance that run_check accepts, with their evidence ids. Demo data only.

### `run_check` (~95 tokens)

Run a Forge Orbital check on a sample scenario

Computes a Forge Orbital verdict for one of five fictional Acme Mutual Insurance scenarios and returns it with a signed decision record in the response. Read-only: nothing is stored, sent or changed. Optionally withdraw evidence ids to see how the verdict changes. Demo only: sample rules and sample evidence, not connected to the user's systems, policies or live actions.

Input parameters:

- `scenario_id` (string, required)
- `withdraw_evidence`

### `verify_decision_record` (~80 tokens)

Verify a Forge Orbital decision record

Verifies the Ed25519 signature of a Forge Orbital demo decision record against the published demo key id. Pass the full signed record object returned by run_check (this demo keeps nothing, so a record id alone cannot be looked up). Editing any field makes verification fail. Demo records only.

Input parameters:

- `record`
- `record_id`

### `replay_decision_record` (~101 tokens)

Replay a Forge Orbital decision from its inputs

Replays a Forge Orbital demo decision: re-runs the deterministic engine on the same sample scenario (and any withdrawn evidence) and checks that the replay key and the decision match the record. Replayability is the point: the same inputs and engine version give the same decision. Reads nothing about the user. Demo only, fictional sample data.

Input parameters:

- `record` (object, required)
- `scenario_id` (string, required)
- `withdraw_evidence`

### `get_attestation_summary` (~74 tokens)

Summarize what a Forge Orbital record attests

Verifies a Forge Orbital demo decision record against the pinned demo key and summarizes what it attests: signature status, the decision, whether the engine abstained, whether human review is required, and how many evidence items were used. Does not store the record. Demo records only.

Input parameters:

- `record` (object, required)

### `explain_verdict` (~56 tokens)

Explain a Forge Orbital verdict in plain English

Explains, in plain English, why Forge Orbital reached the verdict in a demo decision record and what evidence a reviewer would need to change it. Read-only, stateless, demo data only.

Input parameters:

- `record` (object, required)

### `review_agent_workflow` (~274 tokens)

Evaluate an agent change and explore cost options

Run the Forge accountability engine evaluator and optimizer on synthetic examples or supplied labeled old/new outputs. For samples use payload={"sample_mode":"improved"}, or regression/changed_path. For a user-supplied comparison, translate only their supplied actions into this exact format: payload={"workflow":"User test","cases":[{"id":"case-1","expected":{"action":"hold"},"baseline":{"output":{"action":"allow"},"trajectory":[]},"candidate":{"output":{"action":"hold"},"trajectory":[]}}]}. Replace example actions with the user actions; never invent labels or steps. If the user has not said what should happen, ask them in plain English before scoring. The user never needs to write JSON or know these field names. Cases need id, expected.action, baseline.output.action, baseline.trajectory, candidate.output.action and candidate.trajectory. Use empty trajectory arrays when no action steps were supplied. Do not use plain strings for expected/baseline/candidate. Omit usage entirely unless token usage was supplied. If a format error occurs, repair the structure without changing the evidence and retry. A description alone returns a standard preparation checklist, not a measured evaluation. No code runs, external agent calls, changes or deployment. Synthetic prices are unsigned estimates, never approved savings.

Input parameters:

- `payload` (object, required)

## Diagnostics

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

## Score history

- 2026-11-05: 66
- 2026-11-04: 66
- 2026-11-03: 66
- 2026-11-02: 65

## Common questions

### What is the Forge AI Accountability MCP server?

Forge AI Accountability is an MCP server listed in the public MCP registry as io.github.forgeorbital/forge-ai-accountability. Demo of Forge decision accountability on fictional Acme Mutual: signed, replayable records. This page covers its hosted endpoint (https://demo.forgeorbital.com/mcp).

### Is the Forge AI Accountability MCP server safe to use?

Forge AI Accountability scores 66 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 Forge AI Accountability MCP server expose?

Forge AI Accountability exposes 7 tools: list_scenarios, run_check, verify_decision_record, replay_decision_record, get_attestation_summary, and 2 more. Their descriptions and schemas cost roughly 716 tokens of context every time the server is loaded.

### Does the Forge AI Accountability MCP server require authentication?

Its publisher declares no required credentials for Forge AI Accountability. We have not been able to confirm that against the live endpoint, and a server can require authorisation without declaring it here.

### Is the Forge AI Accountability MCP server still maintained?

Forge AI Accountability is still listed in the MCP registry, though our most recent checks did not reach this channel. We last reached this channel on 3 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://demo.forgeorbital.com/mcp
- Website: https://forgeorbital.com/
- Changelog RSS feed: https://verifymcp.io/servers/forgeorbital-forge-ai-accountability/demo.xml
- Changelog JSON feed: https://verifymcp.io/servers/forgeorbital-forge-ai-accountability/demo.json
- HTML version of this page: https://verifymcp.io/servers/forgeorbital-forge-ai-accountability/demo