Forge AI Accountability

io.github.forgeorbital/forge-ai-accountabilityforgeorbitalstreamable-httpv1.30.0Scanned 2 hours ago

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

7 tools: 4 change things and 3 only read.

Reads private data · 0
Reads text others write · 1
Can send data out · 0
2 findings

Anlyon alternative

4 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

7 tools

Changes things 4Creates or changes something that can be changed back.Claude Code: ask

replay_decision_recordReplays a Forge Orbital demo decision: re-runs the deterministic engine on the same sample scenario (and any withdrawn evidence) and checks that the replay key and the decision mat…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
Replays a Forge Orbital demo decision: re-runs the deterministic engine on the same sample scenario (and any withdrawn evidence) and checks that the replay key and the decision match the record.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.
Annotations the server declares
- title: Replay a Forge Orbital decision from its inputs
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
review_agent_workflowRun the Forge evaluator and optimizer on synthetic examples or supplied labeled baseline/candidate outputs and token usage.1 finding
Why it is in this group
- The description's first verb is "run": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
  The server marks "review_agent_workflow" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
  Matched text
  annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "run": a word for a change.
  What this check looks for
Description, as the server wrote it
Run the Forge evaluator and optimizer on synthetic examples or supplied labeled baseline/candidate outputs and token usage. Use payload={sample_mode: improved}, regression, or changed_path for examples. A description alone returns an integration plan, not a measured evaluation. No code runs, external agent calls, changes or deployment. Synthetic prices are unsigned estimates, never approved savings. Interactive version: https://demo.forgeorbital.com/sandbox/
Annotations the server declares
- title: Evaluate an agent change and explore cost options
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
run_checkComputes a Forge Orbital verdict for one of five fictional Acme Mutual Insurance scenarios and returns it with a signed decision record in the response.1 finding
Why it is in this group
- The name "run_check" says "run": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
  The server marks "run_check" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
  Matched text
  annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":false}; The name "run_check" says "run": a word for a change.
  What this check looks for
Description, as the server wrote it
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.
Annotations the server declares
- title: Run a Forge Orbital check on a sample scenario
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
verify_decision_recordVerifies the Ed25519 signature of a Forge Orbital demo decision record against the published demo key id.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
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.
Annotations the server declares
- title: Verify a Forge Orbital decision record
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false

Only reads 3Looks things up and changes nothing.Show 3 read-only tools

explain_verdictExplains, in plain English, why Forge Orbital reached the verdict in a demo decision record and what evidence a reviewer would need to change it.No findings
Why it is in this group
- The name "explain_verdict" says "explain": a word for reading.
Description, as the server wrote it
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.
Annotations the server declares
- title: Explain a Forge Orbital verdict in plain English
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_attestation_summaryVerifies 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 huma…Reads text others writeNo findings
Why it is in this group
- The name "get_attestation_summary" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "review": it reads comments, which other people can write.
Description, as the server wrote it
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.
Annotations the server declares
- title: Summarize what a Forge Orbital record attests
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_scenariosLists the five sample scenarios for the fictional Acme Mutual Insurance that run_check accepts, with their evidence ids.No findings
Why it is in this group
- The name "list_scenarios" says "list": a word for reading.
Description, as the server wrote it
Lists the five sample scenarios for the fictional Acme Mutual Insurance that run_check accepts, with their evidence ids. Demo data only.
Annotations the server declares
- title: List demo scenarios
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.

Reads private data0: Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write1: Brings in text someone else can write: web pages, inbound email, messages, issues and comments.; get_attestation_summary
Can send data out0: Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Findings

Matches of fixed checks, with the text they matched.

2 warn

Warnrun_check
The server marks "run_check" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
Matched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":false}; The name "run_check" says "run": a word for a change.
What this check looks for
Warnreview_agent_workflow
The server marks "review_agent_workflow" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
Matched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "run": a word for a change.
What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

All changes to this server

Install

Pinned to version 1.30.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http forge-ai-accountability https://demo.forgeorbital.com/mcp

claude mcp add --transport http forge-ai-accountability https://demo.forgeorbital.com/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json

{
  "permissions": {
    "allow": [
      "mcp__forge-ai-accountability__list_scenarios",
      "mcp__forge-ai-accountability__get_attestation_summary",
      "mcp__forge-ai-accountability__explain_verdict"
    ],
    "ask": [
      "mcp__forge-ai-accountability__run_check",
      "mcp__forge-ai-accountability__verify_decision_record",
      "mcp__forge-ai-accountability__replay_decision_record",
      "mcp__forge-ai-accountability__review_agent_workflow"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as forge-ai-accountability. Review it before you use it.

Capability tags behind 1 rule

mcp__forge-ai-accountability__get_attestation_summary untrusted-input

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://anlyon.dev/api/v1/servers/io.github.forgeorbital/forge-ai-accountability/verify?hash=c34ccf742aae9e09c0893d2f8f63816fbe14ed91ed2d32128008ee04bfb9f709" | jq -e '.changed == false'

Pinned hash c34ccf742aae, from Nov 2, 2026, 17:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://anlyon.dev/servers/io.github.forgeorbital/forge-ai-accountability/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

[![anlyon.dev](https://anlyon.dev/badge/io.github.forgeorbital/forge-ai-accountability.svg)](https://anlyon.dev/servers/io.github.forgeorbital/forge-ai-accountability)

Source: MCP Registry. Synced Nov 2, 2026, 18:18 UTC.