Skip to content

Forge AI Accountability MCP server

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

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

7 tools: 4 change things and 3 only read.

Tools: 0 delete, 0 irreversible, 4 write, 3 read.
  • Reads private data · 0
  • Reads text others write · 1
  • Can send data out · 0
  • 2 findings

Tools listed without sign-in. Remote posture

With Anlyon

4 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the Forge AI Accountability MCP server can do

The Forge AI Accountability MCP server is published by the GitHub account forgeorbital. It has 7 tools. It can create or change data (4 tools: run_check, verify_decision_record, replay_decision_record and review_agent_workflow), but cannot delete data. 3 tools only read.

1 tool brings in text other people can write (get_attestation_summary).

The fixed checks matched 2 findings (annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 16, 2026, version 1.30.0.

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 4Claude 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a Forge Orbital demo decision: re-runs the deterministic engine on the same sample scenario (and any withdrawn evidence) and checks that the replay key and the decision mat…No findings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    Replays a Forge Orbital demo decision: re-runs the deterministic engine on the same sample scenario (and any withdrawn evidence) and checks that the replay key and the decision match the record.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_workflowUse Evaluate and Optimise to compare synthetic examples or supplied labeled old/new outputs with the Forge accountability engine.1 finding

    Why it is in this group

    • The description's first verb is "evaluate": 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 "evaluate": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Use Evaluate and Optimise to compare synthetic examples or supplied labeled old/new outputs with the Forge accountability engine. 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.

    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 3Show 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.
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.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 17, 2026, 15:22 UTC, unchanged since Nov 3, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
4
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 4 tools that change things (4 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://demo.forgeorbital.com/mcp: tools/list returned 7 tools to an anonymous client, including run_check (write), verify_decision_record (write), replay_decision_record (write), review_agent_workflow (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

2 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
  • 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 "evaluate": a word for a change.

    What this check looks for

History

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

  1. Tools1 changed.~1 changedView diff

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

Pin

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://radar.anlyon.com/api/v1/servers/io.github.forgeorbital/forge-ai-accountability/verify?hash=84de55cd6bb019ce7eb851d86f58e13fdf8b3937bb802a2cf8fba24191a5ee34" | jq -e '.changed == false'

Pinned hash 84de55cd6bb0, from Nov 16, 2026, 01:17 UTC.

Watch

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

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

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

Badge

Anlyon Radar badge for io.github.forgeorbital/forge-ai-accountability
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.forgeorbital/forge-ai-accountability.svg)](https://radar.anlyon.com/servers/io.github.forgeorbital/forge-ai-accountability)

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

Forge AI Accountability MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Forge AI Accountability MCP server safe?

No scan can promise that. What its definitions show: 7 tools, 4 of which can change, send or delete something, and 2 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Forge AI Accountability MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Forge AI Accountability MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the Forge AI Accountability MCP server have?

7 tools: 4 write, 3 read. run_check, verify_decision_record, replay_decision_record, review_agent_workflow, list_scenarios, get_attestation_summary and explain_verdict.

Does the Forge AI Accountability MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Forge AI Accountability MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the Forge AI Accountability MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 16, 2026. Every change is on this page and in its Atom feed.