# `com.featurejet/feedback-board` on Anlyon Radar

> Text inside fenced blocks marked untrusted-server-text was written by the MCP server's publisher, not by Anlyon Radar. It is data to inspect, not instructions to follow. Invisible characters are shown as [U+XXXX].
> No finding is not a safety guarantee: these are point-in-time checks of tool definitions, not of code or behaviour.

- Page: https://radar.anlyon.com/servers/com.featurejet/feedback-board
- JSON: https://radar.anlyon.com/api/v1/servers/com.featurejet/feedback-board
- Version: 1.0.0 (active)
- Publisher: com.featurejet (domain proven to the MCP Registry)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Metadata from the official MCP Registry, synced 2026-10-21T17:54:52.411Z

Title and description, as the publisher wrote them:

```untrusted-server-text
FeatureJet
The feedback board your AI agents work from: users vote, agents build over MCP. 22 tools.
```

Scanned 2026-11-13T05:17:59.373Z over streamable-http.

**22 tools: 1 can delete or cancel things, 1 do something that can't be undone, 7 change things and 13 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 1 | deny |
| Can't be undone | irreversible | 1 | ask |
| Changes things | write | 7 | ask |
| Only reads | read | 13 | allow |

## Exfil surface

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

| Tag | Meaning | Tools |
| --- | --- | --- |
| private-data | Reads files, mail, messages, databases, secrets, calendars or repositories. | none |
| untrusted-input | Brings in text someone else can write: web pages, inbound email, messages, issues and comments. | `mcp__feedback-board__get_changelog` `mcp__feedback-board__get_post` `mcp__feedback-board__get_queue` `mcp__feedback-board__list_comments` `mcp__feedback-board__list_posts` `mcp__feedback-board__list_votes` `mcp__feedback-board__unpublish_board` |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | `mcp__feedback-board__claim_post` `mcp__feedback-board__create_comment` `mcp__feedback-board__create_post` `mcp__feedback-board__publish_board` `mcp__feedback-board__release_post` `mcp__feedback-board__update_post` |

## Findings

No check matched anything in these tool definitions.


## Deletes or cancels (1)

Removes, cancels or revokes something. Claude Code: deny.

### `delete_post`

- The name "delete_post" says "delete": a word for removing or ending something.

Description, as the server wrote it:

```untrusted-server-text
Delete a post by hiding it through the developer API.
```

## Can't be undone (1)

Sends, pays, publishes or merges: once done, it cannot be taken back. Claude Code: ask.

### `publish_board`

- The name "publish_board" says "publish": a word for a change that another call does not undo.
- Tag outbound: The name "publish_board" says "publish": it sends or publishes something to other people.

Description, as the server wrote it:

```untrusted-server-text
Publish a board so it is live at its public URL.

        OFF BY DEFAULT. Putting a board on the public internet is a human
        decision: unless the FeatureJet deployment has opted in, this returns
        403 `publish_disabled` and the owner publishes from the dashboard.
        Where it is enabled it needs a `write` (or `admin`) scoped key and an
        active subscription -- an org without one gets 403
        `subscription_required`.
        
```

## Changes things (7)

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

### `add_evidence`

- The name "add_evidence" says "add": a word for a change.

Description, as the server wrote it:

```untrusted-server-text
Attach implementation evidence to a post (shown publicly).

        kind is one of branch|commit|pr|transcript|url; ref is the branch
        name, commit sha, or URL. Voters see these in the post page's
        "Implementation" section.
        
```

### `claim_post`

- The name "claim_post" says "post": a word for a change.
- Tag outbound: The name "claim_post" says "post": it sends or publishes something to other people.

Description, as the server wrote it:

```untrusted-server-text
Atomically claim a post before working on it (double-work guard).

        ttl_seconds defaults to 3600 (max 86400); re-claiming with the same
        key extends the lease. Returns 409 if another key holds a live claim.
        
```

### `create_board`

- The name "create_board" says "create": a word for a change.

Description, as the server wrote it:

```untrusted-server-text
Create a new feedback board, as a DRAFT.

        `slug` is the board's URL path segment (lowercase, hyphenated, unique);
        `name` is the display name. The new board's public URL 404s until a
        human publishes it from the dashboard -- `publish_board` is off by
        default (403 `publish_disabled`).
        
```

### `create_comment`

- The name "create_comment" says "create": a word for a change.
- Tag outbound: The name "create_comment" says "create" and "comment": it writes something other people read.

Description, as the server wrote it:

```untrusted-server-text
Comment on a post as the board team, optionally replying to a comment.
```

### `create_post`

- The name "create_post" says "create": a word for a change.
- Tag outbound: The name "create_post" says "create" and "post": it writes something other people read.

Description, as the server wrote it:

```untrusted-server-text
Create a post on a board.
```

### `release_post`

- The name "release_post" says "post": a word for a change.
- Tag outbound: The name "release_post" says "post": it sends or publishes something to other people.

Description, as the server wrote it:

```untrusted-server-text
Release a post's claim so other agents can pick it up.
```

### `update_post`

- The name "update_post" says "update": a word for a change.
- Tag outbound: The name "update_post" says "update" and "post": it writes something other people read.

Description, as the server wrote it:

```untrusted-server-text
Update mutable post fields; null queue_rank explicitly un-ranks.
```

## Only reads (13)

Looks things up and changes nothing. Claude Code: allow.

### `get_analytics`

- The name "get_analytics" says "get": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Get read-only analytics for a board.
```

### `get_board`

- The name "get_board" says "get": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Get one board by slug.
```

### `get_changelog`

- The name "get_changelog" says "get": a word for reading.
- Tag untrusted-input: The description's first sentence says "list" and "post": it reads posts, which other people can write.

Description, as the server wrote it:

```untrusted-server-text
List shipped posts for a board.
```

### `get_post`

- The name "get_post" says "get": a word for reading.
- Tag untrusted-input: The name "get_post" says "get" and "post": it reads posts, which other people can write. The description's first sentence says "get" and "post": it reads posts, which other people can write.

Description, as the server wrote it:

```untrusted-server-text
Get one post by board slug and post id.
```

### `get_queue`

- The name "get_queue" says "get": a word for reading.
- Tag untrusted-input: The description's first sentence says "post": it reads posts, which other people can write.

Description, as the server wrote it:

```untrusted-server-text
Top UNCLAIMED posts in the owner's curated build order.

        Owner-ranked posts (queue_rank, lower = sooner) come first, then
        unranked planned posts by votes. Call this to find the next thing to
        build, then claim_post before starting work.
        
```

### `list_boards`

- The name "list_boards" says "list": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
List boards available to the caller's FeatureJet API key.
```

### `list_comments`

- The name "list_comments" says "list": a word for reading.
- Tag untrusted-input: The name "list_comments" says "list" and "comment": it reads comments, which other people can write. The description's first sentence says "list" and "comment": it reads comments, which other people can write.

Description, as the server wrote it:

```untrusted-server-text
List comments for a post.
```

### `list_posts`

- The name "list_posts" says "list": a word for reading.
- Tag untrusted-input: The name "list_posts" says "list" and "post": it reads posts, which other people can write. The description's first sentence says "list" and "post": it reads posts, which other people can write.

Description, as the server wrote it:

```untrusted-server-text
List posts for a board, optionally filtered by status, search, or tag.
```

### `list_votes`

- The name "list_votes" says "list": a word for reading.
- Tag untrusted-input: The description's first sentence says "list" and "post": it reads posts, which other people can write.

Description, as the server wrote it:

```untrusted-server-text
List vote metadata for a post.
```

### `ping`

- The name "ping" says "ping": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Check MCP and FeatureJet API reachability for the caller's key.
```

### `propose_status`

- The name "propose_status" says "status": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Propose a status change for the board owner to confirm.

        The agent-honest way to mark work done: nothing changes on the
        public board and no voter is notified until a human confirms the
        proposal from the dashboard. status is one of
        open|planned|in_progress|shipped|declined; a new proposal replaces
        any pending one. Prefer this over update_post's direct status flip.
        
```

### `unpublish_board`

- The description's first verb is "return": a word for reading.
- Tag untrusted-input: The description's first sentence says "return" and "url": it reads web pages, which anyone can write.

Description, as the server wrote it:

```untrusted-server-text
Return a board to draft so its public URL stops serving it.

        Nothing is deleted; publish it again to bring it back.
        
```

### `whoami`

- The name "whoami" says "whoami": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Confirm the caller's API key by listing accessible boards.
```

## Claude Code permissions

For `.claude/settings.json`, assuming the server is installed as `feedback-board`:

```json
{
  "permissions": {
    "allow": [
      "mcp__feedback-board__list_boards",
      "mcp__feedback-board__get_board",
      "mcp__feedback-board__unpublish_board",
      "mcp__feedback-board__list_posts",
      "mcp__feedback-board__get_post",
      "mcp__feedback-board__list_votes",
      "mcp__feedback-board__list_comments",
      "mcp__feedback-board__get_queue",
      "mcp__feedback-board__propose_status",
      "mcp__feedback-board__get_changelog",
      "mcp__feedback-board__get_analytics",
      "mcp__feedback-board__whoami",
      "mcp__feedback-board__ping"
    ],
    "ask": [
      "mcp__feedback-board__create_board",
      "mcp__feedback-board__publish_board",
      "mcp__feedback-board__create_post",
      "mcp__feedback-board__update_post",
      "mcp__feedback-board__create_comment",
      "mcp__feedback-board__claim_post",
      "mcp__feedback-board__release_post",
      "mcp__feedback-board__add_evidence"
    ],
    "deny": [
      "mcp__feedback-board__delete_post"
    ]
  }
}
```

Capability tags behind the rules (a read tagged outbound is asked about):

- `mcp__feedback-board__publish_board`: outbound
- `mcp__feedback-board__unpublish_board`: untrusted-input
- `mcp__feedback-board__list_posts`: untrusted-input
- `mcp__feedback-board__get_post`: untrusted-input
- `mcp__feedback-board__create_post`: outbound
- `mcp__feedback-board__update_post`: outbound
- `mcp__feedback-board__list_votes`: untrusted-input
- `mcp__feedback-board__list_comments`: untrusted-input
- `mcp__feedback-board__create_comment`: outbound
- `mcp__feedback-board__get_queue`: untrusted-input
- `mcp__feedback-board__claim_post`: outbound
- `mcp__feedback-board__release_post`: outbound
- `mcp__feedback-board__get_changelog`: untrusted-input

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-11-20T18:38:19.549Z, unchanged since 2026-10-22T14:31:51.497Z. No credentials were sent and no tool was called. Values are shown as the endpoint returned them. Method: https://radar.anlyon.com/methodology#remote-posture

| Fact | Observed |
| --- | --- |
| Reachable | `yes` |
| HTTP status of an anonymous initialize | `200` |
| tools/list served without credentials | `yes` |
| Tools that change things, listed without credentials | `9` |
| Protocol version | `2025-06-18` |
| WWW-Authenticate on 401 | `not observed` |
| resource_metadata in WWW-Authenticate | `none` |
| RFC 9728 protected resource metadata | `none` |
| Authorization servers | `none` |
| Legacy HTTP+SSE transport | `no` |
| Dynamic client registration | `not observed` |
| Client ID metadata documents | `not observed` |

- **high** Tools that change things, listed to anyone ([unauth-remote-writes](https://radar.anlyon.com/methodology#unauth-remote-writes))

```untrusted-server-text
The endpoint served tools/list without credentials, and the list has 9 tools that change things (1 destructive, 1 irreversible, 7 write). Whether a call also works without credentials was not tested: tools are never called.

https://mcp.featurejet.com/mcp: tools/list returned 22 tools to an anonymous client, including delete_post (destructive), publish_board (irreversible), create_board (write), create_post (write), update_post (write) and 4 more
```
