# `io.github.flowzap-xyz/flowzap` 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/io.github.flowzap-xyz/flowzap
- JSON: https://radar.anlyon.com/api/v1/servers/io.github.flowzap-xyz/flowzap
- Version: 2.2.1 (active)
- Publisher: io.github.flowzap-xyz (GitHub account)
- Runs: remote (streamable-http), local (npm)
- Sign-in to list tools: none
- Repository: https://github.com/flowzap-xyz/flowzap-mcp
- Metadata from the official MCP Registry, synced 2026-11-08T12:17:38.721Z

Title and description, as the publisher wrote them:

```untrusted-server-text
Create workflow, sequence, architecture, and mind map diagrams via AI assistants.
```

Scanned 2026-11-08T11:18:13.220Z over streamable-http.

**13 tools: 1 can delete or cancel things, 10 change things and 2 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 1 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 10 | ask |
| Only reads | read | 2 | allow |

## Exfil surface

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

| 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__flowzap__flowzap_compliance_check` |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | none |

## Findings

- **warn** Annotations that disagree with the tool in `flowzap_validate` ([annotation-conflict](https://radar.anlyon.com/methodology#annotation-conflict))

```untrusted-server-text
The server marks "flowzap_validate" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "flowzap_validate" says "validate": a word for reading.
```

- **warn** Annotations that disagree with the tool in `flowzap_fix` ([annotation-conflict](https://radar.anlyon.com/methodology#annotation-conflict))

```untrusted-server-text
The server marks "flowzap_fix" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The input takes a statement or command to run (input.code), which can change anything it can reach.
```

- **warn** Annotations that disagree with the tool in `flowzap_mindmap_validate` ([annotation-conflict](https://radar.anlyon.com/methodology#annotation-conflict))

```untrusted-server-text
The server marks "flowzap_mindmap_validate" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "flowzap_mindmap_validate" says "validate": a word for reading.
```

- **warn** Annotations that disagree with the tool in `flowzap_mindmap_approve` ([annotation-conflict](https://radar.anlyon.com/methodology#annotation-conflict))

```untrusted-server-text
The server marks "flowzap_mindmap_approve" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "flowzap_mindmap_approve" says "approve": a word for a change.
```

- **warn** Annotations that disagree with the tool in `flowzap_mindmap_template` ([annotation-conflict](https://radar.anlyon.com/methodology#annotation-conflict))

```untrusted-server-text
The server marks "flowzap_mindmap_template" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "generate": a word for a change.
```

- **warn** Annotations that disagree with the tool in `flowzap_export_graph` ([annotation-conflict](https://radar.anlyon.com/methodology#annotation-conflict))

```untrusted-server-text
The server marks "flowzap_export_graph" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The input takes a statement or command to run (input.code), which can change anything it can reach.
```

- **warn** Annotations that disagree with the tool in `flowzap_compliance_check` ([annotation-conflict](https://radar.anlyon.com/methodology#annotation-conflict))

```untrusted-server-text
The server marks "flowzap_compliance_check" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The description's first verb is "run": a word for a change.
```


## Deletes or cancels (1)

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

### `flowzap_apply_change`

- The name "flowzap_apply_change" says "apply": a word for a change.
- The input takes a statement or command to run (input.code), which can change anything it can reach.
- The server marks it destructive (destructiveHint: true).

Description, as the server wrote it:

```untrusted-server-text
Apply structured patch operations (insert/remove/update nodes or edges) to FlowZap Code. Returns an advisory quality block listing process defects (e.g. a step with no incoming edge, more than one start circle); the diagram is still created — fix the code and call again.
```

## Changes things (10)

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

### `flowzap_artifact_to_diagram`

- The description's first verb is "convert": a word for a change.

Description, as the server wrote it:

```untrusted-server-text
Convert HTTP logs, OpenAPI specs, or code snippets into a FlowZap diagram.
```

### `flowzap_compliance_check`

- The description's first verb is "run": a word for a change.
- The input takes a statement or command to run (input.code), which can change anything it can reach.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.
- Findings: warn annotation-conflict

Description, as the server wrote it:

```untrusted-server-text
Run an automated SOC2 / GDPR / PIPL / EU AI Act architectural compliance review of a FlowZap Code data flow. Returns a Markdown summary of findings (control · status · detail · recommendation) for each framework whose elements are detectable in the diagram. Free quota: 10 free compliance reviews per client per rolling 30-day period. For unlimited manual reviews, paste your code at https://flowzap.xyz/soc2-gdpr-pipl-compliance-checker. Processor disclosure (GDPR Art. 13): analysis powered by Deepseek (Hangzhou DeepSeek AI, China) — see https://flowzap.xyz/legal/subprocessors. This is an advisory architectural review, not legal advice.
```

### `flowzap_create_playground`

- The name "flowzap_create_playground" says "create": a word for a change.
- The input takes a statement or command to run (input.code), which can change anything it can reach.

Description, as the server wrote it:

```untrusted-server-text
Create a shareable FlowZap playground URL. Set view to 'architecture', 'sequence', or 'mindmap' when appropriate. Returns an advisory quality block listing process defects (e.g. a step with no incoming edge, more than one start circle); the diagram is still created — fix the code and call again.
```

### `flowzap_export_graph`

- The input takes a statement or command to run (input.code), which can change anything it can reach.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- Findings: warn annotation-conflict

Description, as the server wrote it:

```untrusted-server-text
Parse FlowZap Code into a structured JSON graph (lanes, nodes, edges).
```

### `flowzap_fix`

- The input takes a statement or command to run (input.code), which can change anything it can reach.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- Findings: warn annotation-conflict

Description, as the server wrote it:

```untrusted-server-text
Deterministically repair mechanical FlowZap Code errors: non-sequential node numbering, inferred edge handles, node/edge label syntax, missing lane display labels, emoji and non-printable characters. Returns the repaired code plus the list of corrections that were applied. Errors that cannot be repaired are reported as-is — the repairer never invents content.
```

### `flowzap_mindmap_approve`

- The name "flowzap_mindmap_approve" says "approve": a word for a change.
- The input takes a statement or command to run (input.code), which can change anything it can reach.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- Findings: warn annotation-conflict

Description, as the server wrote it:

```untrusted-server-text
Check if valid FlowZap Code is suitable for Mind Map rendering. Returns structured verdict with errors (blocking), warnings (advisory), and info. Rules: diamonds and taskboxes are ERROR (not rendered in mind maps), multiple circles produce WARNING (only the first is the root), edge directions are INFO (ignored by renderer), large/deep diagrams produce advisory warnings. Uses local parsing only - no API call.
```

### `flowzap_mindmap_create_playground`

- The name "flowzap_mindmap_create_playground" says "create": a word for a change.
- The input takes a statement or command to run (input.code), which can change anything it can reach.

Description, as the server wrote it:

```untrusted-server-text
Create a FlowZap playground session that opens directly in Mind Map view (?view=mindmap). Validates the code first, then creates a shareable URL. Use this after flowzap_mindmap_validate and flowzap_mindmap_approve have passed.
```

### `flowzap_mindmap_template`

- The description's first verb is "generate": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- Findings: warn annotation-conflict

Description, as the server wrote it:

```untrusted-server-text
Generate a ready-to-extend FlowZap Code skeleton for a Mind Map. Returns a tree structure with a central circle root, rectangle branches and sub-branches, and optional cross-links between branches. Use this to bootstrap a new mind map.
```

### `flowzap_mindmap_validate`

- The name "flowzap_mindmap_validate" says "validate": a word for reading.
- The input takes a statement or command to run (input.code), which can change anything it can reach.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- Findings: warn annotation-conflict

Description, as the server wrote it:

```untrusted-server-text
Validate FlowZap Code syntax specifically for Mind Map diagrams. Checks syntax validity and whether the code is mind-map-ready (no diamonds, no taskboxes, at least one circle for the root, at least one rectangle for branches). Use this before flowzap_mindmap_approve and flowzap_mindmap_create_playground.
```

### `flowzap_validate`

- The name "flowzap_validate" says "validate": a word for reading.
- The input takes a statement or command to run (input.code), which can change anything it can reach.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- Findings: warn annotation-conflict

Description, as the server wrote it:

```untrusted-server-text
Validate FlowZap Code syntax. Returns errors and stats.
```

## Only reads (2)

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

### `flowzap_diff`

- The name "flowzap_diff" says "diff": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Compare two FlowZap Code versions and return a structured diff.
```

### `flowzap_get_syntax`

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

Description, as the server wrote it:

```untrusted-server-text
Get FlowZap Code syntax documentation and examples.
```

## Claude Code permissions

For `.claude/settings.json`, assuming the server is installed as `flowzap`:

```json
{
  "permissions": {
    "allow": [
      "mcp__flowzap__flowzap_get_syntax",
      "mcp__flowzap__flowzap_diff"
    ],
    "ask": [
      "mcp__flowzap__flowzap_validate",
      "mcp__flowzap__flowzap_fix",
      "mcp__flowzap__flowzap_mindmap_validate",
      "mcp__flowzap__flowzap_mindmap_approve",
      "mcp__flowzap__flowzap_mindmap_template",
      "mcp__flowzap__flowzap_mindmap_create_playground",
      "mcp__flowzap__flowzap_create_playground",
      "mcp__flowzap__flowzap_export_graph",
      "mcp__flowzap__flowzap_artifact_to_diagram",
      "mcp__flowzap__flowzap_compliance_check"
    ],
    "deny": [
      "mcp__flowzap__flowzap_apply_change"
    ]
  }
}
```

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

- `mcp__flowzap__flowzap_compliance_check`: untrusted-input

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-11-20T19:04:54.197Z, unchanged since 2026-10-22T14:59:14.312Z. 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 | `11` |
| 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 11 tools that change things (1 destructive, 10 write). Whether a call also works without credentials was not tested: tools are never called.

https://flowzap.xyz/mcp: tools/list returned 13 tools to an anonymous client, including flowzap_apply_change (destructive), flowzap_validate (write), flowzap_fix (write), flowzap_mindmap_validate (write), flowzap_mindmap_approve (write) and 6 more
```
