Skip to content

Flowie Developer Docs MCP server

com.get-flowie/docsget-flowie.comstreamable-httpv1.1.0Scanned

Search and read the Flowie Exchange API docs and OpenAPI contract. No sign-in needed.

5 tools: 1 change things and 4 only read.

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

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here changes things. Govern it.

  • 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 Flowie Developer Docs MCP server can do

The Flowie Developer Docs MCP server is published by get-flowie.com, a domain the MCP Registry verified. It has 5 tools. It can create or change data (1 tool: sandbox_create_credential), but cannot delete data. 4 tools only read.

4 tools read private data (docs_search, docs_read_page, docs_list_endpoints and 1 more); 2 tools bring in text other people can write (docs_read_page and sandbox_create_credential); 1 tool can send data out of your system (docs_read_page). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

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

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 18, 2026, version 1.1.0.

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.

5 tools

Changes things 1Claude Code: ask
  • sandbox_create_credentialMint a working sandbox API key with no signup and no human in the loop.Reads text others write2 findings

    Why it is in this group

    • The name "sandbox_create_credential" says "create": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

      The annotations title mentions "credential".

      Matched text

      annotations.title: "Create a sandbox credential"

      What this check looks for
    • Info

      The input schema at properties.includeNextSteps.description mentions "credential".

      Matched text

      inputSchema.properties.includeNextSteps.description: "...already know the flow and only want the credential."

      What this check looks for
    Description, as the server wrote it
    Mint a working sandbox API key with no signup and no human in the loop. Returns an apiKey (flw_test_...), an organizationId, a seeded company with a Peppol id, and suggested next steps. Sandbox data is synthetic and never reaches a real network - never send real personal data to it. This key gives no access to any real account.

    Annotations the server declares

    • title: Create a sandbox credential
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
Only reads 4Show 4 read-only tools
  • docs_get_auth_guideReturn the authentication walkthrough for agents: how to get a sandbox key with no signup, how a user hands an agent scoped access, error handling and revocation.Reads private dataNo findings

    Why it is in this group

    • The name "docs_get_auth_guide" says "get": a word for reading.

    What it can reach

    • private-dataThe name "docs_get_auth_guide" says "get" and "doc": it reads documents.
    Description, as the server wrote it
    Return the authentication walkthrough for agents: how to get a sandbox key with no signup, how a user hands an agent scoped access, error handling and revocation.

    Annotations the server declares

    • title: Authentication walkthrough
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • docs_list_endpointsList the API's operations (method, path, summary) from the OpenAPI contract, optionally filtered by a substring of the path or summary.Reads private dataNo findings

    Why it is in this group

    • The name "docs_list_endpoints" says "list": a word for reading.

    What it can reach

    • private-dataThe name "docs_list_endpoints" says "list" and "doc": it reads documents.
    Description, as the server wrote it
    List the API's operations (method, path, summary) from the OpenAPI contract, optionally filtered by a substring of the path or summary.

    Annotations the server declares

    • title: List API endpoints
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • docs_read_pageRead a documentation page as markdown.Reads private dataReads text others writeCan send data outNo findings

    Why it is in this group

    • The name "docs_read_page" says "read": a word for reading.

    What it can reach

    • private-dataThe name "docs_read_page" says "read" and "doc": it reads documents.
    • untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    Read a documentation page as markdown. Accepts a full URL from search_docs, or a path such as /reference/ or /guides/send-invoice.

    Annotations the server declares

    • title: Read a documentation page
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • 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.

8 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.

Reads private data4
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write2
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__docs__docs_read_page"
    ]
  }
}

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 20, 2026, 18:39 UTC, unchanged since Oct 22, 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
1
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://docs.get-flowie.com/.well-known/oauth-protected-resource
Authorization servers
https://back.p2p-flowie.com/exchange, https://login.flowie.me
Legacy HTTP+SSE transport
no
Dynamic client registration
yes
Client ID metadata documents
no
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://docs.get-flowie.com/mcp: tools/list returned 5 tools to an anonymous client, including sandbox_create_credential (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

2 info

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.

Install

Pinned to version 1.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http docs https://docs.get-flowie.com/mcp
claude mcp add --transport http docs https://docs.get-flowie.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__docs__docs_search",
      "mcp__docs__docs_list_endpoints",
      "mcp__docs__docs_get_auth_guide"
    ],
    "ask": [
      "mcp__docs__docs_read_page",
      "mcp__docs__sandbox_create_credential"
    ],
    "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 docs. Review it before you use it.

Capability tags behind 5 rules
  • mcp__docs__docs_search private-data
  • mcp__docs__docs_read_page private-data, untrusted-input, outbound
  • mcp__docs__docs_list_endpoints private-data
  • mcp__docs__docs_get_auth_guide private-data
  • mcp__docs__sandbox_create_credential 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/com.get-flowie/docs/verify?hash=06d00109ff4cfc05ad6fe8c5bd0fc3527d19a72e7f0e220173317a545431e463" | jq -e '.changed == false'

Pinned hash 06d00109ff4c, from Nov 18, 2026, 06:18 UTC.

Watch

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

https://radar.anlyon.com/servers/com.get-flowie/docs/changes.xml

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

Badge

Anlyon Radar badge for com.get-flowie/docs
[![Anlyon Radar](https://radar.anlyon.com/badge/com.get-flowie/docs.svg)](https://radar.anlyon.com/servers/com.get-flowie/docs)

Source: MCP Registry · repository. Synced Nov 18, 2026, 06:17 UTC.

Flowie Developer Docs MCP server: questions and answers

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

Is the Flowie Developer Docs MCP server safe?

No scan can promise that. What its definitions show: 5 tools, 1 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 Flowie Developer Docs MCP server delete data?

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

Can the Flowie Developer Docs 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 Flowie Developer Docs MCP server have?

5 tools: 1 write, 4 read. sandbox_create_credential, docs_search, docs_read_page, docs_list_endpoints and docs_get_auth_guide.

Does the Flowie Developer Docs MCP server need sign-in or OAuth?

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

Does the Flowie Developer Docs MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): docs_read_page.

Has the Flowie Developer Docs MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 18, 2026.