Skip to content

Posthell MCP server

io.github.Rohan27s/posthellRohan27sstreamable-httpv1.0.0Scanned

Social media scheduler for AI agents: draft posts into a human-approved queue for 15 networks.

8 tools: 5 change things and 3 only read.

Tools: 0 delete, 0 irreversible, 5 write, 3 read.
  • Reads private data · 1
  • Reads text others write · 4
  • Can send data out · 3
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

5 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 Posthell MCP server can do

The Posthell MCP server is published by the GitHub account Rohan27s. It has 8 tools. It can create or change data (5 tools: shape_post, get_upload_url, create_draft, reschedule_post and 1 more), but cannot delete data. 3 tools only read.

1 tool reads private data (get_upload_url); 4 tools bring in text other people can write (get_upload_url, list_posts, reschedule_post and 1 more); 3 tools can send data out of your system (shape_post, reschedule_post and edit_post). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

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 1.0.0.

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.

8 tools

Changes things 5Claude Code: ask
  • create_draftSave a post as a DRAFT in the user's posthell queue, with any photos or videos and per-network settings (Instagram Reel cover, YouTube title/tags).No findings

    Why it is in this group

    • The name "create_draft" says "create": a word for a change.
    Description, as the server wrote it
    Save a post as a DRAFT in the user's posthell queue, with any photos or videos and per-network settings (Instagram Reel cover, YouTube title/tags). Nothing is published by this tool: the user approves it in the dashboard. Optionally propose a publish time. Warnings in the result are what would stop it publishing; fix them by calling again.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • edit_postChange the caption (body), a network's own caption (overrides), and/or the suggested time of a DRAFT.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "edit_post" says "edit": 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.
    • outboundThe name "edit_post" says "edit" and "post": it writes something other people read.
    Description, as the server wrote it
    Change the caption (body), a network's own caption (overrides), and/or the suggested time of a DRAFT. Scheduled posts can only be moved with reschedule_post: changing the text of a post that is already scheduled needs a key the user has allowed to publish. Get the id from list_posts.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • get_upload_urlUse this to post a file from the user's computer (a video you rendered, a photo).Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "get_upload_url" says "get": a word for reading.
    • The description's first verb is "post": a word for a change.

    What it can reach

    • private-dataThe description's first sentence says "file": it reads files.
    • untrusted-inputThe name "get_upload_url" says "get" and "url": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Use this to post a file from the user's computer (a video you rendered, a photo). Returns uploadUrl and mediaUrl: PUT the raw file bytes to uploadUrl with its Content-Type header (the curl line in the result does it), then pass mediaUrl in the media list of create_draft or publish_post. Files are stored for good, so a draft keeps its video. Up to 50MB. Types: JPG, PNG, GIF, WebP, MP4, MOV, WebM, or PDF.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: false
  • reschedule_postChange when a post goes out.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "reschedule_post" says "reschedule": 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.
    • outboundThe name "reschedule_post" says "reschedule" and "post": it writes something other people read.
    Description, as the server wrote it
    Change when a post goes out. Works on a post in the calendar (scheduled) and on a draft (its suggested time). Get the id from list_posts. A scheduled post is taken out of the network's queue and queued again at the new time; every network it was going to moves together.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • shape_postTurn rough notes about what the user did (shipped a feature, fixed a bug, hit a number) into 2-3 finished social-post angles in the user's voice.Can send data outNo findings

    Why it is in this group

    • The name "shape_post" says "post": a word for a change.

    What it can reach

    • outboundThe name "shape_post" says "post": it sends or publishes something to other people.
    Description, as the server wrote it
    Turn rough notes about what the user did (shipped a feature, fixed a bug, hit a number) into 2-3 finished social-post angles in the user's voice. Grounded only in the notes - never invents facts. Uses one AI generation from the user's monthly quota.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: false
Only reads 3Show 3 read-only tools
  • get_growthThe user's follower counts and 7-day growth per connected network, plus which network is growing fastest.No findings

    Why it is in this group

    • The name "get_growth" says "get": a word for reading.
    Description, as the server wrote it
    The user's follower counts and 7-day growth per connected network, plus which network is growing fastest. Use this to decide where a post matters most or to report progress.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • list_accountsThe user's connected social accounts (id, network, handle), their account groups (a named set, e.g.No findings

    Why it is in this group

    • The name "list_accounts" says "list": a word for reading.
    Description, as the server wrote it
    The user's connected social accounts (id, network, handle), their account groups (a named set, e.g. one business's Instagram + YouTube), and what each network needs: caption limit, whether it needs a photo or video, and the settings it takes. Call this first, then pass a group name or account handles to create_draft or publish_post.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
  • list_postsRead the user's recent posts and drafts with per-network status, the live link once a post is up, and the reason when one failed.Reads text others writeNo findings

    Why it is in this group

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

    What it can reach

    • untrusted-inputThe name "list_posts" says "list" and "post": it reads posts, which other people can write.
    • untrusted-inputThe description's first sentence says "read" and "post": it reads posts, which other people can write.
    Description, as the server wrote it
    Read the user's recent posts and drafts with per-network status, the live link once a post is up, and the reason when one failed. Published posts include engagement metrics (likes, comments, shares, engagementRate - impressions on plans with full analytics) once analytics have synced. Use it to avoid duplicating a topic AND to learn which topics performed before drafting the next post.

    Annotations the server declares

    • readOnlyHint: 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.

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

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write4
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out3
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__posthell__get_upload_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 20, 2026, 19:00 UTC, unchanged since Oct 29, 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
5
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 5 tools that change things (5 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://www.posthell.com/api/mcp: tools/list returned 8 tools to an anonymous client, including shape_post (write), get_upload_url (write), create_draft (write), reschedule_post (write), edit_post (write)

    What this check looks for

Posture changes

  1. Oct 29, 2026
    • Tools that change things, listed without credentials: 2 to 5

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

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

  1. Tools4 added, 4 changed.+4 added~4 changedView diff
  2. PostureRemote posture changed. Tools that change things, listed without credentials: 2 -> 5.View diff
    • Tools that change things, listed without credentials: 2 to 5

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http posthell https://www.posthell.com/api/mcp --header 'Authorization: <your-authorization>'
claude mcp add --transport http posthell https://www.posthell.com/api/mcp --header 'Authorization: <your-authorization>'

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__posthell__list_accounts",
      "mcp__posthell__list_posts",
      "mcp__posthell__get_growth"
    ],
    "ask": [
      "mcp__posthell__shape_post",
      "mcp__posthell__get_upload_url",
      "mcp__posthell__create_draft",
      "mcp__posthell__reschedule_post",
      "mcp__posthell__edit_post"
    ],
    "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 posthell. Review it before you use it.

Capability tags behind 5 rules
  • mcp__posthell__shape_post outbound
  • mcp__posthell__get_upload_url private-data, untrusted-input
  • mcp__posthell__list_posts untrusted-input
  • mcp__posthell__reschedule_post untrusted-input, outbound
  • mcp__posthell__edit_post untrusted-input, outbound

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.Rohan27s/posthell/verify?hash=0432fb398637b1d8e3fd879fb35b38f816c7834c4015b9d9df487969457f836d" | jq -e '.changed == false'

Pinned hash 0432fb398637, from Nov 16, 2026, 20:18 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.Rohan27s/posthell/changes.xml

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

Badge

Anlyon Radar badge for io.github.Rohan27s/posthell
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.Rohan27s/posthell.svg)](https://radar.anlyon.com/servers/io.github.Rohan27s/posthell)

Source: MCP Registry. Synced Oct 21, 2026, 18:18 UTC.

Posthell MCP server: questions and answers

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

Is the Posthell MCP server safe?

No scan can promise that. What its definitions show: 8 tools, 5 of which can change, send or delete something, and 0 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 Posthell MCP server delete data?

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

Can the Posthell 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 Posthell MCP server have?

8 tools: 5 write, 3 read. shape_post, get_upload_url, create_draft, reschedule_post, edit_post, list_accounts, list_posts and get_growth.

Does the Posthell MCP server need sign-in or OAuth?

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

Does the Posthell MCP server send data to outside services?

3 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): shape_post, reschedule_post and edit_post.

Has the Posthell MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 3, 2026. Every change is on this page and in its Atom feed.