# io.github.postmcp/postmcp-mcp-server (npm · @postmcpai/server)

Publish and schedule posts to LinkedIn, X, Facebook, Instagram, Threads, Bluesky and YouTube Shorts.

- Trust score: 76/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- npm · `@postmcpai/server`: 76/100 (this document), [markdown](https://verifymcp.io/servers/postmcp-postmcp-mcp-server/postmcpai-server.md), [page](https://verifymcp.io/servers/postmcp-postmcp-mcp-server/postmcpai-server)

## Channel facts

- Registry: `npm`
- Package: `@postmcpai/server`
- Version: `1.0.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-20.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 31 of 96 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 17 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 73/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2653 tokens (~165/item across 16 items; 16 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 60/100
  - Stability observed for 18 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "publish_post_now" implies "publish" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the io.github.postmcp/postmcp-mcp-server server?

io.github.postmcp/postmcp-mcp-server runs locally as an npm package, launched with npx -y @postmcpai/server. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add postmcp-postmcp-mcp-server -- npx -y @postmcpai/server
```

### Cursor

```json
{
  "mcpServers": {
    "postmcp-postmcp-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@postmcpai/server"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "postmcp-postmcp-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@postmcpai/server"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add postmcp-postmcp-mcp-server -- npx -y @postmcpai/server
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "postmcp-postmcp-mcp-server": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@postmcpai/server"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add postmcp-postmcp-mcp-server --command npx --arg -y --arg @postmcpai/server
```

### Hermes

```yaml
mcp_servers:
  postmcp-postmcp-mcp-server:
    command: "npx"
    args: ["-y", "@postmcpai/server"]
```

### Netclaw

```json
{
  "McpServers": {
    "postmcp-postmcp-mcp-server": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@postmcpai/server"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add postmcp-postmcp-mcp-server -t stdio -c npx -a -y @postmcpai/server
```

### Other

```json
{
  "mcpServers": {
    "postmcp-postmcp-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@postmcpai/server"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-19 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-16 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-14 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-12 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-10 (score 72, +4)

- [functional improvement] Stability: unverified → 0.27

### 2026-09-03 (score 68, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-09-02 (score 53)

First indexed and scored.

## MCP tools (16)

### `get_user_info` (~83 tokens)

Retrieve details of the logged-in user including subscription plan, credit balance, AI token count, the active workspace, and the caller's role in it.

Input parameters:

- `workspaceId` (string): Workspace (project) id to act on, from list_workspaces. Omit to use the caller's default workspace. Always pass this when the user belongs to more than one workspace.

### `list_workspaces` (~58 tokens)

List every workspace (project) the user belongs to, with the id to pass as workspaceId, the caller's role, and which one is the default. Call this first whenever the user mentions a client, brand, or workspace by name.

### `get_connected_accounts` (~91 tokens)

List every connected social profile in the workspace with the profileId needed to target it. Call this before creating a post so the post reaches the intended profile rather than every account on a platform.

Input parameters:

- `workspaceId` (string): Workspace (project) id to act on, from list_workspaces. Omit to use the caller's default workspace. Always pass this when the user belongs to more than one workspace.

### `get_account_health` (~95 tokens)

Report connections whose access token has expired or is about to, and which therefore need the user to reconnect. Check this before scheduling anything far out - a post scheduled onto a dead connection fails silently at publish time.

Input parameters:

- `workspaceId` (string): Workspace (project) id to act on, from list_workspaces. Omit to use the caller's default workspace. Always pass this when the user belongs to more than one workspace.

### `list_brandings` (~94 tokens)

List the workspace's brand kits: tone of voice, audience, keywords, and reference style images. Use one to keep drafted copy on-brand, and pass its id to generate_image for on-brand visuals.

Input parameters:

- `workspaceId` (string): Workspace (project) id to act on, from list_workspaces. Omit to use the caller's default workspace. Always pass this when the user belongs to more than one workspace.

### `list_posts` (~178 tokens)

Retrieve scheduled, published, draft, and failed posts, newest first, with per-profile delivery status. Every profile that received a post carries `url`, the link to the live copy - give the user that link when they ask where a post went. Returns pagination plus counts per status.

Input parameters:

- `all` (boolean): Return every matching post in one response, ignoring pagination.
- `limit` (number): Posts per page. Defaults to 9 on the backend.
- `page` (number): 1-based page number. Defaults to 1.
- `status` (string): Only return posts in this state. Defaults to all.
- `workspaceId` (string): Workspace (project) id to act on, from list_workspaces. Omit to use the caller's default workspace. Always pass this when the user belongs to more than one workspace.

### `get_post` (~96 tokens)

Fetch a single post by id, including per-profile delivery status, the live URL of each published copy, and the error for any profile that failed.

Input parameters:

- `id` (string, required): The Database ObjectId of the post.
- `workspaceId` (string): Workspace (project) id to act on, from list_workspaces. Omit to use the caller's default workspace. Always pass this when the user belongs to more than one workspace.

### `preflight_post` (~216 tokens)

Dry-run a post before creating it: checks copy against each platform's character limit, flags profiles that are not connected or need reconnecting, warns when a platform requires media, reports each target's video limit when a video is attached, and reports the credit cost against the workspace balance. Costs nothing and publishes nothing. Run this before create_post whenever the copy is long, carries a link, or targets several platforms.

Input parameters:

- `content` (string, required): The post copy to check.
- `mediaUrl` (string): Media that would be attached, if any. A video URL makes the check report per-platform video limits.
- `platforms` (array): Whole platforms the post would go to, same shape as create_post.
- `targetAccounts` (array): Profiles the post would go to, same shape as create_post.
- `workspaceId` (string): Workspace (project) id to act on, from list_workspaces. Omit to use the caller's default workspace. Always pass this when the user belongs to more than one workspace.

### `create_post` (~516 tokens)

Schedule or immediately publish a post to specific connected social profiles. Prefer targetAccounts so the post lands only on the profiles you name. Every targeted profile becomes its own post with its own id, so each can be edited, retried or cancelled on its own - the response lists them all. With publishImmediately, each delivered profile comes back with a `url` to the live copy; pass those on to the user.

Input parameters:

- `content` (string, required): The text body / commentary of the post. Used for any profile that does not carry its own content. On YouTube the first line becomes the Short's title (cut at 100 characters) and the whole body become…
- `mediaUrl` (string): Optional public URL of an image/video to attach. Use the mediaUrl returned by generate_image to attach a generated image. Video is uploaded natively to every platform, but each has its own ceiling -…
- `platforms` (array): Whole platforms to post to. Every connected profile on each platform listed here receives the post - use targetAccounts instead unless that fan-out is what you want.
- `publishImmediately` (boolean): If true, publishes immediately. Otherwise schedules for later.
- `scheduleDate` (string): Schedule date in YYYY-MM-DD format (required if publishImmediately is false).
- `scheduleTime` (string): Schedule time in 24-hour HH:MM format (required if publishImmediately is false).
- `targetAccounts` (array): The profiles to post to, each with platform and the profileId from get_connected_accounts. Only these profiles receive the post.
- `timezone` (string): IANA timezone the schedule above is expressed in, e.g. "Asia/Kolkata". Defaults to UTC on the server, so pass the user's own zone whenever a wall-clock time matters.
- `variants` (object): Per-platform copy, keyed by platform name (or "platform:profileId" for one profile), e.g. { "twitter": "short punchy version", "linkedin": "longer version" }. Overrides content for those destinations.
- `workspaceId` (string): Workspace (project) id to act on, from list_workspaces. Omit to use the caller's default workspace. Always pass this when the user belongs to more than one workspace.

### `publish_post_now` (~128 tokens)

Broadcast an existing scheduled post immediately to its platforms. Also the way to retry a failed post: profiles that already received it are skipped, so only the stragglers go out. The returned post carries a `url` per delivered profile - report those links rather than only saying it published.

Input parameters:

- `id` (string, required): The Database ObjectId of the post to publish.
- `workspaceId` (string): Workspace (project) id to act on, from list_workspaces. Omit to use the caller's default workspace. Always pass this when the user belongs to more than one workspace.

### `delete_post` (~80 tokens)

Cancel and delete a scheduled or failed post from the database.

Input parameters:

- `id` (string, required): The Database ObjectId of the post to delete.
- `workspaceId` (string): Workspace (project) id to act on, from list_workspaces. Omit to use the caller's default workspace. Always pass this when the user belongs to more than one workspace.

### `update_post` (~270 tokens)

Update the fields (content, target profiles, schedule date/time) of an existing post. To move a post to a different slot without touching anything else, use reschedule_post.

Input parameters:

- `content` (string): Updated text body of the post.
- `id` (string, required): The Database ObjectId of the post to update.
- `mediaUrl` (string): Replacement media URL to attach.
- `platforms` (array): Replacement platform list; each platform expands to all of its connected profiles.
- `scheduleDate` (string): Updated schedule date in YYYY-MM-DD format.
- `scheduleTime` (string): Updated schedule time in HH:MM format.
- `status` (string): Reset status of the post.
- `targetAccounts` (array): Replacement profile list, each with platform and profileId. Supplying this re-points the post at exactly these profiles.
- `timezone` (string): IANA timezone the schedule above is expressed in, e.g. "Asia/Kolkata". Defaults to UTC on the server, so pass the user's own zone whenever a wall-clock time matters.
- `workspaceId` (string): Workspace (project) id to act on, from list_workspaces. Omit to use the caller's default workspace. Always pass this when the user belongs to more than one workspace.

### `reschedule_post` (~197 tokens)

Move a post to a different date and time, keeping its copy and target profiles. A failed or draft post is re-armed by this and will go out at the new slot; profiles that already received it are not sent to again. Published posts and posts currently publishing cannot be moved.

Input parameters:

- `id` (string, required): The Database ObjectId of the post to move.
- `scheduleDate` (string, required): New date in YYYY-MM-DD format.
- `scheduleTime` (string, required): New time in 24-hour HH:MM format.
- `timezone` (string): IANA timezone the new slot is expressed in, e.g. "Asia/Kolkata". Omit to keep the zone the post was scheduled in.
- `workspaceId` (string): Workspace (project) id to act on, from list_workspaces. Omit to use the caller's default workspace. Always pass this when the user belongs to more than one workspace.

### `reset_stuck_post` (~165 tokens)

Release a post left stuck mid-publish so it can be retried. Profiles that already went out keep their delivered state, so retrying afterwards will not double-post. Only use this on a post whose status is 'processing'; if it started publishing recently the call is refused unless force is true.

Input parameters:

- `force` (boolean): Reset even if the post may still be publishing. Only set this after the user confirms - a run that is genuinely in flight can then deliver twice.
- `id` (string, required): The Database ObjectId of the stuck post.
- `workspaceId` (string): Workspace (project) id to act on, from list_workspaces. Omit to use the caller's default workspace. Always pass this when the user belongs to more than one workspace.

### `generate_image` (~170 tokens)

Generate an image for a post from a text prompt and return its hosted URL, ready to pass to create_post as mediaUrl. Pass a brandingId from list_brandings to match the workspace's visual style. Spends AI tokens.

Input parameters:

- `brandingId` (string): Brand kit id from list_brandings, whose reference image steers the visual style.
- `prompt` (string, required): What the image should show. Be specific about subject, composition, and mood.
- `styleImageUrl` (string): Public URL of a reference image to steer style directly, instead of a brand kit.
- `workspaceId` (string): Workspace (project) id to act on, from list_workspaces. Omit to use the caller's default workspace. Always pass this when the user belongs to more than one workspace.

### `multicall` (~216 tokens)

Run several PostMCP tools in one request, in the order given. Use it whenever a task needs more than one call - scheduling a week of posts, checking accounts then publishing, or cancelling a handful of posts - instead of one round trip per call. Calls run sequentially and every tool name is validated before anything executes, so a typo cannot leave half a batch written. Cannot nest: a call inside a batch may not itself be multicall.

Input parameters:

- `calls` (array, required): The calls to run, in order. Between 1 and 20.
- `stopOnError` (boolean): Stop the batch at the first failing call and skip the rest (default true). Set false to attempt every call regardless - right for independent work like cancelling several posts, wrong when a later ca…
- `workspaceId` (string): Workspace (project) id to act on, from list_workspaces. Omit to use the caller's default workspace. Always pass this when the user belongs to more than one workspace.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/postmcp-postmcp-mcp-server/postmcpai-server#diagnostics

## Score history

- 2026-09-20: 76
- 2026-09-19: 76
- 2026-09-18: 75
- 2026-09-17: 75
- 2026-09-16: 75
- 2026-09-15: 74
- 2026-09-14: 74
- 2026-09-13: 73
- 2026-09-12: 73
- 2026-09-11: 72
- 2026-09-10: 72
- 2026-09-09: 68
- 2026-09-08: 68
- 2026-09-07: 68
- 2026-09-06: 68
- 2026-09-05: 68
- 2026-09-04: 68
- 2026-09-03: 68
- 2026-09-02: 53

## Common questions

### What is the io.github.postmcp/postmcp-mcp-server server?

io.github.postmcp/postmcp-mcp-server is listed in the public MCP registry as io.github.postmcp/postmcp-mcp-server. Publish and schedule posts to LinkedIn, X, Facebook, Instagram, Threads, Bluesky and YouTube Shorts. This page covers its npm package (@postmcpai/server).

### Is the io.github.postmcp/postmcp-mcp-server server safe to use?

io.github.postmcp/postmcp-mcp-server scores 76 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the io.github.postmcp/postmcp-mcp-server server expose?

io.github.postmcp/postmcp-mcp-server exposes 16 tools: get_user_info, list_workspaces, get_connected_accounts, get_account_health, list_brandings, and 11 more. Their descriptions and schemas cost roughly 2,653 tokens of context every time the server is loaded.

### Is the io.github.postmcp/postmcp-mcp-server server still maintained?

io.github.postmcp/postmcp-mcp-server is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the io.github.postmcp/postmcp-mcp-server server under?

io.github.postmcp/postmcp-mcp-server declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/@postmcpai/server
- Socket report: https://socket.dev/npm/package/@postmcpai/server
- Repository: https://github.com/postmcp/postmcp-mcp-server
- Website: https://postmcpai.com/mcp-server
- Changelog RSS feed: https://verifymcp.io/servers/postmcp-postmcp-mcp-server/postmcpai-server.xml
- Changelog JSON feed: https://verifymcp.io/servers/postmcp-postmcp-mcp-server/postmcpai-server.json
- HTML version of this page: https://verifymcp.io/servers/postmcp-postmcp-mcp-server/postmcpai-server