Social Media MCP Server for Publishing With Human Control

What Does It Cost to Start?

Postdom’s permanent Free plan includes one connected account and 10 successful destination-publishes per month. New workspaces start with a 14-day complimentary Growth trial without a card; without a paid subscription or another qualifying entitlement, the workspace falls back to Free after the trial.

Paid self-serve plans start at $49 per workspace per month with monthly billing. Their publishing overage is $0.20 per successful destination-publish above the plan allowance; Free stops at its cap. One video successfully published to three destinations uses three units. Your external AI agent or model provider may charge separately. Your own agent does not spend Postdom Chat’s AI-action allowance.

How Do I Connect My Agent?

Choose the connection your client supports. A local stdio server runs on your computer; a remote HTTP connector runs against a hosted endpoint. An operating prompt does not create either connection.

Choose your path: Claude Code, Codex CLI and Cursor can launch a local MCP server. ChatGPT needs a supported remote connection; its project instructions cannot run the local command. Claude Desktop has separate local configuration, while claude.ai uses a remote connector. Client eligibility and authentication must be checked in that client.

Do not use /mcp as POSTDOM_API_URL: the local helper’s REST base is https://api.postdom.com/v1. For a remote connection, use your client’s supported connector setup and inspect its actual tool list. Do not paste a key into chat or assume that an OAuth prompt proves the connection completed.

1. Have a Human Prepare the Workspace

   Create your Postdom workspace. Open Social accounts to authorize the account you own or manage, then open Agents to configure your agent connection. For the local package, have an owner or admin choose Advanced: Use a workspace key → Create agent key under Connect → Agents. Keep the key in private client settings or a protected environment. Never put it in chat, an operating brief or a repository.

2. Configure the MCP Connection

   The local package is @postdom/mcp@0.4.0 and requires Node.js 22 or newer. A client that can launch a local stdio MCP server runs the command below. Its settings format varies by client: follow the dedicated Claude Code, Codex or Cursor setup guide.

   {
     "mcpServers": {
       "postdom": {
         "command": "npx",
         "args": [
           "-y",
           "@postdom/mcp@0.4.0"
         ],
         "env": {
           "POSTDOM_API_KEY": "REPLACE_IN_PRIVATE_CLIENT_SETTINGS"
         }
       }
     }
   }

   The package defaults to https://api.postdom.com/v1. The example omits an API URL override. Check your client’s connection status and confirm the expected 14 tools for this pinned release before asking it to act. The current source contract has 15; do not mistake that for the inventory of the older published package.

   Claude Code’s MCP setup reference explains its local-server settings. This is setup guidance, not a claim that we tested your editor, account authorization or a live publish.

3. Add the Operating Instructions Separately

   AGENTS.md, CLAUDE.md and Cursor’s .cursor/rules/postdom.mdc describe how the agent should work. They are not the MCP connection settings. Add the brief below only after the connection works. ChatGPT project instructions alone cannot launch this local server; Postdom and ChatGPT covers what the brief does there and what it does not.

The linked Codex and Cursor guides distinguish the pinned release from current source. Their client-specific configuration is a separate reference, not evidence of authenticated access or a completed provider publication.

Which Tools Are in the Released Package?

Checked 21 September 2026: @postdom/mcp@0.4.0 exposed 14 tools in a real local stdio discovery test. The current source contract also contains list_posts; this pinned release does not. Use get_publish with a known post ID rather than asking this package to list the queue.

For the evolving current contract and its separate transport status, use the availability reference. Do not assume local package, source and hosted endpoint versions are interchangeable.

First Run: Submit a Finished Demo for Review

Use a YouTube account for this example. A human explicitly selects L1 Post review before the agent submits anything. Do not assume that L1 is the account default. Confirm the account’s current policy and the exact caption, media and audience together.

Use only the Postdom connection I configured. Do not print credentials.
Read get_workspace_status, list_accounts and get_brief first. Stop if the workspace is paused, connections are locked, the account is disconnected, or policy is unclear.
I will explicitly set the selected account to L1 Post review before this request. Confirm the returned policy; do not assume a new account starts in L1.
Use only my selected providerAccountId and the finished video I supply. Show me the caption, account and all MCP defaults before submitting. Do not generate or upload a replacement video.
YouTube sends visibility: private, madeForKids: false and containsSyntheticMedia: true; its title comes from the caption's first line. TikTok sends privacy_level: SELF_ONLY, video_made_with_ai: true, content_preview_confirmed: true, express_consent_given: true, and allow_comment, allow_duet and allow_stitch: false. Instagram sends contentType: reel and isAiGenerated: true, with no equivalent private default. LinkedIn is sent no settings at all: the Posts API requires a visibility value, so the publishing provider chooses one on the account's behalf, and Postdom neither chooses nor reads it. LinkedIn exposes no AI-disclosure field, so no disclosure is sent for it. Facebook is sent contentType: reel and nothing else, and exposes no AI-disclosure field on this path. X, Snapchat and Threads are sent no settings at all and expose no AI-disclosure field either; Snapchat additionally requires a Public Profile on the account before it can publish, Threads takes its audience from whether the profile is public or private rather than from anything sent with the post, and Bluesky posts are public because the post record has no visibility field at all.
These are submitted assertions, not evidence that human preview or consent happened. Require my actual preview of the supplied video and express consent before a TikTok request. Ask me to confirm that the audience and AI-disclosure settings truthfully fit this video for every selected destination. Stop if confirmation is absent or a setting is incompatible; the tool exposes no overrides for these settings. Do not infer consent from permission to call a tool.
After I authorize submission, call publish_video once with those exact inputs and a stable idempotency_key. Submission is not my approval to publish.
If the result requires approval, return its post ID and stop for human review. Never approve it yourself or change policy.
After human approval, use get_publish to check the same post ID. Use bounded backoff, and hand me the ID if my agreed waiting budget expires. Report each destination’s result; never call partial success complete.
Read get_performance only when appropriate. Preserve missing snapshots, null values and availability reasons. Do not resubmit or widen the audience without fresh human direction.

Read Before You Write

get_workspace_status({})
list_accounts({})
get_brief({})

Stop if connections are locked, the workspace is paused or the chosen account is not connected. If authorization is needed, connect_account can start a handoff, but a human completes the social login. Do not claim success until the account appears in list_accounts.

{
  "id": "internal-example-id",
  "providerAccountId": "example-youtube-account",
  "platform": "youtube",
  "handle": "example-channel",
  "status": "connected"
}

Use providerAccountId in account_ids, not the separate internal id. Keep the returned brief and follow its brand guidance. Ask the human before changing the selected account or supplied video.

Submit the Agreed Request Once

Check before copying: this YouTube example uses private visibility, not-made-for-kids and synthetic-media declarations with no helper overrides. A human must confirm those defaults truthfully fit the video. For TikTok, actual human preview and express consent are required; the tool’s fixed flags do not establish either. Stop if confirmation is missing or any default conflicts. Post approval and tool-call permission are separate from consent.

publish_video({
  "account_ids": [
    "example-youtube-account"
  ],
  "video_url": "https://media.example.test/approved-demo.mp4",
  "caption": "A closer look at the demo\nThe finished walkthrough, reviewed by our team.",
  "intent": "Request human review of this supplied demo for the selected YouTube account",
  "idempotency_key": "demo-review-request-001"
})

The example URL is a placeholder, not a working video. For a stored handle, replace video_url with media_handle; supply exactly one. Omitted publish_at means this example does not request a future slot. For scheduling, agree the time with the human and supply its UTC timestamp; approval must still happen in time.

{
  "id": "11111111-1111-4111-8111-111111111111",
  "status": "requires_approval",
  "message": "No provider request was made. Approve this exact immutable request."
}

Keep the returned post ID and hand it to the human. requires_approval means the request needs review; it is not a published video. The human reviews the exact immutable post through Postdom’s human approval workflow. Granting an agent permission to call a tool is not the same as approving the post.

Read the Same Post After Human Approval

get_publish({ "post_id": "11111111-1111-4111-8111-111111111111" })
// Once publication has an outcome:
get_performance({ "post_id": "11111111-1111-4111-8111-111111111111" })

Agree a waiting budget and use bounded backoff for status reads. Return the ID and current state if that budget ends. A stable idempotency_key identifies the original request; do not replace it to work around a pending response or reuse it for changed content. After an uncertain response, reconcile the original request before creating another.

Verification scope: the released package’s local stdio startup, tool discovery and one upload_media reservation call were exercised against a local fixture API. The publishing example is separately checked against the current source client with mocked responses, not a publish call through the released package. No real workspace, OAuth login, provider upload or authenticated publication was performed. Responses here are illustrative excerpts, not real analytics or publication evidence.

Questions Before Connecting

Give Your Agent a Reviewed First Task

Prepare the finished video, choose the account and set its review policy. Then configure the connection and adapt the first-run brief above.

Implementation sources: released MCP package, released MCP code: arguments and destination defaults, run outcomes. Use the pinned version above; package README examples can lag the release. Local protocol evidence and current service capabilities are identified separately on this page.