TikTok Agent Publisher MCP server
Local-first TikTok Content Posting API for AI agents: OAuth checks, dry-run and live uploads.
3 stars99 downloads/wk
Reviews
Write oneNobody has reviewed TikTok Agent Publisher yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
TikTok Agent Publisher tools (6, 2 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
tiktok_agent_manifestMachine-readable install, client, runtime and safety guidance for agents.
tiktok_connection_statusCheck dry-run mode, OAuth readiness and live publish readiness without exposing tokens.
tiktok_list_videosList recent TikTok videos visible to the configured OAuth token.
tiktok_privacy_auditReturn token, media-hosting, local-file and live-publish safety boundaries.
tiktok_publish_statuswrite actionFetch TikTok Content Posting API publish status by publish id.
tiktok_publish_videowrite actionCreate a TikTok video publish job. Dry-run is enabled by default; live mode requires explicit TIKTOK_DRY_RUN=false.
Public scan report
scanner v0.1.10 · 2026-11-10 · same rubric, same numbers if you re-run it
- Code scan15 source files scanned13/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitystatic API keys via environment variables6/15
- Maintenancelast push 8 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Findings (1)
- highShell command built from a string (injection risk)
exec.shell-concatsrc/tools/tiktok-oauth.js: …f (process.platform === 'darwin') { exec(`open "${url}"`); } } if (cmd === 'auth-url') …
How TikTok Agent Publisher compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 65/100
- higher than 20% of 4,456 AI and agents servers
- Tools
- 6
- the typical AI and agents server has 7
- Tools that change things
- 33%
- typical: 3%. Fewer write tools means less an agent can break
- GitHub stars
- 3
- more than 73% of 2,733 AI and agents servers
- Downloads a week
- 99
- more than 61% of 1,712 AI and agents servers with a package
What its tools let an agent do: 4 read · 2 change
Install TikTok Agent Publisher in Claude Code, Cursor or VS Code
Runs npx -y tiktok-agent-publisher on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add tiktok-agent-publisher -- npx -y tiktok-agent-publisher
What the publisher says
From the TikTok Agent Publisher repository's README, as published. We do not edit it. Read it on GitHub
<!-- delx header v2 --> TikTok Agent Publisher
Agent-first TikTok Content Posting API CLI + MCP.Dry-run safe, OAuth readiness checks, structured output for any agent runtime.
⭐ If this agent-first tool helps your workflow, please star the repo. Stars make this tooling easier for other builders to discover and help Delx keep shipping open infrastructure.
🧱 Part of the Delx agent stack — 15 open-source MCP servers across body, reach and coordination.
<!-- /delx header v2 -->
Local-first TikTok Content Posting API tooling for AI agents. It gives Codex, Claude, Cursor, Hermes, OpenClaw and other MCP clients a safe way to check readiness, build OAuth URLs, dry-run publish flows and upload TikTok videos only when live mode is explicitly enabled.
Use it when an agent needs to publish or inspect TikTok content without browser automation, hidden state or token leakage.
Why It Exists
Most social publishing scripts are built for humans at a terminal. Agents need a different contract:
- a manifest that explains install/runtime rules
- a connection status tool before write operations
- privacy boundaries that never return token values
- dry-run by default
- structured JSON outputs for planning, retries and audit trails
This repo packages that contract around TikTok's official Content Posting API.
Install
npm install -g tiktok-agent-publisherOr run without installing:
npm exec --yes --package=tiktok-agent-publisher -- tiktok-agent-publisher doctorFirst Post (Dry-Run) Walkthrough
No TikTok credentials are required to try this. With no .env, dry-run is on by default, so every command below returns structured JSON without touching the live API. This is the exact sequence an agent should follow before its first real post. The outputs are real CLI runs, lightly trimmed.
1. Check readiness. doctor reports mode and what is still missing — never any token values.
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
TikTok Agent Publisher: common questions
- Is TikTok Agent Publisher MCP server safe?
- With care: it is graded C, so read the findings first (65/100). Read the TikTok Agent Publisher safety report
- How do I install TikTok Agent Publisher?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does TikTok Agent Publisher need an API key?
- Yes. The registry entry asks for
TIKTOK_CLIENT_SECRET. - Is TikTok Agent Publisher maintained?
- The last commit was 13 days ago (2026-11-02). The latest release is v0.1.5.
- What can I use instead of TikTok Agent Publisher?
- Servers from other publishers that do the same job: Taisly Social Media Posting MCP server, Basic Memory MCP server and HOL Guard MCP server.
- How does TikTok Agent Publisher compare with other AI and agents MCP servers?
- safety score 65/100 (higher than 20% of 4,456 AI and agents servers); tools 6 (the typical AI and agents server has 7); tools that change things 33% (typical: 3%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to TikTok Agent Publisher
Same job from other publishers: the closest match first, then the best rated.
Taisly Social Media PostingPublish videos to TikTok, Reels, Shorts, X, and Facebook through Taisly.not reviewedEstablishedA- Basic MemoryLocal-first knowledge management with bi-directional LLM sync via Markdown files.not reviewedWidely usedB
- HOL GuardLocal-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.not reviewedEstablishedA
- Agent-Native ChatMinimal chat-first app with durable threads, actions, and the app-agent loopnot reviewedEstablishedA
- haiku.ragLocal-first agentic RAG with citations - hybrid search, reranking, multimodal document retrievalnot reviewedEstablishedA