TweetClaw

Xquik is an independent third-party service. Not affiliated with X Corp. "Twitter" and "X" are trademarks of X Corp.

Search tweets, search tweet replies, post tweets, post tweet replies, export followers, monitor X/Twitter, manage media, send direct messages, and run giveaway draws from OpenClaw.

Use TweetClaw as an OpenClaw tweet scraper and X/Twitter automation plugin. Search tweets, search tweet replies, post tweets, post tweet replies, scrape tweets, run follower export, perform user lookup, handle media upload and media download, send direct messages, monitor tweets, deliver webhooks, and run giveaway draws. Powered by Xquik, the all-in-one X automation platform.

Install

openclaw plugins install clawhub:@xquik/tweetclaw

This command installs TweetClaw from Xquik's verified ClawHub publisher scope. OpenClaw records ClawHub as the tracked update source.

Use openclaw plugins install npm:@xquik/tweetclaw when you need the npm fallback.

For normal upgrades, reuse the tracked install source:

openclaw plugins update tweetclaw

For reproducible production installs, pin a published npm version:

openclaw plugins install npm:@xquik/tweetclaw@<version> --pin

OpenClaw keeps pinned records on the selected version during later plugins update tweetclaw runs. Move back to the default npm release line with openclaw plugins update @xquik/tweetclaw when you want the current stable package again.

Current source metadata targets OpenClaw 2026.7.1 or newer. Update OpenClaw before testing source builds or freshly packed artifacts from this repository.

If your OpenClaw install runs with OPENCLAW_NIX_MODE=1, plugin lifecycle mutators are disabled. Install or update TweetClaw through your Nix OpenClaw source instead of openclaw plugins install or openclaw plugins update.

TweetClaw can be installed before credentials are configured. Until you add an API key or MPP signing key, the free explore catalog remains available and live API calls return setup guidance instead of failing plugin installation.

Agent-skill installers can also discover TweetClaw through Skills.sh. This installs the packaged SKILL.md for agents that use skills directories; use the OpenClaw command above for the plugin runtime.

npx skills add xquik-dev/tweetclaw

TweetClaw is an OpenClaw plugin, not an MCP server. For remote MCP clients, add https://xquik.com/mcp and complete OAuth 2.1. Clients without OAuth can use an Xquik API key as an Authorization: Bearer token. See the Xquik MCP guide.

Note: @xquik/tweetclaw is the canonical npm package. Any other scope (for example @intentsolutionsio/tweetclaw) is a third-party redistribution and may ship stale metadata or outdated endpoint counts.

Pricing

TweetClaw uses Xquik billing for account-backed automation, credit top-ups, and optional MPP pay-per-use reads. See Billing & Pricing for current plans, eligible endpoints, and live prices.

Configure

Option A: API key (account-backed X automation)

Get an API key at dashboard.xquik.com. Store it in an environment variable and configure TweetClaw to use it:

openclaw config set plugins.entries.tweetclaw.config.apiKey "$XQUIK_API_KEY"

Security: Keep the key out of chats, docs, and shell history. Prefer the environment-variable command above so OpenClaw writes the secret to its local config without exposing it in the prompt.

Option B: Credits (pay-per-use, no subscription)

Top up credits from the Xquik dashboard. An API key can spend prepaid credits across 33 public paid-read routes without a subscription. TweetClaw does not create checkout sessions or charge saved payment methods from the agent.

Option C: Direct MPP pay-per-use (no account needed)

Machine Payments Protocol (MPP) lets agents pay 7 direct read routes without an account, API key, or subscription. Create an MPP account with mppx account create. The signing key stays local and signs payment proofs only.

npm i mppx viem
openclaw config set plugins.entries.tweetclaw.config.tempoSigningKey "$MPP_SIGNING_KEY"

Security: Keep the signing key out of chats, docs, and shell history. Prefer the environment-variable command above so OpenClaw writes the secret to its local config without exposing it in the prompt.

The 7 direct MPP routes cover tweet lookup, user lookup, follower check, article lookup, trends, X trends, and community info. See the billing guide for current eligibility and costs.

Other paid reads use an API key with prepaid credits. Media downloads and gallery creation require account-backed access.

Enable the optional action tool

OpenClaw loads explore as the safe catalog tool. The live endpoint invoker, tweetclaw, is registered as an optional tool because it can perform paid reads, private reads, and write actions.

OpenClaw's local onboarding default is often tools.profile: "coding", which excludes external plugin tools from agent runs until they are explicitly allowed. If the agent can see the TweetClaw skill but cannot call the tools, add the tool names to tools.alsoAllow so you keep the normal coding tools and opt into TweetClaw.

openclaw config set tools.alsoAllow '["explore", "tweetclaw"]'

Verify runtime registration after install or update:

openclaw plugins inspect tweetclaw --runtime --json
openclaw skills info tweetclaw

The runtime inspection should show the loaded tweetclaw plugin, the explore tool, the optional tweetclaw tool, the before_tool_call approval hook, and the xtrends command. A managed Gateway with reload enabled can restart automatically after install or update; otherwise run openclaw gateway restart before inspecting live runtime surfaces. Use OPENCLAW_PLUGIN_LIFECYCLE_TRACE=1 openclaw plugins inspect tweetclaw --runtime --json when install or runtime inspection is slow; OpenClaw keeps JSON output parseable while printing lifecycle timing to stderr.

For release-like local checks, pack and install the artifact rather than a repo folder so OpenClaw loads the published dist/index.js entry:

npm pack
openclaw plugins install npm-pack:./xquik-tweetclaw-<version>.tgz
openclaw plugins inspect tweetclaw --runtime --json

Maintainers should run npm run check-openclaw-platform-fitness after npm run build. The gate keeps package metadata, OpenClaw compatibility fields, manifest tool ownership, optional-tool metadata, approval hooks, runtime entries, docs, and the packaged skill aligned.

Optional settings

openclaw config set plugins.entries.tweetclaw.config.baseUrl "https://xquik.com"
openclaw config set plugins.entries.tweetclaw.config.pollingEnabled true
openclaw config set plugins.entries.tweetclaw.config.pollingInterval 60

Only change baseUrl for a self-hosted Xquik-compatible API. TweetClaw requires an HTTPS base URL with no embedded credentials.

OpenClaw Trust Model

TweetClaw uses 2 OpenClaw gates:

• Optional tool exposure: explore is always safe local catalog search, while tweetclaw stays optional until the user allows it with tools.alsoAllow.
• Per-call approval: write-like, private, paid, recurring, extraction, monitor, webhook, and account-scoped calls trigger a plugin approval prompt. TweetClaw offers one-time approval or deny for those calls so a social-account action is reviewed each time.

That shape makes TweetClaw useful for source-backed social workflows without turning an agent into an unattended publisher. Good OpenClaw use cases include searching tweets before a draft, checking tweet replies before a giveaway draw, exporting followers for review, collecting user lookup context, uploading media for an approved post, monitoring tweets after the user creates a monitor, and using webhooks for reviewed follow-up automation.

Tools

TweetClaw uses 2 structured tools for the agent-safe endpoint catalog:

explore (free, no network)

Search the API spec to find endpoints. No API calls are made.

You: "What endpoints are available for tweet composition?"

AI uses explore → filters spec by category "composition"
→ Returns matching endpoints with parameters and response shapes

tweetclaw (invoke API endpoints)

Invoke catalog-listed API endpoints with structured path, method, query, and body fields. Auth is injected automatically - the LLM never sees your API key.

This tool is optional in OpenClaw. If your agent can see the skill but cannot call TweetClaw tools, add explore and tweetclaw to tools.alsoAllow so your normal tool profile stays intact.

OpenClaw approval prompts are enforced before write-like tweetclaw tool calls. Review the structured request before approving any post, delete, follow, DM, monitor, extraction, webhook, or profile-change action. Risky calls offer one-time approval or deny so future social-account actions still require review.

You: "Post a tweet saying 'Hello from TweetClaw!'"

AI uses tweetclaw → finds connected account, posts tweet
→ Returns { tweetId, success: true }

You: "Search tweets about AI agents"

AI uses explore → finds /api/v1/x/tweets/search
AI uses tweetclaw → calls the endpoint with auth
→ Returns tweet results

Commands

Instant responses, no LLM needed:

Event Notifications

When polling is enabled (default), TweetClaw checks for new events every 60 seconds and delivers them to your chat:

• Monitor alerts: New tweets, replies, quotes, retweets from monitored accounts

Set up a monitor first:

You: "Monitor @elonmusk for new tweets, replies, and retweets"

API Coverage

99 agent-callable endpoints across 9 categories. Dashboard-only account-admin, billing, support, and raw credential flows are excluded from the tool catalog and blocked at runtime.

Media download requires account-backed access and is not MPP-eligible.

Links

• Xquik Platform
• API Documentation
• Billing & Pricing
• Context7 Agent Docs
• OpenClaw Setup Guide
• Agent Workflow Guide
• Framework guides: Mastra, CrewAI, LangChain, Pydantic AI, Google ADK, Microsoft Agent Framework, n8n, Zapier, Make, Pipedream, Composio migration
• npm Registry Metadata
• OpenClaw

License

MIT