# Send Coupler.io to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - Download the package from Yavira. - Extract it into a folder your agent can access. - Paste one of the prompts below and point your agent at the extracted folder. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "coupler-io", "name": "Coupler.io", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/nika-is-nika/coupler-io", "canonicalUrl": "https://clawhub.ai/nika-is-nika/coupler-io", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/coupler-io", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=coupler-io", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "coupler-io", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-02T03:34:37.322Z", "expiresAt": "2026-05-09T03:34:37.322Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=coupler-io", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=coupler-io", "contentDisposition": "attachment; filename=\"coupler-io-1.1.2.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "coupler-io" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/coupler-io" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/coupler-io", "downloadUrl": "https://openagent3.xyz/downloads/coupler-io", "agentUrl": "https://openagent3.xyz/skills/coupler-io/agent", "manifestUrl": "https://openagent3.xyz/skills/coupler-io/agent.json", "briefUrl": "https://openagent3.xyz/skills/coupler-io/agent.md" } } ``` ## Documentation ### Coupler.io Read-only data access via Coupler.io's MCP server. Author: Coupler.io Team Homepage: coupler.io ### Prerequisites mcporter CLI installed and on PATH Coupler.io account with at least one data flow configured to OpenClaw destination ### Quick Reference mcporter call mcp-coupler-io-mcp.list-dataflows mcporter call mcp-coupler-io-mcp.get-dataflow dataflowId= mcporter call mcp-coupler-io-mcp.get-schema executionId= mcporter call mcp-coupler-io-mcp.get-data executionId= query="SELECT * FROM data LIMIT 10" ### Connection Setup Endpoint verification: This skill connects to auth.coupler.io (OAuth) and mcp.coupler.io (MCP data). These are official Coupler.io endpoints. You can verify them via your Coupler.io account (AI integrations page). Transport: This MCP uses streamable HTTP, not SSE. If you see "SSE error" in output, ignore the misleading label — it's still HTTP. ### 1. Authenticate and add server in one step Do not use mcporter config add followed by mcporter auth separately — this creates a config entry without auth metadata and causes a 401 loop. Instead, do it all in one command: mcporter auth --http-url https://mcp.coupler.io/mcp --persist config/mcporter.json This auto-detects OAuth, opens the browser for Coupler.io login (PKCE flow), and saves the server definition + tokens on success. To re-authenticate or clear stale tokens: mcporter auth --http-url https://mcp.coupler.io/mcp --persist config/mcporter.json --reset ### 2. Ensure "auth": "oauth" is in config After auth, check config/mcporter.json. mcporter won't use cached tokens unless the entry has "auth": "oauth". It should look like: { "mcpServers": { "mcp-coupler-io-mcp": { "baseUrl": "https://mcp.coupler.io/mcp", "auth": "oauth" } } } If "auth": "oauth" is missing, add it manually. ### 3. Verify mcporter list mcp-coupler-io-mcp Should return 4 tools: get-data, get-schema, list-dataflows, get-dataflow. Note: The server name is auto-generated as mcp-coupler-io-mcp from the URL. Use this name in all subsequent commands. ### Token Refresh mcporter handles token refresh automatically on 401 errors. No manual intervention needed. If you need to force a fresh token: mcporter auth mcp-coupler-io-mcp --reset ### list-dataflows List all data flows with OpenClaw destination. mcporter call mcp-coupler-io-mcp.list-dataflows --output json ### get-dataflow Get flow details including lastSuccessfulExecutionId. mcporter call mcp-coupler-io-mcp.get-dataflow dataflowId= --output json ### get-schema Get column definitions. Column names are in columnName (e.g., col_0, col_1). mcporter call mcp-coupler-io-mcp.get-schema executionId= ### get-data Run SQL on flow data. Table is always data. mcporter call mcp-coupler-io-mcp.get-data executionId= query="SELECT col_0, col_1 FROM data WHERE col_2 > 100 LIMIT 50" Always sample first (LIMIT 5) to understand structure before larger queries. ### Typical Workflow # 1. List flows, find ID mcporter call mcp-coupler-io-mcp.list-dataflows --output json # 2. Get execution ID mcporter call mcp-coupler-io-mcp.get-dataflow dataflowId= --output json # 3. Check schema mcporter call mcp-coupler-io-mcp.get-schema executionId= # 4. Query mcporter call mcp-coupler-io-mcp.get-data executionId= query="SELECT * FROM data LIMIT 10" ### Constraints Read-only: cannot modify flows, sources, or data Only flows with OpenClaw destination are visible Tokens expire in 2 hours (mcporter refreshes automatically) ## Trust - Source: tencent - Verification: Indexed source record - Publisher: nika-is-nika - Version: 1.1.2 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-05-02T03:34:37.322Z - Expires at: 2026-05-09T03:34:37.322Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/coupler-io) - [Send to Agent page](https://openagent3.xyz/skills/coupler-io/agent) - [JSON manifest](https://openagent3.xyz/skills/coupler-io/agent.json) - [Markdown brief](https://openagent3.xyz/skills/coupler-io/agent.md) - [Download page](https://openagent3.xyz/downloads/coupler-io)