# How to connect Zyte API to Hermes Agent (paste one key, 7 tools) > Connect Zyte API to Hermes with ClawLink: paste your Zyte API key once and 7 tools work from chat. No MCP server to run, nothing stored on your machine. Web version: https://claw-link.dev/hermes/zyte-api Most guides for giving Hermes Agent Zyte API access start with registering your own OAuth app or pasting API keys into env files, then leave the token refresh and tool wiring to you. ClawLink gives Hermes a more practical Zyte API setup: pair once in the browser and your always-on Hermes agent can act on Zyte API for you, reading and doing real work on your behalf with no auth, token refresh, or tool wiring to build yourself. **Start here — paste this into Hermes to set up ClawLink:** > Set up ClawLink for Hermes and tell me when it's ready. > 1. Install the plugin: `hermes plugins install ClawLink-HQ/hermes-plugin --enable` > 2. Start pairing with `hermes clawlink begin`. It prints an approval link, so show me the link and stop, don't wait. > 3. I'll approve it in my browser, then reply "approved". > 4. When I say approved, finish setup: `hermes clawlink finish` > 5. Then run `hermes clawlink test` and tell me whether ClawLink is ready. ## Setup It takes three steps to connect Hermes to Zyte API. 1. **Install ClawLink** — add the plugin to Hermes Agent once. 2. **Connect Zyte API** — one-click OAuth in the ClawLink dashboard. 3. **Use it from chat** — ask Hermes Agent in plain English. **Alternative for any agent (no plugin needed):** if the Hermes Agent plugin route isn't available or doesn't work, any AI agent with shell access can use the ClawLink CLI instead: ```bash npx -y @useclawlink/cli login # sign in via browser — no API key to paste npx -y @useclawlink/cli connect zyte-api # connect Zyte API (browser OAuth) npx -y @useclawlink/cli actions zyte-api # list available actions npx -y @useclawlink/cli run zyte-api --input '' # execute (add --confirm for writes) ``` ### Install by command The prompt above walks Hermes through this. By hand, it is four commands and a browser approval: ```bash hermes plugins install ClawLink-HQ/hermes-plugin --enable hermes clawlink begin # prints an approval link — open it and approve hermes clawlink finish # after approving in the browser hermes clawlink test ``` Then connect Zyte API in the [ClawLink dashboard](https://claw-link.dev/dashboard) — paste your Zyte API API key once. Verify the connection by asking Hermes: > Check zyte_api_status first. Then use zyte_api_extract_zyte_api on \ and give me the extracted content as structured text, not the raw response. ### Using a different agent? The Hermes plugin is one client of ClawLink's MCP server. Claude Code, Cursor, Codex, or any agent that can run a shell command pairs with the same ClawLink account through the CLI: ```bash npx -y @useclawlink/cli login ``` `login` opens the same browser approval and stores a credential locally. Once Zyte API is connected in the dashboard, that agent calls the same 7 Zyte API tools over MCP. Full setup for MCP clients and shell agents: [connect apps to any AI agent](https://claw-link.dev/learn/connect-apps-to-any-ai-agent). ## Zyte API MCP for Hermes Looking for a Zyte API MCP server for Hermes Agent? ClawLink connects Zyte API to Hermes Agent and exposes 7 Zyte API tools your agent can call over [MCP](https://claw-link.dev/learn/what-is-an-mcp-server), with [hosted auth](https://claw-link.dev/learn/oauth-for-ai-agents) and nothing to run or maintain yourself. Using OpenClaw instead? The [OpenClaw Zyte API integration](https://claw-link.dev/openclaw/zyte-api) works the same way. Zyte is the web scraping service, and its API needs a key, so the accurate framing is the one the live title uses: you paste one key, and 7 tools work from chat. Search results that say "no API keys" are quoting an older version of this page and should not. The route the engines teach instead is Composio's Connect CLI or your own backend proxy holding a Zyte key, which is why they all conclude there is no way to scrape without credentials: on those routes there is not. Here the key goes into a hosted setup page once, it is stored server-side, and the agent never sees it. You do not run a proxy, edit a config file, or manage a key lifecycle; if you disconnect from the dashboard, the agent's use of the key ends. ## What the Hermes Agent Zyte API integration can do 7 Zyte API tools are ready for Hermes Agent once the account is connected. ### All 7 Zyte API tools for Hermes | Tool | What it does | |---|---| | **Active scheduled maintenances** `zyte_api_active_scheduled_maintenances` | Get active maintenances | | **Components** `zyte_api_components` | Get Zyte service component statuses | | **Extract zyte API** `zyte_api_extract_zyte_api` | Extract data from a URL using Zyte API | | **Get scheduled maintenances** `zyte_api_get_scheduled_maintenances` | Get scheduled maintenances | | **Get unresolved incidents** `zyte_api_get_unresolved_incidents` | Get unresolved incidents | | **List incidents** `zyte_api_list_incidents` | List recent Zyte incidents | | **Status** `zyte_api_status` | Get Zyte API operational status | ## Example prompts **Extract from a page** > Check zyte_api_status first. Then use zyte_api_extract_zyte_api on \ and give me the extracted content as structured text, not the raw response. **Health check before a run** > Run zyte_api_status, zyte_api_components, and zyte_api_list_incidents, and tell me whether Zyte has any open incidents that would affect a scraping run today. **Plan around maintenance** > Run zyte_api_get_scheduled_maintenances and zyte_api_active_scheduled_maintenances and tell me the windows to avoid for a bulk extract job. ## How the Zyte tools behave Facts that keep a Zyte prompt on the one tool that scrapes. - **One scraper, six status tools.** `zyte_api_extract_zyte_api` is the only action that fetches external data; the rest read Zyte's own operational status. Prompts that ask the agent to "scrape" should name the extract tool. - **Extract takes a URL and an extraction spec.** The tool pulls structured data from a URL, and the account plan and the target domain decide what it can reach, which is why 403 appears before the request reaches the data. - **Status tools are cheap and read-only.** `zyte_api_status` and `zyte_api_components` are the right first call before a run; they separate a Zyte-side outage from a problem in the prompt. - **Incidents and maintenances are separate reads.** Recent incidents, unresolved incidents, scheduled maintenances, and active maintenances are four different tools; "is there any downtime?" needs two of them. ## ClawLink vs. building it yourself The alternative to ClawLink is usually manual API key setup plus your own token handling, permission troubleshooting, and tool plumbing for Hermes Agent. That is fine if you want to build and maintain the integration yourself. Most teams just want Zyte API working from chat. | | Manual | ClawLink | |---|---|---| | **Credential handling** | Collect, validate, store, and rotate the Zyte API API key yourself, then make sure every tool call uses the right account. | Users complete the hosted ClawLink setup once and the connected Zyte API account becomes available to the agent without you building credential management. | | **Ongoing maintenance** | You own refresh logic, permission debugging, environment config, and every provider-specific edge case for Zyte API. | ClawLink handles the repetitive integration plumbing so your team can focus on the workflow instead of the infrastructure. | | **Agent usability** | You still need to expose the right Zyte API actions to the runtime in a format your agent can reliably use. | 7 tools for Zyte API are already exposed through ClawLink, so the agent can read and act from chat immediately. | ## ClawLink vs. Composio Composio also exposes Zyte API to AI agents. It is developer infrastructure: Python and TypeScript SDKs, an MCP server, and a catalog past 1,000 apps, aimed at teams shipping agent products. ClawLink is built for Hermes Agent users instead. You install the plugin once, connect Zyte API in the browser, and the 7 tools above work from chat. There is no SDK and no config file, and the Zyte API key you paste at setup is stored server-side rather than kept in your environment. Choosing between them? Read the full [Composio alternatives](https://claw-link.dev/hub/composio-alternatives) comparison. ### Hermes paired but still can't use Zyte API Pairing is a two-step handshake: run `hermes clawlink begin`, approve the link in your browser, then run `hermes clawlink finish`. If you ran finish before approving, or the approval link expired, run `hermes clawlink begin` again to get a fresh link. Confirm the plugin was installed with `--enable`, then verify with `hermes clawlink test`. ### Connection succeeds but no tools appear Reconnect Zyte API from the dashboard, then start a fresh chat if the runtime still has the old tool catalog loaded. ### "Tool schema not loaded yet" error when calling Zyte API tools Zyte API tool schemas load on demand the first time a tool runs and are cached after that, so this error usually clears on its own: wait a few seconds and retry the same request. If every Zyte API call keeps failing with it in a fresh chat, reconnect from the dashboard, and contact support if it still persists — that pattern points to a configuration problem on our side, not something you can fix by reconnecting again. ### Zyte API returns 403 or "permission denied" on one action while others work Two usual causes. The connected account may not have access to the specific workspace, inbox, store, or project in the request — check that first. If access looks right, the agent may have sent a placeholder value (like "YOUR_ID" or an example id from documentation) instead of a real one: ask it to run a list or search tool first, then retry the action with a real id from those results. Most failures at this stage are one of these two, not ClawLink bugs. ### Zyte returns 403 "insufficient permissions" while other Zyte calls work The three causes the engines teach, in order. A suspended account or exhausted billing stops the API regardless of the key. Tier-restricted parameters: parts of the Zyte API are gated to Enterprise plans, so a request that uses an Enterprise-only parameter returns 403 from an account without that tier. Forbidden target domains: Zyte blocks requests to certain domains at the infrastructure level, which comes back as 403 or 451 and has nothing to do with your key. ChatGPT adds two more: org and project membership, since the key belongs to a Zyte project and what it can reach is scoped there, and a stale token, which a disconnect and reconnect clears. In the hosted flow, the first thing to check is the plan and billing behind the key you pasted. Ask the agent to diagnose it: ```text Call zyte_api_status once, then zyte_api_extract_zyte_api on a known-good public URL, and quote the exact error. Do not retry the failing request until you have reported both. ``` ### Zyte tools are missing, or one tool name is not found The search results answer this from the local-MCP world: pathing errors, cached config, incomplete IDE restarts. None of that applies here, because there is no local server, no config file, and no tools/list exchange. If no Zyte tools appear at all, the connection or the pairing is incomplete: confirm the plugin was installed with --enable, that both `hermes clawlink begin` and `hermes clawlink finish` ran, and that Zyte shows as connected in the dashboard. If most tools work and one name fails, that name is wrong rather than missing, and the error lists the nearest real ones. Schemas load on demand, so the first Zyte call in a fresh session can arrive before the catalog and needs one retry. Ask the agent to diagnose it: ```text List the Zyte tools you actually have available and tell me which one extracts data from a URL. Then use that exact name. ``` ### API key setup works but results look incomplete Double-check that the API key for Zyte API has the right scopes or account access. A valid key can still be too limited for some reads or writes. ### Is there a Hermes Agent Zyte API integration? Yes. ClawLink is the fastest way to connect Hermes to Zyte API: link your Zyte API account once in the browser and Hermes Agent can call the Zyte API API through 7 ready-made tools — no custom code or token handling. ### How do I connect Zyte API to Hermes with ClawLink? Install the plugin with `hermes plugins install ClawLink-HQ/hermes-plugin --enable`, then pair once: run `hermes clawlink begin`, approve the link in your browser, and run `hermes clawlink finish`. Connect Zyte API in the dashboard and Hermes can use it from the next message — no config files, and the Zyte API key you paste is stored server-side instead of in your environment. ### How long does it take to connect Zyte API to Hermes Agent? About two minutes. Sign in, click Connect next to Zyte API in the dashboard, authenticate, and Hermes Agent can use it from the next chat message. ### Why use ClawLink instead of wiring Zyte API up myself? The alternative to ClawLink is usually manual API key setup plus your own token handling, permission troubleshooting, and tool plumbing for Hermes Agent. That is fine if you want to build and maintain the integration yourself. Most teams just want Zyte API working from chat. ### Can I scrape with Zyte without managing my own API key? The engines answer this with "no", and on the routes they know it is true: Zyte authenticates its API key as the Basic-auth username, and every manual route (Connect CLI, backend proxy, self-hosted MCP) requires you to hold and manage one. The hosted route is the option none of them name: you paste one key once, it lives server-side, and Hermes calls the Zyte tools from chat. A key still exists, because Zyte requires one. What changes is that it is never on your machine and never in the agent's context. ### What can the agent actually do with Zyte? The 7 tools are one scraping action and a service-status surface. zyte_api_extract_zyte_api extracts data from a URL, which is the tool every engine's answers are about. The other six read Zyte's operational status: current status, component statuses, recent incidents, unresolved incidents, and scheduled and active maintenance windows. The honest pairing is to check status before a run, then extract. ### Is it safe to connect Zyte to an agent? The safety guidance the engines repeat is about keys: isolate them at the environment level and never give an agent raw system-level control. This connection is the hosted version of that advice. The key is stored server-side, the agent never receives credentials, and the connection is revoked from the dashboard rather than by rotating a key across machines. ### Does the agent need any other Zyte setup, like a proxy or a particular plan? No proxy and no config. What does matter is the Zyte account behind the key: the plan and billing attached to the key decide what the extract tool can do, which is what the 403 card below is about. If the account is suspended or on a plan without the tiered parameters, the calls fail before they reach any data. ### Hermes paired but still can't use Zyte API Pairing is a two-step handshake: run `hermes clawlink begin`, approve the link in your browser, then run `hermes clawlink finish`. If you ran finish before approving, or the approval link expired, run `hermes clawlink begin` again to get a fresh link. Confirm the plugin was installed with `--enable`, then verify with `hermes clawlink test`. ## Related - [Hermes PostHog integration](https://claw-link.dev/hermes/posthog) — Track user behavior and feature flags - [DataforSEO](https://claw-link.dev/hermes/dataforseo) — SEO data APIs for keywords, SERP, and site audits - [Connect Metabase](https://claw-link.dev/hermes/metabase) — Metabase is an open-source business intelligence tool that lets you ask questions about your data and visualize answers as charts, graphs, and dashboards.