How to connect Storyblok to Hermes Agent

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.

Reconnect Storyblok from the dashboard, then start a fresh chat if the runtime still has the old tool catalog loaded.

Storyblok 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 Storyblok 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.

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.

The causes ChatGPT keeps quoting from this page are the right map, in order. Space access: the connected account must be a member of the space the content lives in, and a story in another space fails as a permission error rather than not-found. Placeholder ID: an id like YOUR_ID or an example story id from documentation fails exactly the same way, because the call targets an object outside the connected scope. Stale session: a connection that has been idle or superseded can reject calls while the dashboard still shows it as connected, and the fix is a fresh reconnect from the dashboard. Storyblok roles also factor in: read-only roles reject writes to stories and datasources.

Ask the agent to diagnose it:

Call storyblok_fetch_content_type_items_graphql for the space and content type you were using. Tell me the exact error body from the failed call and which id it mentioned. Do not retry it yet.

The engine-taught causes for this error are Storyblok's discovery flow and client cache clearing, local-server problems this setup does not have. Here a missing tool is almost always the lazy-schema timing case: schemas load on demand, so the first Storyblok call in a fresh session can arrive before the catalog and needs one retry. If tools stay missing after that, the pairing is the suspect: confirm the plugin was installed with --enable, both hermes clawlink begin and hermes clawlink finish ran, and Storyblok shows as connected in the dashboard.

Ask the agent to diagnose it:

List the Storyblok tools you actually have access to. If there are none, say so plainly. If there are, tell me which one fetches content items and use that exact name.

Storyblok rate-limits its APIs by plan, with the management and GraphQL surfaces having different allowances, and an agent walking every content type, then every story, one call at a time, is the traffic shape that meets them. The integration ships a tool for this: storyblok_get_graphql_rate_limit reads the GraphQL API's current rate limit and max cost per request, so the agent can check its allowance before a heavy crawl instead of guessing. Shape the work around it: one content type at a time, paginated, and pause when the limit reports are tight.

Ask the agent to diagnose it:

Call storyblok_get_graphql_rate_limit and tell me the current limit and cost allowance. Do not run a crawl until we know the headroom.

Double-check that the API key for Storyblok has the right scopes or account access. A valid key can still be too limited for some reads or writes.

Yes. ClawLink is the fastest way to connect Hermes to Storyblok: link your Storyblok account once in the browser and Hermes Agent can call the Storyblok API through 10 ready-made tools — no custom code or token handling.

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 Storyblok in the dashboard and Hermes can use it from the next message — no config files, and the Storyblok key you paste is stored server-side instead of in your environment.

About two minutes. Sign in, click Connect next to Storyblok in the dashboard, authenticate, and Hermes Agent can use it from the next chat message.

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 Storyblok working from chat.

The manual route search results teach is a Storyblok PAT: My Account, then Personal access tokens, then generating one with the right scopes and space restrictions. Storyblok is also tightening the older token model, retiring unscoped tokens in favour of scoped ones, which is exactly the maintenance this setup removes. Here a Storyblok credential is pasted once into the dashboard and held server-side, and the scope question becomes a setup decision you make once rather than a token you re-audit. The credential still exists, the point is who manages it and where it lives.

Everything here is content operations over GraphQL: fetch stories and content items for a content type with filtering and pagination, get a single page item by id or slug in draft or published version, query page items by path prefix or slug exclusion, retrieve the navigation links with their published status, read datasource entries, and list tags. There is no visual editor tool and no asset management, so think of the agent as the content API in front of your prompts: draft previews, link audits, navigation checks, and content-type reviews. The writes to be deliberate about are the ones that change published content, and the confirmation gate covers them.

Storyblok's official MCP server and its search and describe and execute discovery flow is what the engines teach for the tool-not-found shape, and it is a real product. This integration is the hosted version of the same idea: no server process to install, no client discovery cache to clear, and the 10 tools appear in chat through the plugin pairing. The engine-taught fixes for missing tools, clearing a client cache or re-registering a server, do not exist here because there is no client-side server.

The AI Overview for the "without api key" shape says an agent cannot interact with your workspace completely keyless, but you can shift the responsibility for managing keys away from your agent code, and it teaches that shift through MCP and integration platforms. That is exactly this setup: the credential is held server-side by ClawLink, the agent never sees it, and the shift is done. The nuance from that answer applies here too, a credential still exists somewhere, it just is not on your machine and it is not managed per session.

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.