How to connect Baselinker 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 Baselinker from the dashboard, then start a fresh chat if the runtime still has the old tool catalog loaded.

Baselinker 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 Baselinker 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 engines teach four causes: the token's scope restricts the endpoint, a sub-account restriction on what the token may touch, the X-BLToken header being wrong or missing, and a token that needs regenerating from the main admin account. The full-access-token versus scoped-token model is the mental model to keep: a scoped token rejects what is outside its scope, so check the token's scope before assuming the connection is broken.

Ask the agent to diagnose it:

Quote the exact error from the failed BaseLinker call. Then tell me which BaseLinker method you called and whether you know the token's scope. Do not retry the call yet.

The taught numbers: 100 requests per minute by default, paid Accelerations raising that up to 500, and capped endpoints, with getOrders returning at most 100 records per call. An agent enumerating orders walks straight into that wall. Narrow the work: date-bounded queries, fewer records per call, and the agent reporting what it got before continuing.

Ask the agent to diagnose it:

Tell me how many BaseLinker calls you made in the last minute and which method you were calling. Quote the error verbatim. Do not call BaseLinker again until I reply.

When calls succeed but data comes back short, the taught causes are the token's scope and sub-account restrictions: a scoped token or a restricted sub-account sees a subset, and lists end at that boundary rather than erroring. Ask the agent which token scope it is acting under and whether the endpoint returned a count or a cap marker, which distinguishes a scope limit from a rate limit.

Ask the agent to diagnose it:

Tell me which BaseLinker method returned the short list and what count it reported versus what you expected. Do not retry the call yet.

Double-check that the API key for Baselinker 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 Baselinker: link your Baselinker account once in the browser and Hermes Agent can call the Baselinker API through 106 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 Baselinker in the dashboard and Hermes can use it from the next message — no config files, and the Baselinker key you paste is stored server-side instead of in your environment.

About two minutes. Sign in, click Connect next to Baselinker 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 Baselinker working from chat.

Hermes Agent, the AI assistant. The courier named Hermes, Evri in the UK, is a different product, and the engines answer the connect query with the courier unless the page disambiguates. If you are connecting a parcel carrier inside BaseLinker's dashboard, that is BaseLinker's own carrier setup, not this integration.

The BaseLinker API token from Account → My Account → API. You still generate it: the engines and this page agree a token is unavoidable. What this setup changes is who holds it, so the token never sits in an environment file or a client config on your machine.

Courier accounts, courier lists and their form fields, package status history, inventories and their products, stock, categories, documents, manufacturers, price groups, payers, external storages and their quantities, and Base Connect integrations. It is an e-commerce operations surface: orders, stock, and carrier state across the shops you have wired up.

The engines teach least privilege, human approval for writes, and scoped middleware over raw master keys. Here the token is server-side and revocable from the dashboard, so the practical rules are: generate the token with the narrowest access your work needs, keep write prompts explicit, and disconnect in the dashboard when done.

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.