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

Make 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 Make 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.

It is right, and it is not confused. This integration has no scenario execution, listing, or trigger tools — the surface is account, organisation, team, operations, and enum data. An agent that invents a plausible name like make_run_scenario is calling something that has never existed, and the error will list the closest real tools. If scenario execution is the goal, use Make's own MCP server, which exposes scenarios as tools; if you want the agent to react to a scenario finishing, that is a job for Make's webhooks pointed at whatever you want notified, not for this connection.

Ask the agent to diagnose it:

List every Make tool you actually have access to, and tell me plainly whether any of them can execute a scenario. Do not guess at tool names.

This is a token integration, so "connected" means a token was accepted at setup, not that it is still valid. If the token was regenerated or deleted in Make afterwards, every call fails from that point and re-pasting the current one from the dashboard is the fix. If some calls succeed and others do not, the token is alive and you are looking at scope: Make tokens carry the permissions of the user who created them, so a token from a user without access to an organisation returns a permission error for it while working fine elsewhere. Run make_get_current_authorization first — it tells you what the token actually is before you change anything.

Ask the agent to diagnose it:

Call make_get_current_authorization and make_get_users_me, then make_list_organizations. Tell me which Make user and organisations this token can see, and quote the exact error from the failed call.

Almost always the token's owner rather than a fault. Make scopes visibility to the user the token belongs to, so a token created by an account that belongs to one team enumerates that team and nothing else, and an empty list is an accurate answer for that user. Confirm which user you are acting as before assuming the call failed. make_ping_api is the cheapest way to separate "the API is unreachable" from "the API answered and there is genuinely nothing to show".

Ask the agent to diagnose it:

Run make_ping_api, then make_get_users_me, then make_list_organizations and make_list_teams. Tell me which user this is and exactly what each call returned.

Double-check that the API key for Make 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 Make: link your Make account once in the browser and Hermes Agent can call the Make API through 25 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 Make in the dashboard and Hermes can use it from the next message — no config files, and the Make key you paste is stored server-side instead of in your environment.

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

No. This is the thing to check before you connect, because it is the natural expectation and the toolset does not support it. There is no run-scenario tool, no scenario listing, and no trigger — the 25 tools cover account, organisation, team, operations, and enum data. Make publishes its own MCP server that exposes scenarios as callable tools, and that is the right route for scenario execution. The two are not in competition: one answers questions about the account, the other runs the automations.

Account-level questions an agent would otherwise make you go and look up. It can tell you which organisations and teams your key can see, how many operations you have consumed, what the current authorization is, and confirm the API is reachable. In practice that is most valuable as a check rather than as a workflow — confirming which Make account an automation is billing against, or reading operations usage before someone turns on something expensive. It is a narrow toolset and the page would rather say so than have you discover it on the first prompt.

Mostly in what you have to run and edit. The Composio route that search results teach involves an MCP endpoint, an API key, and editing Hermes's config.yaml to point at it — a setup you then own and maintain. Here the plugin install and a one-time pairing handshake are the whole client-side story, the key lives server-side, and Make sits alongside your other connected accounts in one dashboard with one place to revoke. The underlying Make API is the same, so the capability limits above apply either way.

A Make API token, generated in your Make profile, pasted once into the hosted setup page. It carries the permissions of the user who created it, so the agent sees the organisations and teams that user can see — a token from an account with access to one team will not enumerate another. Because it is stored server-side rather than in an environment file, rotating it means updating it in one place, and removing the connection from the dashboard cuts access immediately.

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.