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

FreeAgent 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 FreeAgent 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 name causes from the raw-API world: a user permission level too low for the endpoint, locked or filed accounting periods that reject writes from any client, and a sandbox-versus-production mismatch between the credential and the environment. The hosted-flow equivalents: the connection was authorized under a user whose permission level cannot reach the endpoint, in which case freeagent_get_personal_profile and freeagent_list_all_users show who can; or the agent passed a placeholder value from documentation, which fails like a permissions error on a strict API. Reconnecting is rarely the fix; check the user and the argument first.

Ask the agent to diagnose it:

Call freeagent_get_personal_profile and tell me the user and permission level this connection acts as. Then quote the exact error from the failed call. Do not retry it yet.

FreeAgent rate-limits its API, and the traffic shape that meets the limit is an agent enumerating accounting transactions or timeslips one call at a time. The response is not to retry immediately but to change the shape of the work: narrower date ranges, fewer records per call, and the agent telling you what it intends to enumerate before it starts. If a bulk review is genuinely needed, running it in stages across a few turns is more reliable than one sweep.

Ask the agent to diagnose it:

Tell me how many FreeAgent calls you have made in the last minute and what you were enumerating. Quote any rate-limit detail from the last response. Do not call FreeAgent again until I reply.

The taught fixes for this symptom are all self-hosted: edit claude_desktop_config.json or mcp.json, fix absolute paths, rebuild /dist/index.js, force tool discovery. None of that applies here, because there is no local server. The hosted causes are: pairing incomplete, fixed by rerunning hermes clawlink begin and hermes clawlink finish and confirming FreeAgent shows as connected; schemas loading on demand, so the opening call in a fresh session can arrive before the catalog and needs one retry; and a wrong tool name, where the error lists the closest real ones.

Ask the agent to diagnose it:

List the FreeAgent tools you actually have access to. If there are none, say so plainly. If there are, tell me which one fetches the P&L summary and use that exact name.

Try reconnecting FreeAgent and complete the consent flow in the same browser session. Partial OAuth approvals or switching accounts mid-flow can leave the connection incomplete.

Yes. ClawLink is the fastest way to connect Hermes to FreeAgent: link your FreeAgent account once in the browser and Hermes Agent can call the FreeAgent API through 76 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 FreeAgent in the dashboard and Hermes can use it from the next message — no config files or API keys to manage.

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

The alternative to ClawLink is usually manual OAuth app 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 FreeAgent working from chat.

No. Search results teach app registration as the only path because FreeAgent genuinely has no personal access tokens. The hosted route registers and runs the OAuth app for you: you approve the connection in the browser, pairing is two Hermes commands, and no client secret file ever lands on your machine. The OAuth 2.0 flow is the same flow; the difference is who runs it.

Company details, invoices, estimates, bills with attachments, contacts, bank accounts, timeslips, mileage settings, cashflow summaries for a date range, profit and loss, trial balance, balance sheets, opening balances, accounting transactions, stock items, recurring invoices, price list items, users, and bank feeds. Creating invoices, estimates, bills, contacts, bank accounts, and timeslips are the writes to be deliberate about, since they change the accounting picture.

FreeAgent accounts are company-scoped: one account is one company, and every tool acts on that company. There is no cross-company surface to configure, which also means there is no wrong-company failure mode to debug.

It can create invoices and estimates, and bills with attachments. Whether it sends them depends on what you approve: the create tools produce the document, and sending is a separate action you should confirm explicitly. A created invoice is a real document in your books either way.

The engines answer 'safe if you use official OAuth 2.0, limit permissions, and use a secure gateway', with prompt injection and over-privileging as the taught risks. This connection is official OAuth 2.0 run hosted, with the token held server-side and revocable from one dashboard. The practical discipline is the same as anywhere: keep write prompts explicit and treat anything the agent reads from invoices or bills as untrusted input.

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.