# How to connect Ashby to Hermes Agent (paste one key, 125 tools)

> Connect Ashby to Hermes Agent with ClawLink: paste your Ashby API key once and 125 tools work from chat. Stored server-side, revoked from one dashboard.

Web version: https://claw-link.dev/hermes/ashby

Most guides for giving Hermes Agent Ashby 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 Ashby setup: pair once in the browser and your always-on Hermes agent can act on Ashby 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 Ashby.

1. **Install ClawLink** — add the plugin to Hermes Agent once.
2. **Connect Ashby** — 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 ashby  # connect Ashby (browser OAuth)
npx -y @useclawlink/cli actions ashby  # list available actions
npx -y @useclawlink/cli run ashby <action> --input '<json>'  # execute (add --confirm for writes)
```

The whole pairing handshake. Run these once, then paste your Ashby key in the dashboard:

```bash
hermes plugins install ClawLink-HQ/hermes-plugin --enable
hermes clawlink begin     # approve the link in your browser
hermes clawlink finish
hermes clawlink test
```

The key comes from Ashby: Admin → Integrations → API Keys → + New, created with the permissions you intend. A read-only key stays read-only no matter what you ask the agent to do.

### 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 Ashby is connected in the dashboard, that agent calls the same 125 Ashby 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).

## Ashby MCP for Hermes

Looking for a Ashby MCP server for Hermes Agent? ClawLink connects Ashby to Hermes Agent and exposes 125 Ashby 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 Ashby integration](https://claw-link.dev/openclaw/ashby) works the same way.

Ashby keys are admin-generated, and the safety advice search engines give treats pasting a third-party integration's API key as the risky pattern. Both deserve a straight answer. You do paste one key, into a hosted setup page, and it is stored server-side rather than in an environment file or a client config. What the key can do is still what you granted it: a read-only key stays read-only, and the connection revokes with one dashboard action or by deleting the key in Ashby. 125 tools, one key, no MCP server to run.

## Is it safe to connect Ashby to an AI agent?

The search answer says 'generally safe' for Ashby's official integration and flags third-party API-key integrations as the risk. This page is the third-party case, so the honest answer is about what is actually exposed.

- **The key's permissions are the ceiling.** The connection can only do what the key you pasted can do. A read-only key cannot write, move candidates, or change openings no matter what the prompt asks, which is the strongest single control available.
- **Custody is server-side.** The key is stored on the hosted connection, not in an env file or config on your machine. Rotating or deleting the key in Ashby kills the connection immediately; disconnecting in the dashboard does the same.
- **Writes are the risk surface, not reads.** Viewing candidates and applications is what the connection is for; moving candidates, adding tags, and assigning interviewers change state your recruiters rely on, so keep those prompts explicit and approved.
- **Treat candidate data as sensitive.** Ashby holds resumes, interview notes, and feedback. The connection inherits the key's reach into that data, so scope the key to what the agent genuinely needs.

A sensible default is a read-only key for the first week, reads and pipeline snapshots only, then a deliberate decision about whether the agent needs write access.

## What the Hermes Agent Ashby integration can do

125 Ashby tools are ready for Hermes Agent once the account is connected. The 30 below are the ones people reach for most; your agent can call all 125.

### 30 of 125 Ashby tools for Hermes

| Tool | What it does |
|---|---|
| **Add candidate project** `ashby_add_candidate_project` | Add a candidate to a project in Ashby |
| **Add candidate tag** `ashby_add_candidate_tag` | Add a tag to a candidate in Ashby |
| **Add hiring team member** `ashby_add_hiring_team_member` | Add an Ashby user to a hiring team at the application, job, or opening level |
| **Add interviewer pool user** `ashby_add_interviewer_pool_user` | Add a user to an interviewer pool |
| **Get API key info** `ashby_get_api_key_info` | Retrieve information about the current API key, including associated organization, user details, and permissions |
| **Get application info** `ashby_get_application_info` | Retrieve detailed information about a specific application by its ID |
| **Get candidate info** `ashby_get_candidate_info` | Retrieve detailed information about a specific candidate by their ID |
| **Get custom field info** `ashby_get_custom_field_info` | Retrieve detailed information about a specific custom field by its ID |
| **Get department info** `ashby_get_department_info` | Retrieve detailed information about a specific department by its ID |
| **Get feedback form definition** `ashby_get_feedback_form_definition` | Retrieve detailed information about a specific feedback form definition by its ID |
| **Get file info** `ashby_get_file_info` | Retrieve the URL of a file associated with a candidate |
| **Get interview info** `ashby_get_interview_info` | Retrieve detailed information about a specific interview type by its ID |
| **Get interview stage info** `ashby_get_interview_stage_info` | Fetch interview stage details by ID |
| **Get interviewer pool info** `ashby_get_interviewer_pool_info` | Retrieve detailed information about a specific interviewer pool by its ID |
| **Get interviewer user settings** `ashby_get_interviewer_user_settings` | Get interviewer settings for a specific user by their ID |
| **Get job info** `ashby_get_job_info` | Retrieve detailed information about a specific job by its ID |
| **Get job interview plan info** `ashby_get_job_interview_plan_info` | Retrieve the interview plan information for a specific job |
| **Get job posting info** `ashby_get_job_posting_info` | Retrieve detailed information about a specific job posting by its ID |
| **Get location info** `ashby_get_location_info` | Retrieve detailed information about a specific location by its ID |
| **Get offer info** `ashby_get_offer_info` | Retrieve detailed information about a specific offer by its ID |
| **Get opening info** `ashby_get_opening_info` | Retrieve detailed information about a specific opening (job requisition) by its ID |
| **Get survey form definition** `ashby_get_survey_form_definition` | Retrieve detailed information about a specific survey form definition by its ID |
| **Get user info** `ashby_get_user_info` | Retrieve detailed information about a specific user by their ID |
| **List application criteria evaluations** `ashby_list_application_criteria_evaluations` | Retrieve AI-generated criteria evaluations for an application |
| **List application feedback** `ashby_list_application_feedback` | Retrieve all feedback submissions for an application |
| **List application hiring team role** `ashby_list_application_hiring_team_role` | Retrieve all available hiring team roles for applications in the organization |
| **List application history** `ashby_list_application_history` | Retrieve the complete history of stage transitions for an application |
| **List applications** `ashby_list_applications` | Retrieve a list of applications with optional pagination and sync-token filtering for |
| **List approval** `ashby_list_approval` | Retrieve a list of approvals (offer approvals, job approvals, etc.) |
| **List archive reasons** `ashby_list_archive_reasons` | Retrieve a list of all archive reasons |

## Example prompts

**Pipeline snapshot**

> List applications with ashby_list_applications for opening \<id> and group them by stage, then show me how long each has been in its current stage.

**Candidate brief**

> Get candidate \<id> with ashby_get_candidate_info, pull their applications with ashby_get_application_info, and summarise where the process stands.

**Interview prep**

> Get the interview plan for the job with ashby_get_job_interview_plan_info and list the stages and who is assigned to each.

**Feedback themes**

> List application feedback with ashby_list_application_feedback for \<application id> and summarise the themes across interviewers.

## How the Ashby tools behave

Details that matter once the key is in and the agent is working the pipeline.

- **The key's permissions are the ceiling.** A read-only key cannot write, no matter what the prompt asks.
- **Lookups are granular.** Candidates, applications, jobs, openings, interviews, offers, and feedback forms each have their own get tool; ids come from the list tools.
- **History is reconstructable.** `ashby_list_application_history` and `ashby_list_application_feedback` rebuild what happened in a pipeline.
- **Writes touch real hiring workflows.** Adding candidates to projects or tags and assigning interviewers changes what recruiters see.
- **The key can inspect itself.** `ashby_get_api_key_info` returns the key's own organisation, user, and permissions; the first call on a permission error.

## 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 Ashby working from chat.

| | Manual | ClawLink |
|---|---|---|
| **Credential handling** | Collect, validate, store, and rotate the Ashby API key yourself, then make sure every tool call uses the right account. | Users complete the hosted ClawLink setup once and the connected Ashby 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 Ashby. | 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 Ashby actions to the runtime in a format your agent can reliably use. | 125 tools for Ashby are already exposed through ClawLink, so the agent can read and act from chat immediately. |

## ClawLink vs. Composio

Composio also exposes Ashby 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 Ashby in the browser, and the 125 tools above work from chat. There is no SDK and no config file, and the Ashby 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 Ashby
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 Ashby 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 Ashby tools
Ashby 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 Ashby 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.

### Ashby 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.

### Ashby returns 403 or "insufficient permissions"
The engines teach key-type causes: a read-only key on a write call, missing scopes, or a deactivated key, with the fix being to re-check key permissions in Ashby Admin. That maps directly onto a hosted flow: the pasted key carries its own permissions, so start with `ashby_get_api_key_info`, which returns the key's organisation, user, and permissions, then check the argument, where a placeholder id from documentation fails like a real 403.

Ask the agent to diagnose it:

```text
Call ashby_get_api_key_info and tell me the key's permissions and the organisation it belongs to. Then quote the exact error from the failed call. Do not retry it yet.
```

### Ashby rate limits or a list stalls
Ashby rate-limits its API, and an agent walking every application one call at a time is the traffic shape that meets it. The response is not to retry immediately but to narrow the work: one opening, one stage, one date-bounded set, and the agent telling you what it intends to enumerate before it starts.

Ask the agent to diagnose it:

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

### 'Tool not found' or Ashby tools missing
The taught causes are a client config problem and a known agent-side tool-registration bug, with six Cursor forum threads' worth of fixes. Our 'Tool schema not loaded yet' card is the same phenomenon in a hosted flow: schemas load on demand, so the opening call in a fresh session can arrive before the catalog and needs one retry. The other causes are pairing incomplete, fixed by rerunning `hermes clawlink begin` and `hermes clawlink finish`, and a wrong tool name, where the error lists the closest real ones.

Ask the agent to diagnose it:

```text
List the Ashby tools you actually have access to. If there are none, say so plainly. If there are, tell me which one lists applications and use that exact name.
```

### API key setup works but results look incomplete
Double-check that the API key for Ashby 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 Ashby integration?
Yes. ClawLink is the fastest way to connect Hermes to Ashby: link your Ashby account once in the browser and Hermes Agent can call the Ashby API through 125 ready-made tools — no custom code or token handling.

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

### How long does it take to connect Ashby to Hermes Agent?
About two minutes. Sign in, click Connect next to Ashby in the dashboard, authenticate, and Hermes Agent can use it from the next chat message.

### Why use ClawLink instead of wiring Ashby 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 Ashby working from chat.

### Which Ashby key does ClawLink need?
The one from Ashby Admin → Integrations → API Keys, created by an admin. Create it with the permissions you want the agent to have: read-only for read-only work, read/write when the agent must move candidates through the pipeline. The key's permissions are the ceiling: no prompt can exceed them, which is also the answer to the safety question below.

### What can the agent do in Ashby?
Candidates, applications, jobs, openings, interview plans, interviews, interview stages, feedback forms, offers, departments, locations, custom fields, hiring team roles, and interviewer pools are readable; candidates can be added to projects or tags, and hiring team members and interviewer pool users can be added. The writes are visible to your recruiters, so confirm before executing them.

### Where is the key stored, and how do I revoke it?
Server-side, on the hosted connection. It is not in `~/.hermes` or any env file on your machine. Revoke from the ClawLink dashboard, or delete the key in Ashby Admin, and the connection dies from that moment. There is no token file to hunt down on any machine you have used.

### Is pasting an Ashby key into a service safe?
The engines call official integrations safe and frame third-party API-key integrations as the risk path, and this page is the third-party case, so here is the straight answer. The mitigation is custody and scope: the key lives server-side, revokes in one place, and its permissions still apply in Ashby. The risk that remains is the key's own permissions, which is why the setup note says to create it narrowly. If that tradeoff is outside your risk tolerance, read-only key for read-only work.

### Can it move candidates through pipelines?
It adds candidates to projects and tags, adds hiring team members, and adds interviewer pool users. These change what your recruiters see in Ashby, so they are the writes to approve explicitly rather than letting a broad prompt run them.

### Hermes paired but still can't use Ashby
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

- [BambooHR tools](https://claw-link.dev/hermes/bamboohr) — Manage employees, time-off, benefits, and hiring