# How to connect Ramp to OpenClaw (no API keys)

> Connect Ramp to OpenClaw with ClawLink in one click — 168 tools your AI agent can call from chat via hosted OAuth. No API keys, no manual setup.

Web version: https://claw-link.dev/openclaw/ramp

The usual route to Ramp access for OpenClaw is an MCP server you configure and keep running, plus your own OAuth app or API keys. ClawLink gives OpenClaw a more practical Ramp setup: install one ClawHub skill, connect Ramp in the browser, and OpenClaw can call real Ramp actions from any chat surface with no auth, token refresh, or tool wiring to build yourself.

## Setup

It takes three steps to connect OpenClaw to Ramp.

1. **Install ClawLink** — add the plugin to OpenClaw once.
2. **Connect Ramp** — one-click OAuth in the ClawLink dashboard.
3. **Use it from chat** — ask OpenClaw in plain English.

**Paste this into OpenClaw to set up ClawLink:**

> I want to connect my apps to OpenClaw through ClawLink.
> Please install the ClawLink plugin from ClawHub and enable it: `openclaw plugins install clawhub:clawlink-plugin`
> When it is installed, tell me and stop. After I reply, give me the ClawLink pairing link. Setup notes, if you need them: https://claw-link.dev/skill.md

**Alternative for any agent (no plugin needed):** if the OpenClaw 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 ramp  # connect Ramp (browser OAuth)
npx -y @useclawlink/cli actions ramp  # list available actions
npx -y @useclawlink/cli run ramp <action> --input '<json>'  # execute (add --confirm for writes)
```

### Install by command

The setup prompt above does all of this in one paste. By hand, it is one install command plus a browser approval:

```bash
openclaw plugins install clawhub:clawlink-plugin
```

Then ask OpenClaw to set up ClawLink. It starts browser pairing and prints an approval link — open it, approve the device, return to the chat, and say `done`. Finally, connect Ramp in the [ClawLink dashboard](https://claw-link.dev/dashboard) — a one-click OAuth approval, no API keys.

Verify the connection by asking OpenClaw:

> Use Ramp to mcp ramp answer policy question and walk me through the result in plain English.

### Using a different agent?

The OpenClaw 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 Ramp is connected in the dashboard, that agent calls the same 168 Ramp 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).

## Ramp MCP for OpenClaw

Looking for a Ramp MCP server for OpenClaw? ClawLink connects Ramp to OpenClaw and exposes 168 Ramp 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 Hermes instead? The [Hermes Ramp integration](https://claw-link.dev/hermes/ramp) works the same way.

## What the OpenClaw Ramp integration can do

168 Ramp tools are ready for OpenClaw once the account is connected. The 30 below are the ones people reach for most; your agent can call all 168.

### 30 of 168 Ramp tools for OpenClaw

| Tool | What it does |
|---|---|
| **Mcp ramp answer policy question** `ramp_mcp_ramp_answer_policy_question` | Use this tool when the user asks about expense policy rules, spending limits, fund |
| **Mcp ramp create fund request** `ramp_mcp_ramp_create_fund_request` | Always use this tool (never invent URLs) and include the returned url in your next message |
| **Mcp ramp departments** `ramp_mcp_ramp_departments` | Returns the departments available in the user's business, which can be used as inputs to |
| **Mcp ramp estimate mileage reimbursement** `ramp_mcp_ramp_estimate_mileage_reimbursement` | Estimate the reimbursement amount for a given mileage distance based on the user's company rates |
| **Mcp ramp estimate per diem amount** `ramp_mcp_ramp_estimate_per_diem_amount` | Estimate the per diem reimbursement amount for a trip given start/end dates and optional meal |
| **Mcp ramp events** `ramp_mcp_ramp_events` | Get audit log events |
| **Mcp ramp execute analyst query** `ramp_mcp_ramp_execute_analyst_query` | First use the analyst catalog and read the domain docs for every table in the query; those docs |
| **Mcp ramp get account balance history** `ramp_mcp_ramp_get_account_balance_history` | Use when the user asks about balance history for a specific account, savings account trend |
| **Mcp ramp get agent card funds** `ramp_mcp_ramp_get_agent_card_funds` | Returns eligible funds with available balance |
| **Mcp ramp get AI token spend aggregates** `ramp_mcp_ramp_get_ai_token_spend_aggregates` | Aggregate AI token usage or estimated cost over a time window, grouped by caller-selected |
| **Mcp ramp get AI token spend connections** `ramp_mcp_ramp_get_ai_token_spend_connections` | Use GetAiTokenSpendCurrentSpend for actual vendor spend and GetAiTokenSpendAggregates for |
| **Mcp ramp get AI token spend current spend** `ramp_mcp_ramp_get_ai_token_spend_current_spend` | Requires transaction, reimbursement, or bill read access |
| **Mcp ramp get AI token spend filter options** `ramp_mcp_ramp_get_ai_token_spend_filter_options` | List the dimensions and values available for AI-spend aggregate queries: providers, models |
| **Mcp ramp get analyst catalog** `ramp_mcp_ramp_get_analyst_catalog` | Review the catalog before writing a query, then read domain docs for every table used |
| **Mcp ramp get analyst metric metadata** `ramp_mcp_ramp_get_analyst_metric_metadata` | Discover supported analyst metrics and starter SQL for aggregate business analysis |
| **Mcp ramp get analyst spend facts domain docs** `ramp_mcp_ramp_get_analyst_spend_facts_domain_docs` | Read domain documentation for analyst.spend_facts before using it in an analyst query |
| **Mcp ramp get analyst table domain docs** `ramp_mcp_ramp_get_analyst_table_domain_docs` | Read domain documentation for an analyst table before using it in an analyst query |
| **Mcp ramp get attention feed** `ramp_mcp_ramp_get_attention_feed` | Use this tool to see what needs the user's attention right now: pending approvals, missing |
| **Mcp ramp get authorized businesses** `ramp_mcp_ramp_get_authorized_businesses` | Returns all client businesses that the external firm (advisor console) user has been granted |
| **Mcp ramp get bank accounts** `ramp_mcp_ramp_get_bank_accounts` | List bank accounts |
| **Mcp ramp get bill amount summary** `ramp_mcp_ramp_get_bill_amount_summary` | Examples: total unpaid amount, total pending amount |
| **Mcp ramp get bill comments** `ramp_mcp_ramp_get_bill_comments` | Bills in Ramp have two stages: draft bills (created/uploaded but not yet submitted; use the |
| **Mcp ramp get bill details** `ramp_mcp_ramp_get_bill_details` | Requires a bill UUID and known submitted status |
| **Mcp ramp get bill history** `ramp_mcp_ramp_get_bill_history` | Returns a chronological event log — creation, submission, each approval-chain action with actor |
| **Mcp ramp get bill invoices** `ramp_mcp_ramp_get_bill_invoices` | Returns the source documents backing the bill: for each attachment, the filename, type, and a |
| **Mcp ramp get bill metrics** `ramp_mcp_ramp_get_bill_metrics` | Use this to answer questions like "How many bills are pending approval?" or "How many overdue |
| **Mcp ramp get bill status** `ramp_mcp_ramp_get_bill_status` | Does not determine required next actions: next_action_required is always null (unavailable) |
| **Mcp ramp get bills for approval** `ramp_mcp_ramp_get_bills_for_approval` | Use this tool when the user wants to see bills they need to approve or asks about pending |
| **Mcp ramp get booking details** `ramp_mcp_ramp_get_booking_details` | Call filtered GetBookings first when the booking UUID is unknown |
| **Mcp ramp get bookings** `ramp_mcp_ramp_get_bookings` | Optionally identify existing bookings by city, hotel name, flight airline, flight number |

## Example prompts

**Mcp Ramp Answer Policy Question**

> Use Ramp to mcp ramp answer policy question and walk me through the result in plain English.

**Mcp Ramp Create Fund Request**

> Use Ramp to mcp ramp create fund request and walk me through the result in plain English.

**Mcp Ramp Departments**

> Use Ramp to mcp ramp departments and walk me through the result in plain English.

**Mcp Ramp Estimate Mileage Reimbursement**

> Use Ramp to mcp ramp estimate mileage reimbursement and walk me through the result in plain English.

## ClawLink vs. building it yourself

The alternative to ClawLink is usually manual OAuth app setup plus your own token handling, permission troubleshooting, and tool plumbing for OpenClaw. That is fine if you want to build and maintain the integration yourself. Most teams just want Ramp working from chat.

| | Manual | ClawLink |
|---|---|---|
| **Connection flow** | Register a Ramp app, configure redirect URLs, manage consent details, and reconnect users when auth settings drift. | Users connect Ramp through the hosted browser flow and ClawLink keeps the token lifecycle out of your app code. |
| **Ongoing maintenance** | You own refresh logic, permission debugging, environment config, and every provider-specific edge case for Ramp. | 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 Ramp actions to the runtime in a format your agent can reliably use. | 168 tools for Ramp are already exposed through ClawLink, so the agent can read and act from chat immediately. |

## ClawLink vs. Composio

Composio also exposes Ramp 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 OpenClaw users instead. You install the plugin once, connect Ramp in the browser, and the 168 tools above work from chat. There is no SDK, no config file, and no API key handling. Choosing between them? Read the full [Composio alternatives](https://claw-link.dev/hub/composio-alternatives) comparison.

### OpenClaw installed the Ramp skill but can't call the tools
The ClawHub skill teaches OpenClaw about Ramp, but the calls run through the ClawLink plugin and your connected account. Make sure Ramp is connected in the dashboard, then start a fresh chat so OpenClaw reloads the tool catalog. If OpenClaw runs as a persistent gateway, restart it so the new tools register.

### Connection succeeds but no tools appear
Reconnect Ramp 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 Ramp tools
Ramp 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 Ramp 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.

### Ramp 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.

### OAuth finished in the browser but the account is still missing
Try reconnecting Ramp and complete the consent flow in the same browser session. Partial OAuth approvals or switching accounts mid-flow can leave the connection incomplete.

### Is there a OpenClaw Ramp integration?
Yes. ClawLink is the fastest way to connect OpenClaw to Ramp: link your Ramp account once in the browser and OpenClaw can call the Ramp API through 168 ready-made tools — no custom code or token handling.

### How do I add Ramp to OpenClaw with ClawLink?
Paste the setup prompt from this page into OpenClaw. It installs the ClawLink Ramp skill from ClawHub, then you click Connect in the dashboard to authorize Ramp. OpenClaw calls the tools from the next message — no config files or API keys to manage.

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

### Why use ClawLink instead of wiring Ramp up myself?
The alternative to ClawLink is usually manual OAuth app setup plus your own token handling, permission troubleshooting, and tool plumbing for OpenClaw. That is fine if you want to build and maintain the integration yourself. Most teams just want Ramp working from chat.

### OpenClaw installed the Ramp skill but can't call the tools
The ClawHub skill teaches OpenClaw about Ramp, but the calls run through the ClawLink plugin and your connected account. Make sure Ramp is connected in the dashboard, then start a fresh chat so OpenClaw reloads the tool catalog. If OpenClaw runs as a persistent gateway, restart it so the new tools register.

## Related

- [Stripe](https://claw-link.dev/openclaw/stripe) — Manage payments, customers, and invoices
- [Zoho Books](https://claw-link.dev/openclaw/zoho-books) — Organize finances, invoices, bills, and accounting
- [Zoho Invoice](https://claw-link.dev/openclaw/zoho-invoice) — Create and send invoices, track payments, and manage billing
