Read-only Ramp corporate spend: transactions, cards and card limits, users, departments. No spend actions by design. Trigger phrases: ramp, corporate spend, expense transactions, card spend limits.
npx skills add https://github.com/Anil-matcha/awesome-muse-connectors --skill ramp
Inspect a Ramp corporate-spend account without any ability to move money: list and retrieve transactions, list cards and show their spending restrictions, list users, and list departments. Reach for this when the user wants spend visibility, expense review, or cardholder lookup. It cannot issue cards, set limits, pay bills, or reimburse.
All commands go through bin/ramp.py. Read-only, so there is no sandbox/prod split: every call is a GET against https://api.ramp.com/developer/v1.
bin/ramp.py auth # verify the credential
bin/ramp.py transactions --limit 25 # list transactions
bin/ramp.py transactions --limit 50 --from-date 2026-09-01T00:00:00Z --to-date 2026-09-30T23:59:59Z
bin/ramp.py transaction-get --transaction-id TX_ID # one transaction
bin/ramp.py cards --limit 25 # list cards
bin/ramp.py card-limits --card-id CARD_ID # spending restrictions on one card
bin/ramp.py users --limit 25 # list users
bin/ramp.py departments --limit 25 # list departments
ramp (credential is collected as custom.ramp)credentials.request_api_access); the runtime exchanges them at POST /developer/v1/token (OAuth 2.0 client credentials grant) and hands the CLI a fresh Bearer tokenAuthorization: Bearer <token> on every requesttransactions:read, cards:read, users:read; request no write scopes for this connectorapi.ramp.combin/ramp.py authbin/ramp.py). Do not print, log, or transmit the client secret or tokens.card-limits reads the card object's spending_restrictions field; no separate limits endpoint was verified. Ramp also runs a demo host (demo-api.ramp.com), but this CLI targets production only, which is safe because it cannot spend.Draft: written from Ramp's public developer docs; not yet live-tested end-to-end.
Take anil-matcha/ramp from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.