Ramp

What it does

When your agent uses it

• Corporate spend
• Expense transactions
• Card spend limits

Example prompts

• “/ramp”

Requirements

• Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

1. 1This connector stays read-only: it wires only GET endpoints, because one mistyped id or misread instruction in a write-capable connector…
2. 2Collect the credential with read-only scopes only. If Ramp adds broader scopes to the stored credential later, this CLI still cannot spend…
3. 3Never exfiltrate the credential: the CLI only ever handles surrogates (see bin/ramp.py). Do not print, log, or transmit the client secret…
4. 4Honesty flags (unverified while building this connector): the single-transaction GET path and the departments list path were not confirmed…

What it can do on your machine

Read from SKILL.md and the folder at commit d6dc5d8. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships script files (Python), which the agent can run.

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • api.ramp.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ramp loads about 872 tokens when it runs. Until then it costs about 51 tokens; SKILL.md has 333 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~51

When it runs · the whole SKILL.md, loaded when a task matches

~872

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Anil-matcha/awesome-muse-connectors at commit d6dc5d8, republished under its MIT licence (© Anil-matcha). 333 words, ~872 tokens.

name

ramp

description

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.

metadata.includeInPrompt

true

tagline

Read-only view of corporate spend: transactions, cards and limits, users, departments. No spend actions by design.

catalog_auth

OAuth 2.0 client credentials (per-user)

catalog_hosts

api.ramp.com

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

© Anil-matcha, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in connectors/ramp of Anil-matcha/awesome-muse-connectors.

• SKILL.md
• bin/ramp.py

Open the folder on GitHubat commit d6dc5d8