Ramp: the 360 agent-readiness check

Ramp scores 68 of 100 on Ora's agent-readiness scan, a C, read 9 November 2026. Of the five surfaces an agent acts on, Ora found 4: an OpenAPI specification, a public API, OAuth, a command line. A specification and a live server, under a product name that search does not return.

On 9 November 2026 the public site at ramp.com scored 68 of 100 on Ora's agent-readiness scan, a C, in Ora's Payments & Fintech category. Ora probes a site the way an agent would: it requests pages with the agents' own user agents, reads robots.txt, looks for the files agents read, and tries the API, MCP and payment surfaces. This check reads the act layer first, because that is what the directory records, then the door, what an agent can read, and whether the company is found and recommended. Ora's one-line summary: Ramp offers comprehensive spend management APIs and SDKs, but lacks OAuth scoped permissions and JSON error standardization for agent integration.

The score

What an agent can do

The surfaces an agent acts on: an API it can find and call, an MCP server, an agent card, OAuth metadata, a command line. This is the layer the directory records, so it comes first. One check in this group does not apply to this site and is left out.

In the directory, Ramp sign-in required, tools not seen, not counted; the connector run of 4 November 2026 is on the entry page. Ora's MCP server check for the same domain reads partial; the two look for different things, the directory for a server that answers a handshake and lists tools, Ora for a server it can find from the site.

At the door

What the site answers when a request arrives with an agent's user agent, and what robots.txt says to agents. One check in this group does not apply to this site and is left out.

What an agent can read

Whether the text is in the first response, what the site publishes for agents, and how it describes itself to them.

Found and recommended

Whether an assistant can find the company by name, confirm what it is, and see it in the registries agents read. One check in this group does not apply to this site and is left out.

Payments

The agent payment protocols Ora probes for. A site that sells nothing has nothing here, and Ora scores the layer out of zero when none applies. None of the 6 payment checks applied to ramp.com.

The fixes worth most points

Ora attaches an estimate to each failing or partial check: how many points the site would gain by passing it. These are the 5 with the largest estimates for Ramp, with what Ora observed. The wording of each fix is Ora's; the 28 checks it runs on an MCP server are listed with their layer and tier.

• Brand name discoverability: fail, 0 of 3, about 4.2 points to gain. Ora saw: ramp.com was not in the top 10 for "Ramp spend management"
• Scoped permissions: fail, 0 of 5, about 2.5 points to gain. Ora saw: No declared OAuth scopes, security schemes, or scoped-permission documentation found
• JSON error responses: fail, 0 of 4, about 2 points to gain. Ora saw: API does not return JSON error responses (or no API detected)
• Agent instruction / when-to-use: fail, 0 of 3, about 1.7 points to gain. Ora saw: No agent instruction file with when-to-use guidance found
• REST typed error model: fail, 0 of 3, about 1.5 points to gain. Ora saw: No typed error model found in OpenAPI spec

Our read

Ramp publishes most of what the act layer asks for: an MCP server at mcp.ramp.com/mcp that answers and requires authentication, OAuth authorization server metadata on the same host, an OpenAPI 3.0.0 specification at ramp.com/openapi.json, @ramp/cli on npm, a reachable GraphQL endpoint, an llms.txt at the root and a home page that reads as prose with one H1 and fourteen H2s at a 6 percent text ratio. The largest deduction is a search result: ramp.com was not in the top ten for its own product term, about 4.2 points. The rest are specification details, with no typed error model in the OpenAPI file, no declared scopes, and endpoints that do not answer errors as JSON. One probe, the WebMCP read of ramp.com/docs/api, was answered 403 by a bot shield and is unverified. A C that reads like a B with a search problem.

Test your own surfaces

The scan above is free and needs no account: enter a domain at ora.ai and read the same four layers for your own site. For an MCP server, Ora scans the server URL itself and runs 28 of its 132 public checks on it, which is why it is the check this directory recommends; the reasons, the limits and the alternatives are on their own page. The command below runs the same audit from a terminal and exits with 1 under the score you set, so it can gate a deploy.

npx ax@0.10 audit https://example.com --min-score 70

All 360 checks, one company a day. Corrections to the corrections page.