Agent MCP Directory

Intercom: the 360 agent-readiness check

Intercom scores 81 of 100 on Ora's agent-readiness scan, a B, read 9 November 2026. Of the five surfaces an agent acts on, Ora found 2: a public API, OAuth. Markdown on request, a server card and a specification: the shape to copy.

On 9 November 2026 the public site at intercom.com scored 81 of 100 on Ora's agent-readiness scan, a B, in Ora's Communication & Support 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: Intercom offers strong REST API coverage and a published OpenAPI spec, but lacks WebMCP support, which would let agents interact with its pages directly.

The score

Intercom on Ora, read 2026-11-09: points per layer, with the share of each layer's maximum. 44 checks pass, 22 are partial, 25 fail and 41 do not apply to this site.
LayerAsksPointsShare
UsabilityCan agents use it50 of 6775%
AccessCan agents read it55 of 6387%
DiscoveryCan agents find and recommend it12 of 1486%
PaymentsCan agents pay0 of 0none apply
TotalGrade B81 of 10081%

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. 2 checks in this group do not apply to this site and are left out.

In the directory, Intercom 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.

What an agent can do: 17 checks Ora ran on intercom.com, read 2026-11-09. The last column is Ora's own observation where it published one.
CheckResultPointsWhat Ora saw
MCP server / manifest mcp-serverPartial5 of 6MCP server detected at https://mcp.intercom.com/mcp; it requires authentication. Presence is verified (5/6), but Ora could not inspect its tools or verify access scopes without credentials.
MCP well-known discovery mcp-well-known-discoveryPass2 of 2MCP server discoverable via server-card.json at /.well-known/mcp/
Public API with reachable endpoints public-apiPass7 of 7REST API documentation found at /api. Best-of-protocols score: 7/7.
Public API/docs linked from homepage public-api-docsPass3 of 3Documentation site found at https://www.intercom.com
Developer portal developer-portalPass6 of 6Developer portal found at /developers
OpenAPI spec published openapi-specPartial5 of 7OpenAPI spec (YAML) found at https://developers.intercom.com/_bundle/docs/references/@2.15/rest-api/api.intercom.io.yaml
API catalog (RFC 9727) api-catalog-rfc9727Partial1 of 2api-catalog linkset[0] has no 'item' entries
A2A / agent-card a2a-agent-cardFail0 of 2No A2A agent card found at /.well-known/agent-card.json
Agent discovery file agent-discovery-fileFail0 of 2No agent discovery file found
OAuth 2.0 support oauth-supportPass5 of 5OAuth authorization server metadata at https://mcp.intercom.com
OAuth Protected Resource metadata (RFC 9728) oauth-protected-resourcePass2 of 2no detail published
auth.md exists auth-md-existsFail0 of 2No /auth.md found at site root
WebMCP support webmcpFail0 of 5No WebMCP support detected - no document.modelContext / navigator.modelContext usage found
NLWeb /ask endpoint nlweb-askPass1 of 1NLWeb /ask endpoint exists but requires authentication (HTTP 403, via POST)
CLI tool available cli-toolPartial2 of 3CLI tool mentioned in llms.txt
Multi-language SDK packages rest-sdk-packagesPartial2 of 3SDK packages found in npm, go
JSON error responses json-error-responsesFail0 of 4API does not return JSON error responses (or no API detected)

At the door

What the site answers when a request arrives with an agent's user agent, and what robots.txt says to agents.

At the door: 8 checks Ora ran on intercom.com, read 2026-11-09. The last column is Ora's own observation where it published one.
CheckResultPointsWhat Ora saw
Not blocked by bot detection bot-detectionPass2 of 2Site accessible to 4 agent user-agents (ChatGPT-User, OAI-SearchBot, Claude-User, PerplexityBot).
Agent crawler reachability agent-crawler-reachabilityPass2 of 2Reachable to every agent we tested - ChatGPT-User: reachable, OAI-SearchBot: reachable, Claude-User: reachable, PerplexityBot: reachable
robots.txt AI crawler policy robots-ai-policy-qualityPass2 of 2AI search crawlers: allowed in 3 of 3 checks (3 crawlers on 1 page). AI training crawlers: allowed in 2 of 2 checks (2 crawlers on 1 page), not scored.
robots.txt agent-user policy robots-agent-user-policyPass2 of 2No applicable crawl or usage restriction found for 3 user-triggered agents (chatgpt-user, claude-user, perplexity-user) on 1 public page: https://intercom.com/. Declared policy only;
Content behind auth docs-auth-gatePass2 of 2All 5 sampled pages are publicly readable (5 with substantive content)
Homepage not hidden from search noindex-directivesPass1 of 1No noindex on the homepage: no robots, googlebot or bingbot meta tag and no X-Robots-Tag header hides it from search.
Redirect hygiene redirect-hygienePass1 of 1no detail published
Web Bot Auth directory web-bot-auth-directoryFail0 of 2No /.well-known/http-message-signatures-directory found

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.

What an agent can read: 17 checks Ora ran on intercom.com, read 2026-11-09. The last column is Ora's own observation where it published one.
CheckResultPointsWhat Ora saw
Content without JavaScript content-no-jsPartial2 of 3Homepage: 7283 chars with H1, but 2.0% content ratio is below the 5% target. 1 of 1 sampled inner page has text without JavaScript (4 skipped).
Page token budget page-token-budgetPass1 of 1All 6 measured pages fit an agent context budget (largest ~4K tokens)
Sitemap exists sitemapPass2 of 2Valid sitemap found at https://www.intercom.com/sitemap.xml with multiple sitemaps entries
Sitemap freshness (lastmod) sitemap-lastmodFail0 of 1None of the 77 sampled sitemap entries carries a lastmod date. Add <lastmod> (W3C datetime) so agents can prioritize fresh content.
llms.txt exists llms-txt-existsPass1 of 1Found the llms.txt at https://www.intercom.com/llms.txt.
llms.txt formatting llms-txt-formattingPass2 of 2The llms.txt is well-formatted: 173 lines with markdown links, 10,277 characters in total.
llms.txt links resolve llms-txt-links-resolvePass2 of 2no detail published
Markdown agent docs markdown-negotiationPass1 of 1Returns markdown when requested via Accept header
Markdown URL fallback markdown-url-fallbackFail0 of 2Homepage does not support the .md suffix. Probed https://intercom.com/index.md and it did not return markdown (expected text/markdown content-type or a heading-led non-HTML body).
Bot-UA markdown serving agent-ua-markdownFail0 of 1No probed bot User-Agent (ChatGPT-User, Claude-User, Perplexity-User) receives markdown when requesting HTML. Optional: detect AI-bot UAs server-side and serve them a markdown representation directly.
Agent mode view agent-mode-viewFail0 of 2?mode=agent returns same content as homepage (no dedicated agent view)
JSON-LD structured data json-ldPass4 of 4Rich JSON-LD identity: Product with name, description, url, and offers/brand (1 block(s))
Organization schema completeness org-schema-completenessPartial1 of 2Organization schema found but missing: contactPoint, address
JSON-LD entity linking (sameAs) json-ld-entity-linkingPass2 of 2no detail published
Schema type breadth schema-type-breadthPartial1 of 2Some extended schema types found: ItemList, BreadcrumbList - add 1 more type that matches what the homepage shows, for full coverage
Metadata completeness metadata-completenessPass2 of 2All metadata signals present: canonical URL, lang="en", og:image, og:type
Agent instruction / when-to-use agent-instructionPartial2 of 3When-to-use guidance found at https://www.intercom.com

Found and recommended

Whether an assistant can find the company by name, confirm what it is, and see it in the registries agents read.

Found and recommended: 9 checks Ora ran on intercom.com, read 2026-11-09. The last column is Ora's own observation where it published one.
CheckResultPointsWhat Ora saw
Brand name discoverability brand-search-accuracyPass3 of 3intercom.com ranks #3 for "Intercom" (searched your brand name alone: no main product term from your homepage qualified)
Wikipedia / Wikidata entity presence wikipedia-presencePartial2 of 4Wikidata Q48965215 (Intercom) verified - draft a Wikipedia page with cited references to complete knowledge graph coverage
Developer resource discoverability agentic-search-specificPass3 of 3no detail published
Listed in MCP registries mcp-registry-listedFail0 of 1No verified entry in the official MCP Registry or on Smithery, and no npm or PyPI package of yours that runs as an MCP server. To pass,
NPM/PyPI SDK package npm-sdk-packagePass1 of 1no detail published
ChatGPT app listed chatgpt-app-listedFail0 of 2Not found in ChatGPT app directory
Registry branding registry-brandingFail0 of 2No registry branding (name, icon, description) found
Listed on skills.sh skills-sh-listedPass1 of 1no detail published
ARD discovery ard-catalogFail0 of 1No /.well-known/ard.json, no same-site rel="ard" link, and no legacy /.well-known/ai-catalog.json

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.

Payments: 6 checks Ora ran on intercom.com, read 2026-11-09. The last column is Ora's own observation where it published one.
CheckResultPointsWhat Ora saw
UCP - Universal Commerce Protocol ucp-supportPartial0 of 3no UCP (Universal Commerce Protocol) signals detected
ACP - Agentic Commerce Protocol acp-supportPartial0 of 3no ACP (Agentic Commerce Protocol) signals detected
ACP delegate payment acp-delegate-paymentPartial0 of 3No ACP Delegate Payment signals detected
AP2 - Agent Payments Protocol ap2-supportPartial0 of 3No AP2 (Agent Payments Protocol) signals detected
x402 payment protocol x402-supportPartial0 of 2No x402 payment protocol support detected
MPP payment protocol mpp-supportPartial0 of 2No MPP (Machine Payments Protocol) support detected

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 Intercom, 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.

  • WebMCP support: fail, 0 of 5, about 3.3 points to gain. Ora saw: No WebMCP support detected - no document.modelContext / navigator.modelContext usage found
  • JSON error responses: fail, 0 of 4, about 2.7 points to gain. Ora saw: API does not return JSON error responses (or no API detected)
  • Scoped permissions: partial, 2 of 5, about 2 points to gain. Ora saw: Scoped permissions described at https://www.intercom.com, but no machine-readable scope declaration found (OpenAPI oauth2 scopes or RFC 9728 scopes_supported)
  • ARD discovery: fail, 0 of 1, about 1.6 points to gain. Ora saw: No /.well-known/ard.json, no same-site rel="ard" link, and no legacy /.well-known/ai-catalog.json
  • Listed in MCP registries: fail, 0 of 1, about 1.6 points to gain. Ora saw: No verified entry in the official MCP Registry or on Smithery, and no npm or PyPI package of yours that runs as an MCP server. To pass,

Our read

Intercom's 81 is one of the few in this directory earned on the older and the newer surfaces at once. The MCP server at mcp.intercom.com/mcp answers and requires authentication, its server card sits at /.well-known/mcp/, OAuth authorization server metadata is on the same host, an OpenAPI specification in YAML is published, the REST documentation scores 7 of 7, SDKs are in npm and Go, intercom.com serves an llms.txt and returns markdown when an agent asks for it with an Accept header, which almost no company here does. The points left are small and specific: the endpoints Ora tried did not answer errors as JSON, scopes are described in prose rather than declared, there is no ARD catalog and no entry in the official MCP Registry or on Smithery, and no WebMCP registration. The home page is 2 percent text. For a support platform that agents will be asked to read and write, this is the shape to copy.

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.