# www.openagentguide.com — technology — 3 of 5

Home > Browse > By type > directory > www.openagentguide.com

> Probe-verified (tier 2 of 3). Last checked 2026-10-23. 3 of 5 capability checks passed.

- host: www.openagentguide.com
- url: https://www.openagentguide.com/
- category: technology
- type: directory
- language: en

## Probe-verified · tier 2 of 3

Probed live on 2026-10-23 against rubric v1.2. 3 of 5 checks passed.

- FAIL — Markdown negotiation (`Accept: text/markdown`)
- FAIL — Markdown twin at a predictable URL (`/page.md`)
- PASS — llms.txt (`/llms.txt`)
- PASS — API catalog (`RFC 9727`)
- PASS — MCP endpoint answers tools/list (`initialize → tools/list, no credentials`) · on 23 Oct 2026
  - ABSENT — MCP server card (`/.well-known/mcp/server-card.json`): absent; not scored
  - Platform-supplied: no; not scored
- FAIL — Other agent files at well-known paths (`agent-skills/index.json · oauth-authorization-server · oauth-protected-resource · http-message-signatures-directory`): none found; not scored

## What answered

`https://www.openagentguide.com/mcp`, found through its llms.txt, answered tools/list on 23 Oct 2026.

### The tools it lists

7 tools, as the server gave them on 23 Oct 2026. The descriptions are the server's own words, not ours.

- `search_products`: Search AI-native products, optionally filtered by category, job-to-be-done, capability, organization, SDK language, or affordances. has_mcp selects hosted MCP servers; has_api_spec and spec_type select API specifications. Returns a cursor-paginated page with \`\`ai_native_score\`\` (0-100), \`\`ai_native_tier\`\` (S/A/B/C/D), the research-coverage axis \`\`coverage_score\`\` (0-100) and derived \`\`unrated\`\` boolean and the \`\`attested_absences\`\` list of confirmed absent fields. Use \`\`expand\`\` to resolve relat (cut by our probe at 500 characters)
- `get_product`: Fetch one catalog product by UUID or slug, including its AI-native scores (\`\`ai_native_score\`\` 0-100, \`\`ai_native_tier\`\` S/A/B/C/D) and related organization, capabilities, and integrations (MCP servers, SDKs, CLIs, A2A servers, API specs, and plugins) expanded inline as full objects. SDKs include their programming languages and licenses as named records alongside IDs. Also returned: a second research-coverage axis — \`\`coverage_score\`\` (0-100) and the derived boolean \`\`unrated\`\`. Coverage tells y (cut by our probe at 500 characters)
- `list_categories`: List product categories. Pass a category's slug to \`\`search_products\`\` to filter by it.
- `list_jobs_to_be_done`: List jobs-to-be-done. Pass a job's slug to \`\`search_products\`\` to filter by it.
- `list_capabilities`: List capabilities. Pass a capability's slug to \`\`search_products\`\` to filter by it.
- `list_compliance_certifications`: List compliance certifications (e.g. SOC 2, ISO 27001, HIPAA). Use this to resolve the opaque \`\`compliance_certification_ids\`\` that \`\`get_product\`\` returns to named certifications, and to enumerate which certifications the catalog tracks.
- `get_product_coverage`: Read coverage, unknown scored fields, and evidence guidance before drafting. Returns the catalog API response unchanged, including confirmed absences. Guidance and score projections do not corroborate proposed claims.

## The files found

The agent files at well-known paths, as the probe read them on 23 Oct 2026.

- `/.well-known/mcp/server-card.json`: not found (not_found_at_path (404))
- `/.well-known/api-catalog`: found (ok)
- `/.well-known/agent-skills/index.json or /.well-known/skills/index.json`: not found (not_found_at_path (404))
- `/.well-known/oauth-authorization-server`: not found (not_found_at_path (404))
- `/.well-known/oauth-protected-resource`: not found (not_found_at_path (404))
- `/.well-known/http-message-signatures-directory`: not found (not_found_at_path (404))

## Probe history

- 23 Oct 2026: the full probe (v2-probe-2026-09-30.1): every check on this page
- 23 Oct 2026: the markdown re-probe: markdown on request and at a markdown URL


## Summary

Directory of AI-native products with capabilities, pricing, compliance, and agent-facing affordances, searchable and browsable via API and MCP server, serving humans and AI agents globally.

## Context

242 sites in this index share the category "technology"; 31 are transactional.

## How we grade

- tier 1 — **Declared**: The site says agents are welcome in its robots.txt. A permission, not a capability.
- tier 2 — **Probe-verified** (this site): We fetched the site and tested each signal ourselves. Dated, repeatable, re-checked on a schedule.
- tier 3 — **Behaviourally verified**: An agent completed the action end to end — booked, bought, submitted — and it worked.

## About this record

Known Good probes sites live and publishes what was tested and when.
Method: https://knowngood.sh/about.md · Rubric: https://knowngood.sh/benchmark

How we found this site: someone asked us to probe it.

## Where this sits

- directory: https://knowngood.sh/type/directory
- technology: https://knowngood.sh/category/technology
- Browse: https://knowngood.sh/browse
- Rubric: https://knowngood.sh/benchmark
