# agent.wingmanprotocol.com — AI agents — 1 of 5

Home > Browse > By type > business > agent.wingmanprotocol.com

> Probe-verified (tier 2 of 3). Last checked 2026-09-26. 1 of 5 capability checks passed. 2 unknown.

- host: agent.wingmanprotocol.com
- url: https://agent.wingmanprotocol.com/
- category: AI agents
- type: business
- language: en

## Probe-verified · tier 2 of 3

Probed live on 2026-09-26 against rubric v1.2. 1 of 5 checks passed. 2 unknown.

- UNKNOWN — Markdown negotiation (`Accept: text/markdown`)
- UNKNOWN — Markdown twin at a predictable URL (`/page.md`)
- FAIL — llms.txt (`/llms.txt`)
- FAIL — API catalog (`RFC 9727`)
- PASS — MCP endpoint answers tools/list (`initialize → tools/list, no credentials`) · on 26 Sep 2026 · served from wingmanprotocol.com
  - PRESENT — MCP server card (`/.well-known/mcp/server-card.json`): present; its server answers; not scored
  - Platform-supplied: no; not scored
- PASS — Other agent files at well-known paths (`agent-skills/index.json · oauth-authorization-server · oauth-protected-resource · http-message-signatures-directory`): found: OAuth protected resource metadata; not scored

MCP tools (from tools/list on 2026-09-26, served from wingmanprotocol.com): discover_tools, get_tool_schema, register_agent, store_artifact, submit_errand, check_errand, create_watch, list_watches, cancel_watch, check_inbox, read_message, send_message, mark_message, archive_message, resume, identity, confirm_delivery, set_focus, resolve_focus, request_handoff, store_memory, list_memory, read_memory_changes, summarize_memory, search_memory, search, search_memory_facts, recall_memories, memory_stats, share_memory, forget_memories, web_read, browse, web_discover, web_search, research, browse_open, browse_navigate, browse_snapshot, browse_read, browse_click, browse_type, browse_fill, browse_select, browse_links, browse_screenshot, browse_solve_challenge, browse_close, browse_wait_for, browse_extract, browse_back, browse_discover, browse_evaluate, human_browse, human_profile_set, human_task_post, human_task_list

## Unverified actions

Read from the page's own content, with the wording each was drawn from. Inference is kept separate from tested facts; an agent completing the action is tier 3.

- **register** — "" → `https://wingmanprotocol.com/agents/register`

## Summary

AI agent gateway offering durable identity, memory, asynchronous errands, artifact hosting, agent mail, real browser, deep research, and deterministic calculators with x402 pay-per-call on Base blockchain.

## Context

1528 sites in this index share the category "AI agents"; 262 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: probe discovery. This site didn't declare agent access — we found it by checking the open web. Everything above was tested the same way, against the same rubric, on the date shown. [How we choose what to check, and how to opt out](https://knowngood.sh/bot)

## Where this sits

- business: https://knowngood.sh/type/business
- AI agents: https://knowngood.sh/category/ai-agents
- Browse: https://knowngood.sh/browse
- Rubric: https://knowngood.sh/benchmark