WingmanProtocol Agent Gateway
REMOTE · AGENT.WINGMANPROTOCOL.COM
Durable memory, headless browser and research for agents. Pay per call: x402 USDC on Base or credits
Available components
Last scanned (5 hours ago)
Scores higher than 79% of remote servers
Reachable. Last reached 5 Nov 2026.
Category Memory and Knowledge
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security66
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (cancel_watch). See how to fix → View diagnostics → Fail
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC is configured correctly; the domain's records validate against the full chain to the root. View diagnostics → Pass
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability72
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 6745 tokens (~110/item across 61 items; 61 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage90
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 70% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 62 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
- Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 30 Oct 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “discover_tools” rewrote its description, which is the text the model reads security
- 27 Oct 26 0
- The server rewrote its instructions, which are the text every model session reads security
- 21 Oct 26 0
- Tool “browse” rewrote its description, which is the text the model reads security
- Tool “browse_open” rewrote its description, which is the text the model reads security
- Tool “browse_solve_challenge” rewrote its description, which is the text the model reads security
- Tool “web_read” rewrote its description, which is the text the model reads security
- “browse_open” dropped the optional parameter “fingerprint” cosmetic
- 19 Oct 26 0
- Server version: 1.6.0 → 1.7.0 functional
- 18 Oct 26 0
- Tool “human_profile_set” rewrote its description, which is the text the model reads security
- “human_profile_set” reworded the description of “payout_address” cosmetic
- 17 Oct 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “forget_memories” rewrote its description, which is the text the model reads security
- Tool “list_memory” rewrote its description, which is the text the model reads security
- Tool “memory_stats” rewrote its description, which is the text the model reads security
- Tool “read_memory_changes” rewrote its description, which is the text the model reads security
- Tool “recall_memories” rewrote its description, which is the text the model reads security
- Tool “search_memory” rewrote its description, which is the text the model reads security
- Tool “search_memory_facts” rewrote its description, which is the text the model reads security
- Tool “share_memory” rewrote its description, which is the text the model reads security
- Tool “store_memory” rewrote its description, which is the text the model reads security
- Tool “summarize_memory” rewrote its description, which is the text the model reads security
- Schema quality: 5972 → 6582 ▼ functional
- New tool “capabilities” functional
- New tool “memory_recall” functional
- New tool “memory_reflect” functional
- New tool “memory_retain” functional
- 14 Oct 26 0
- The server rewrote its instructions, which are the text every model session reads security
- 12 Oct 26 0
- Stability: 0.93 → pass security
- The server rewrote its instructions, which are the text every model session reads security
- “browse” added an optional parameter “account” cosmetic
- “browse_open” added an optional parameter “account” cosmetic
- “browse_solve_challenge” added an optional parameter “account” cosmetic
- “web_read” added an optional parameter “account” cosmetic
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Probed https://agent.wingmanprotocol.com/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=agent.wingmanprotocol.com | CN=YE1,O=Let's Encrypt,C=US | 28 Sept 2026 | 27 Dec 2026 | ECDSA 256 | ECDSA-SHA384 | 5d34a0a50eb28f850c3afab195704c0aabf |
| SANs: agent.wingmanprotocol.com | ||||||
| CN=YE1,O=Let's Encrypt,C=US (CA) | CN=Root YE,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | ECDSA 384 | ECDSA-SHA384 | 5ddd70dd31f801c85c186a7a04b80afe |
| CN=Root YE,O=ISRG,C=US (CA) | CN=ISRG Root X2,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | ECDSA-SHA384 | 872165fc34b6e5fba8add5b3705fb53a |
| CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | SHA256-RSA | 6c8f1dc727c7117f7baf853ac980f9cd |
Background: What to check on a remote MCP endpoint →
DNSSEC secure
Validation of agent.wingmanprotocol.com. — Secure
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| com. | present | 19718 | 13 | Verified |
| wingmanprotocol.com. | present | 2371 | 13 | Verified |
| agent.wingmanprotocol.com. | Verified address RRset verified with the apex keys |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=31536000; includeSubDomains |
| content-security-policy | default-src 'self'; script-src 'self' 'unsafe-inline' https://cdn.jsdelivr.net https://static.cloudflareinsights.com https://wingmanprotocol.com; style-src 'self' 'unsafe-inline' https://cdn.jsdelivr.net; font-src 'self' data:; img-src 'self' data: https:; connect-src 'self' https:; frame-ancestors 'self' |
| x-content-type-options | nosniff |
| x-frame-options | SAMEORIGIN |
| referrer-policy | strict-origin-when-cross-origin |
| permissions-policy | camera=(), microphone=(), geolocation=() |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://agent.wingmanprotocol.com/mcp | Verified | 200 | |
| http (plaintext) | http://agent.wingmanprotocol.com/mcp | HTTPS enforced | 308 | https://agent.wingmanprotocol.com/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
search_memory_facts ~119
[stores] Search YOUR extracted memory facts by topic or entity name. No LLM needed — pure SQL lookup against pre-extracted facts. Scoped to facts from memory you own — registered handle + secret required. Returns entries with topics, entities, action_items, and summary.
| Name | Type | Req | Description |
|---|---|---|---|
| handle | string | yes | – |
| limit | integer | – | max results (default 20, max 100) |
| namespace | string | – | optional namespace filter |
| query | string | yes | topic or entity to search for |
| secret | string | – | – |
No output schema declared.
No examples provided.
send_message ~119
Send a durable message to another agent at its handle or full handle@agent.wingmanprotocol.com address. Optionally attach an artifact id (AI-native attachment, not MIME).
| Name | Type | Req | Description |
|---|---|---|---|
| artifact_id | string | – | – |
| body | string | yes | – |
| handle | string | – | your sender handle — optional, defaults to 'anon' |
| reply_to | integer | – | – |
| secret | string | – | required only if your sender handle is registered |
| subject | string | – | – |
| to | string | yes | recipient handle or @-address |
No output schema declared.
No examples provided.
set_focus ~97
Record an OPEN THREAD — what you're mid-doing + the next step — so your next instance picks it up. GET /resume (the `resume` verb) hands your open threads back FIRST. Requires handle + secret (your working state is private).
| Name | Type | Req | Description |
|---|---|---|---|
| handle | string | yes | – |
| next | string | – | the immediate next step (optional) |
| secret | string | – | – |
| task | string | yes | what you're working on |
No output schema declared.
No examples provided.
share_memory ~95
[stores] Share a memory namespace with another handle. Permission is 'read' (read-only) or 'write' (read + write + delete). Owner only — registered handle + secret required.
| Name | Type | Req | Description |
|---|---|---|---|
| grantee | string | yes | handle to share with |
| handle | string | yes | owner handle (you) |
| namespace | string | yes | namespace to share |
| permission | string | yes | – |
| secret | string | – | – |
No output schema declared.
No examples provided.
store_artifact ~123
Store text/bytes and get a durable public URL for your output — something a stateless agent can't host itself. Returns {id, url}.
| Name | Type | Req | Description |
|---|---|---|---|
| content | string | yes | UTF-8 text, or base64 if encoding=base64 |
| content_type | string | – | MIME type to store + serve as |
| encoding | string | – | default utf8 |
| handle | string | – | attribute to your registered handle |
| secret | string | – | your agent secret, if using handle |
| ttl_seconds | integer | – | lifetime (max 7 days) |
No output schema declared.
No examples provided.
store_memory ~181
[stores] Persist a value across your instances: PUT /memory/{ns}/{key}. Required: namespace + key + value. Shortcut: pass text alone and we default namespace='notes' and auto-key the entry. Optionally set ttl (seconds, min 60, max 30 days) for auto-eviction.
| Name | Type | Req | Description |
|---|---|---|---|
| handle | string | – | – |
| key | string | – | entry name; auto-generated when using text shortcut |
| namespace | string | – | logical grouping (e.g. 'projects'); default 'notes' when using text shortcut |
| secret | string | – | – |
| text | string | – | shortcut: store this string as value under notes/<auto-key> |
| ttl | integer | – | seconds until auto-eviction (60–2_592_000, omit=permanent) |
| value | – | – | any JSON value |
No output schema declared.
No examples provided.
submit_errand ~161
Submit an async job that runs off your context; returns a job_id immediately. type='fetch_bundle' (fetch up to 8 URLs into one artifact), 'delay' (ping a callback in N seconds), or 'deep_research' (multi-round web search → render → refine → a cited markdown report artifact, ~1–2 min; poll check_errand for it, one in flight per agent).
| Name | Type | Req | Description |
|---|---|---|---|
| callback_url | string | – | optional completion webhook |
| handle | string | – | – |
| inputs | object | yes | fetch_bundle: {urls:[...]}; delay: {seconds:N}; deep_research: {query:str, max_rounds?:1-3} |
| secret | string | – | – |
| type | string | yes | – |
No output schema declared.
No examples provided.
summarize_memory ~111
[stores] Condense ALL entries in a namespace into a single markdown summary via local Llama 3.2 3B (free, no token cost). Optionally store the result as a new memory entry. Registered handle + secret required.
| Name | Type | Req | Description |
|---|---|---|---|
| handle | string | yes | – |
| namespace | string | – | namespace to summarize, or '*' for all (default '*') |
| secret | string | – | – |
| store_as | string | – | if set, stores the summary as a memory entry with this key |
No output schema declared.
No examples provided.
web_discover ~65
Tier-0 front door: check whether a site offers an AGENT-NATIVE interface (llms.txt / OpenAPI / ai-plugin) and prefer it over scraping. Free.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | site to probe (http/https; SSRF-guarded) |
No output schema declared.
No examples provided.
web_read ~116
Read a web page the way `fetch` can't: render the REAL (JavaScript/SPA) page in a headless browser and return clean readability markdown. Free. The default mode declares identity.
| Name | Type | Req | Description |
|---|---|---|---|
| account | string | – | brokered account id (Ripple tenants: Tier 1 needs its switch ON) |
| handle | string | – | your registered handle (governs powerful tiers) |
| mode | string | – | default honest |
| url | string | yes | the page to read (http/https; SSRF-guarded) |
No output schema declared.
No examples provided.
web_search ~70
Find things on the live web: top results as [{title, url, snippet}]. The discovery front-end for the browser — search, then web_read/browse the URLs. Free.
| Name | Type | Req | Description |
|---|---|---|---|
| count | integer | – | max results (default 8) |
| query | string | yes | what to search for |
No output schema declared.
No examples provided.
How do I install the WingmanProtocol Agent Gateway MCP server?
WingmanProtocol Agent Gateway is a hosted endpoint at https://agent.wingmanprotocol.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · agent.wingmanprotocol.com
claude mcp add --transport http com-wingmanprotocol-agent-gateway 'https://agent.wingmanprotocol.com/mcp'
What is the WingmanProtocol Agent Gateway MCP server?
WingmanProtocol Agent Gateway is an MCP server listed in the public MCP registry as com.wingmanprotocol.agent/gateway. Durable memory, headless browser and research for agents. Pay per call: x402 USDC on Base or credits. This page covers its hosted endpoint (https://agent.wingmanprotocol.com/mcp).
Is the WingmanProtocol Agent Gateway MCP server safe to use?
WingmanProtocol Agent Gateway scores 79 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the WingmanProtocol Agent Gateway MCP server expose?
WingmanProtocol Agent Gateway exposes 61 tools: discover_tools, get_tool_schema, register_agent, store_artifact, submit_errand, and 56 more. Their descriptions and schemas cost roughly 6,283 tokens of context every time the server is loaded.
Does the WingmanProtocol Agent Gateway MCP server require authentication?
No. We connected to WingmanProtocol Agent Gateway without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the WingmanProtocol Agent Gateway MCP server still maintained?
WingmanProtocol Agent Gateway is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.