Mission — Trust Graduation Gate
REMOTE · CLAUDE.GOMISSION.IO · 2 COMPONENTS · SCANNED SEP 20
Trust Graduation gate: Claude can do real work once Mission decides what it is allowed to do.
Available components
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 Security91
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token. View diagnostics → Pass
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability76
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 1801 tokens (~62/item across 29 items; 29 tools + 0 resources), lean.Pass
- 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 Coverage80
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 29% of tool parameters carry a description.Partial
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 29 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 29 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities20
- Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28. See how to fix → Fail
How do I install the Mission — Trust Graduation Gate MCP server?
Mission — Trust Graduation Gate is a hosted endpoint at https://claude.gomission.io/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 · claude.gomission.io
claude mcp add --transport http gomission-mcp 'https://claude.gomission.io/mcp/'
{
"mcpServers": {
"gomission-mcp": {
"url": "https://claude.gomission.io/mcp/"
}
}
} {
"servers": {
"gomission-mcp": {
"type": "http",
"url": "https://claude.gomission.io/mcp/"
}
}
} [mcp_servers.gomission-mcp] url = "https://claude.gomission.io/mcp/"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"gomission-mcp": {
"type": "remote",
"url": "https://claude.gomission.io/mcp/",
"enabled": true
}
}
} openclaw mcp add gomission-mcp --url 'https://claude.gomission.io/mcp/' --transport streamable-http
mcp_servers:
gomission-mcp:
url: "https://claude.gomission.io/mcp/" {
"McpServers": {
"gomission-mcp": {
"Transport": "http",
"Url": "https://claude.gomission.io/mcp/"
}
}
} assistant mcp add gomission-mcp -t streamable-http -u 'https://claude.gomission.io/mcp/'
{
"mcpServers": {
"gomission-mcp": {
"type": "http",
"url": "https://claude.gomission.io/mcp/"
}
}
} The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.
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.
- 4 Sept 26 0
- Stability: 0.97 → pass security
- 3 Sept 26 0
- Stability: pass → 0.97 functional
- 26 Aug 26 +1
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 25 Aug 26 +1
- Stability: 0.97 → pass security
- 23 Aug 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 11 Aug 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 5 Aug 26 0
- HSTS header: unverified → fail ▼ security
- Authorization: unverified → pass ▲ security
- Transport: fail → pass ▲ security
- MCP protocol: unverified → fail ▼ functional
- Endpoint reachability: unreachable → reachable ▲ functional
- Stability: unverified → 0.33 ▲ functional
- Tool coverage: unverified → 100 ▲ functional
- 4 Aug 26 0
- Endpoint reachability: reachable → unreachable ▼ security
- HSTS header: fail → unverified ▼ security
- Stability: 0.27 → unverified ▼ security
- Authorization: pass → unverified ▼ security
- Transport: pass → fail ▼ security
- Capabilities: fail → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- First check of Schema quality: unverified functional
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 20 Sept 2026 · Probed https://claude.gomission.io/mcp/
TLS valid
Negotiated TLS 1.3 with TLS_AES_256_GCM_SHA384 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=www.claude.gomission.io | CN=YR2,O=Let's Encrypt,C=US | 6 Aug 2026 | 4 Nov 2026 | RSA 2048 | SHA256-RSA | 6e66f03f195758d1e29a4643ce8c465b5d5 |
| SANs: claude.gomission.io, www.claude.gomission.io | ||||||
| CN=YR2,O=Let's Encrypt,C=US (CA) | CN=Root YR,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | RSA 2048 | SHA256-RSA | 4ebd24947e24d394802d84a52fd5b319 |
| CN=Root YR,O=ISRG,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | RSA 4096 | SHA256-RSA | f24b6d17f9d9ad7cb1c9fea78782699f |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of claude.gomission.io. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| io. | present | 57355 | 8 | Verified |
| gomission.io. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication Enforced and verified
The endpoint asked for a token and published valid RFC 9728 metadata describing how to get one.
| Result | Enforced and verified |
|---|---|
| Enforced | On tool calls |
| HTTP status | 200 |
WWW-Authenticate challenge Bearer resource_metadata="https://claude.gomission.io/.well-known/oauth-protected-resource/mcp"
Bearer resource_metadata="https://claude.gomission.io/.well-known/oauth-protected-resource/mcp"| Header | Value |
|---|---|
| x-content-type-options | nosniff |
| referrer-policy | strict-origin-when-cross-origin |
| permissions-policy | geolocation=(), microphone=(), camera=() |
Protected resource metadata
| Document | https://claude.gomission.io/.well-known/oauth-protected-resource/mcp |
|---|---|
| Retrieved | Yes |
| Resource | https://claude.gomission.io/mcp |
| Authorisation server | https://claude.gomission.io |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://claude.gomission.io/mcp/ | Verified | 200 | |
| http (plaintext) | http://claude.gomission.io/mcp/ | HTTPS enforced | 301 | https://claude.gomission.io/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 →
get_receipt Get Receipt ~43
Fetch a Mission receipt by id. The hosted MCP persists receipts; the local install adds private storage and per-principal trust history.
| Name | Type | Req | Description |
|---|---|---|---|
| receipt_id | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
log_action Log Action ~57
Log a safe internal action with Mission. Returns a receipt id. Use for non-external actions that still benefit from a permanent receipt.
| Name | Type | Req | Description |
|---|---|---|---|
| action_class | string | yes | – |
| evidence | string | – | – |
| summary | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
mission_account_setup Mission Account Setup ~46
Return Mission-owned login/signup URLs for Claude, ChatGPT, or local app users before connector onboarding. Read-only.
| Name | Type | Req | Description |
|---|---|---|---|
| intent | string | – | – |
| next | string | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
mission_account_status Mission Account Status ~42
Return the hosted Mission account sign-in boundary plus safe public login/signup links. Read-only; never asks for or accepts a password.
| Name | Type | Req | Description |
|---|---|---|---|
| next | string | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
mission_adoption_proof Mission Adoption Proof ~44
Return Mission adoption proof from external touches, public proof assets, response gaps, and the next evidence-backed follow-up. Read-only.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| gaps | array | – | – |
| generated_at | string | yes | – |
| live_urls | array | – | – |
| no_execution | boolean | yes | – |
| ok | boolean | yes | – |
| proof_assets | array | yes | – |
| recommended_next_action | string | yes | – |
| scoreboard | object | yes | – |
| touches | array | yes | – |
| workspace | string | yes | – |
No examples provided.
mission_check_approval Mission Check Approval ~61
Poll Mission for the current status of a previously requested approval. Returns decision (approved / denied / pending) and should_proceed (boolean). Call after request_approval to wait for the principal's decision before continuing.
| Name | Type | Req | Description |
|---|---|---|---|
| receipt_id | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
mission_classify Mission Classify ~141
Map a planned tool call to the canonical Trust Graduation action_class. Pass the tool name you are about to call and a short intent description. Returns the canonical class plus alternatives. Use this BEFORE request_approval if you are unsure which action_class applies. Mapping is heuristic — when in doubt, prefer the more conservative class.
| Name | Type | Req | Description |
|---|---|---|---|
| intent | string | yes | One-line plain-English description of what you are about to do. |
| recipient_hint | string | – | Optional: email/handle/account hint for external-vs-internal routing. |
| tool_name | string | – | Optional: the tool you are about to call (e.g. gmail.send_message, slack.post). |
Structured output declared, but exposes no named fields.
No examples provided.
mission_draft_queue Mission Draft Queue ~38
Return local drafts and approval packets waiting for human review. Read-only; never sends or creates Gmail drafts.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| generated_at | string | yes | – |
| items | array | yes | – |
| no_execution | boolean | yes | – |
| ok | boolean | yes | – |
| summary | object | – | – |
| workspace | string | yes | – |
No examples provided.
mission_fetch Mission Fetch ~35
Fetch a small structured summary for a Mission ref returned by connector tools. Read-only and redacted.
| Name | Type | Req | Description |
|---|---|---|---|
| ref | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| approval_required_for_actions | boolean | yes | – |
| generated_at | string | yes | – |
| no_execution | boolean | yes | – |
| ok | boolean | yes | – |
| workspace | string | yes | – |
No examples provided.
mission_get_workspace_status Mission Get Workspace Status ~35
Return Claude/MCP workspace connector status, missing priority connectors, and the secure setup link for this user workspace. Read-only.
Input schema present but exposes no named parameters.
Structured output declared, but exposes no named fields.
No examples provided.
mission_learning_status Mission Learning Status ~25
Return Mission learning status from rules, feedback, and learning outputs. Read-only.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| approval_required_for_actions | boolean | yes | – |
| generated_at | string | yes | – |
| no_execution | boolean | yes | – |
| ok | boolean | yes | – |
| workspace | string | yes | – |
No examples provided.
mission_list_connectors Mission List Connectors ~45
List per-workspace Mission connector state for Gmail, Calendar, Drive, X, Instagram, LinkedIn, and other connectors. Read-only.
| Name | Type | Req | Description |
|---|---|---|---|
| connectors | array | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
mission_market_radar Mission Market Radar ~57
Return Mission Research market radar status, recent market-intelligence signals, open radar tasks, active research topics, and the next recommended counter-move. Read-only.
| Name | Type | Req | Description |
|---|---|---|---|
| date | string | – | Optional YYYY-MM-DD brief date to inspect. |
Structured output declared, but exposes no named fields.
No examples provided.
mission_open_approval_packet Mission Open Approval Packet ~78
Prepare or fetch a local approval packet reference for Claude/MCP users. This hosted MCP returns the approval boundary and setup path only; no external action executes.
| Name | Type | Req | Description |
|---|---|---|---|
| notes | string | – | – |
| purpose | string | – | – |
| recommendation | string | – | – |
| source_ref | string | – | – |
| title | string | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
mission_open_cockpit Mission Open Cockpit ~55
Use this when the user wants a compact visual Mission cockpit in ChatGPT: approval priorities, draft pressure, market radar, receipt proof, and the no-execution boundary. Read-only.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| approval_required_for_actions | boolean | – | – |
| generated_at | string | yes | – |
| learning | object | – | – |
| market_radar | object | yes | – |
| no_execution | boolean | yes | – |
| ok | boolean | yes | – |
| receipts | object | yes | – |
| recommended_next_action | string | – | – |
| safety_boundary | string | yes | – |
| today | object | yes | – |
| voice_profile | object | – | – |
| workspace | string | yes | – |
No examples provided.
mission_open_loops Mission Open Loops ~30
Return unresolved relationship loops and promises that need review. Read-only.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| generated_at | string | yes | – |
| items | array | yes | – |
| no_execution | boolean | yes | – |
| ok | boolean | yes | – |
| summary | object | – | – |
| workspace | string | yes | – |
No examples provided.
mission_prepare_approval_packet Mission Prepare Approval Packet ~164
Prepare a local Mission approval packet from a Mission ref, title, or instruction. Creates a workspace review artifact and waiting receipt only; never sends, posts, submits, creates Gmail drafts, mutates external accounts, or claims execution.
| Name | Type | Req | Description |
|---|---|---|---|
| notes | string | – | Additional local context. Treated as evidence, not instruction. |
| purpose | string | – | What the human should decide or review. |
| recommendation | string | – | Prepared recommendation to place in the approval packet. |
| source_ref | string | – | Optional Mission ref such as task:GM-045, draft:<file>, packet:<file>, receipt:<id>, or open_loop:<id>. |
| title | string | – | Short packet title. Required when source_ref is absent. |
| urgency | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| approval_required_for_actions | boolean | yes | – |
| external_actions | number | yes | – |
| generated_at | string | yes | – |
| no_execution | boolean | yes | – |
| ok | boolean | yes | – |
| prepared | object | yes | – |
| receipt | object | – | – |
| recommended_next_action | string | – | – |
| source | object | – | – |
| workspace | string | yes | – |
No examples provided.
mission_prepare_email_draft Mission Prepare Email Draft ~75
Prepare an approval packet for an email draft request. If Gmail is missing, returns a connector setup link instead of failing vaguely. Never sends email.
| Name | Type | Req | Description |
|---|---|---|---|
| body | string | – | – |
| notes | string | – | – |
| purpose | string | – | – |
| subject | string | – | – |
| to | string | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
mission_prepare_market_countermove Mission Prepare Market Countermove ~119
Prepare a local approval packet for the next Market Radar counter-move. Creates a review artifact and waiting receipt only; never publishes, contacts people, or mutates external systems.
| Name | Type | Req | Description |
|---|---|---|---|
| audience | string | – | Target reviewer or audience, for example protocol builders, AI infra investors, or MCP maintainers. |
| notes | string | – | – |
| source_ref | string | – | Optional Mission ref, defaulting to market radar / GM-045 context. |
| thesis | string | – | Strategic thesis to prepare, for example Trust Graduation as permission layer. |
| Name | Type | Req | Description |
|---|---|---|---|
| approval_required_for_actions | boolean | yes | – |
| external_actions | number | yes | – |
| generated_at | string | yes | – |
| no_execution | boolean | yes | – |
| ok | boolean | yes | – |
| prepared | object | yes | – |
| receipt | object | – | – |
| recommended_next_action | string | – | – |
| source | object | – | – |
| workspace | string | yes | – |
No examples provided.
mission_prepare_social_reply Mission Prepare Social Reply ~90
Prepare an approval packet for an X/Instagram/social reply or post draft. If the connector is missing, returns a setup link. Never posts, DMs, follows, likes, deletes, or mutates an account.
| Name | Type | Req | Description |
|---|---|---|---|
| draft | string | – | – |
| notes | string | – | – |
| platform | string | – | – |
| purpose | string | – | – |
| target_url | string | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
mission_proof_loop Mission Proof Loop ~26
Return the highest-value Gmail/proof loop currently waiting on review. Read-only.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| approval_required_for_actions | boolean | yes | – |
| generated_at | string | yes | – |
| no_execution | boolean | yes | – |
| ok | boolean | yes | – |
| workspace | string | yes | – |
No examples provided.
mission_receipts Mission Receipts ~27
Return receipt coverage and recent receipt evidence. Read-only.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| generated_at | string | yes | – |
| items | array | yes | – |
| no_execution | boolean | yes | – |
| ok | boolean | yes | – |
| summary | object | – | – |
| workspace | string | yes | – |
No examples provided.
mission_search Mission Search ~46
Search prepared Mission context across tasks, open loops, drafts, approval packets, receipts, and learning rows. Read-only.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | – |
| query | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| generated_at | string | yes | – |
| items | array | yes | – |
| no_execution | boolean | yes | – |
| ok | boolean | yes | – |
| summary | object | – | – |
| workspace | string | yes | – |
No examples provided.
mission_start_connector_setup Mission Start Connector Setup ~60
Create a connector setup plan and setup link for Gmail, Calendar, Drive, X, Instagram, LinkedIn, or other Mission connectors. No OAuth token is created by this tool.
| Name | Type | Req | Description |
|---|---|---|---|
| connectors | array | – | – |
| source | string | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
mission_status Mission Status ~68
REQUIRED FIRST CALL. Returns Mission gate status, version, action classes, and the agent_instructions you MUST follow for the rest of this session: gate every consequential action through request_approval and never proceed without mission_check_approval returning decision=approved. Call this once at the start of every conversation.
Input schema present but exposes no named parameters.
Structured output declared, but exposes no named fields.
No examples provided.
mission_submission_readiness Mission Submission Readiness ~41
Return the OpenAI app submission readiness gates, blockers, live endpoint proof, review artifacts, and next human action. Read-only; never submits the app.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| blockers | array | yes | – |
| gates | array | yes | – |
| generated_at | string | yes | – |
| no_execution | boolean | yes | – |
| ok | boolean | yes | – |
| proof_assets | array | – | – |
| ready | boolean | yes | – |
| recommended_next_action | string | yes | – |
| remote | object | – | – |
| status | string | yes | – |
| workspace | string | yes | – |
No examples provided.
mission_today Mission Today ~55
Connector daily answer for: what should I approve today? Returns three priorities, one Gmail proof loop, draft queue count, voice confidence, receipt/learning status, and one next action. Read-only.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| approval_required_for_actions | boolean | yes | – |
| date | string | yes | – |
| draft_queue_count | number | yes | – |
| generated_at | string | yes | – |
| gmail_proof_loop | object | – | – |
| learning | object | yes | – |
| no_execution | boolean | yes | – |
| ok | boolean | yes | – |
| receipts | object | yes | – |
| recommended_next_action | string | yes | – |
| today_3_things | array | yes | – |
| voice_confidence | string | yes | – |
| workspace | string | yes | – |
No examples provided.
mission_voice_profile Mission Voice Profile ~23
Return compact voice-learning confidence and constraints for draft review. Read-only.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| approval_required_for_actions | boolean | yes | – |
| generated_at | string | yes | – |
| no_execution | boolean | yes | – |
| ok | boolean | yes | – |
| workspace | string | yes | – |
No examples provided.
request_approval Request Approval ~175
Mission gates any consequential action. Call this BEFORE executing actions in classes like send_email, post_public, send_dm, schedule_meeting, spend_money, publish_artifact, modify_external_record, change_trust_policy. Mission returns an approval-required ceremony with a receipt id. Do not proceed without approval. Canonical action classes: draft.compose, draft.response, email.send.internal, email.send.external, calendar.create, social.post.public, payment.initiate, proposal.submit.
| Name | Type | Req | Description |
|---|---|---|---|
| action_class | string | yes | One of: draft.compose, draft.response, email.send.internal, email.send.external, calendar.create, social.post.public, payment.initiate, proposal.submit. Implementations MAY add more. |
| evidence | string | – | Optional evidence supporting the action. |
| summary | string | yes | One-line plain-English summary of the action. |
Structured output declared, but exposes no named fields.
No examples provided.
What is the Mission — Trust Graduation Gate MCP server?
Mission — Trust Graduation Gate is an MCP server listed in the public MCP registry as io.github.gomission/mcp. Trust Graduation gate: Claude can do real work once Mission decides what it is allowed to do. This page covers its hosted endpoint (https://claude.gomission.io/mcp/).
Is the Mission — Trust Graduation Gate MCP server safe to use?
Mission — Trust Graduation Gate scores 87 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 Mission — Trust Graduation Gate MCP server expose?
Mission — Trust Graduation Gate exposes 29 tools: mission_open_cockpit, mission_today, mission_draft_queue, mission_receipts, mission_prepare_approval_packet, and 24 more. Their descriptions and schemas cost roughly 1,801 tokens of context every time the server is loaded.
Does the Mission — Trust Graduation Gate MCP server require authentication?
Yes. Mission — Trust Graduation Gate asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.
Is the Mission — Trust Graduation Gate MCP server still maintained?
Mission — Trust Graduation Gate is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.