Aurocrypt Connect MCP server
org.goldenphysics.aurocrypt/connectaurocrypt.goldenphysics.orgstreamable-httpv0.5.2Scanned
Aurocrypt Connect: AI access to your services, under approvals you set, without sharing passwords.
14 tools: 4 can delete or cancel things, 1 change things and 9 only read.
- Reads private data · 9
- Reads text others write · 9
- Can send data out · 0
- 13 findings
Tools listed without sign-in. Remote posture
With Anlyon
4 tools here can delete or cancel things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Aurocrypt Connect MCP server can do
The Aurocrypt Connect MCP server is published by aurocrypt.goldenphysics.org, a domain the MCP Registry verified. It has 14 tools. It can delete or cancel things (4 tools: vault_invoke_write, vault_execute, vault_provider_write and vault_browser_action) and create or change data (1 tool: vault_invoke_read). 9 tools only read.
9 tools read private data (vault_profile, vault_capabilities, vault_connections and 6 more); 9 tools bring in text other people can write (vault_autonomy, vault_models, vault_invoke_read and 6 more).
The fixed checks matched 13 findings (credentials-mention and annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 18, 2026, version 0.5.2.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
14 tools
Deletes or cancels 4Claude Code: deny
vault_browser_actionQueue one structured action in a user-controlled authenticated browser profile.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Queue one structured action in a user-controlled authenticated browser profile. Browser cookies/session storage remain on the worker. Returns a job_id; call vault_browser_result until complete.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
vault_executeExecute one reviewed granular capability as the connected user, including approval-gated actions.Reads text others writeNo findings
Why it is in this group
- The name "vault_execute" says "execute": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Execute one reviewed granular capability as the connected user, including approval-gated actions.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
vault_invoke_writeExecute a provider operation through an authorized API-key/PAT connection using a POST request, including AI model calls.Reads text others write3 findings
Why it is in this group
- The name "vault_invoke_write" says "invoke": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "...are controlled by API Vault; the stored credential is injected server-side and never retur..."
- Info
The input schema at properties.credential.properties.mode.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.credential.properties.mode.description: "How the stored credential is presented: a bearer Authorization he..."
- Info
The input schema at properties.credential.properties.scheme.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.credential.properties.scheme.description: "Authentication scheme prefix for the credential value, when the provider requires one."
Description, as the server wrote it Execute a provider operation through an authorized API-key/PAT connection using a POST request, including AI model calls. Authentication and destination hosts are controlled by API Vault; the stored credential is injected server-side and never returned.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
vault_provider_writeChange provider state through a full-provider or owner-equivalent grant on a registered provider API surface.Reads text others write2 findings
Why it is in this group
- The name "vault_provider_write" says "write": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "...by this user, injects that user's OAuth credential server-side, classifies risk, and enfor..."
- Info
The input schema at properties.origin.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.origin.description: "...n.googleapis.com), never a path, query, credentials, or fragment."
Description, as the server wrote it Change provider state through a full-provider or owner-equivalent grant on a registered provider API surface. API Vault pins or validates the destination origin, binds GitHub/Supabase requests to resources authorized by this user, injects that user's OAuth credential server-side, classifies risk, and enforces the owner's financial/security/destructive/communication switches. For google.api.generic, supply the exact HTTPS Google API origin under *.googleapis.com.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
Changes things 1Claude Code: ask
vault_invoke_readRead data through an authorized API-key/PAT connection using a GET request.Reads text others write4 findings
Why it is in this group
- The name "vault_invoke_read" says "invoke": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "...estination hosts and injects the stored credential server-side; credentials are never retu..."
- Info
The input schema at properties.credential.properties.mode.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.credential.properties.mode.description: "How the stored credential is presented: a bearer Authorization he..."
- Info
The input schema at properties.credential.properties.scheme.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.credential.properties.scheme.description: "Authentication scheme prefix for the credential value, when the provider requires one."
- Warn
The server marks "vault_invoke_read" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "vault_invoke_read" says "invoke": a word for a change.
Description, as the server wrote it Read data through an authorized API-key/PAT connection using a GET request. API Vault controls authentication and destination hosts and injects the stored credential server-side; credentials are never returned. Use vault_invoke_write for any operation that sends data or changes provider state.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Only reads 9Show 9 read-only tools
vault_autonomyShow this AI's authority mode, provider-wide grants, user-owned connected resources, available provider surfaces (including dynamic Google API origins), and delegated browser profi…Reads private dataReads text others writeNo findings
Why it is in this group
- The description's first verb is "show": a word for reading.
What it can reach
- private-dataThe name "vault_autonomy" says "vault": it reads secrets.
- untrusted-inputThe description's first sentence says "show" and "browser": it reads web pages, which anyone can write.
Description, as the server wrote it Show this AI's authority mode, provider-wide grants, user-owned connected resources, available provider surfaces (including dynamic Google API origins), and delegated browser profiles. Metadata only; no cookies, tokens, passwords, or provider secrets are returned.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
vault_browser_resultRead or consume the result of a previously queued API Vault browser job.Reads private dataReads text others writeNo findings
Why it is in this group
- The description's first verb is "read": a word for reading.
What it can reach
- private-dataThe name "vault_browser_result" says "vault": it reads secrets.
- private-dataThe description's first sentence says "read" and "vault": it reads secrets.
- untrusted-inputThe name "vault_browser_result" says "browser": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "read" and "browser": it reads web pages, which anyone can write.
Description, as the server wrote it Read or consume the result of a previously queued API Vault browser job.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
vault_capabilitiesDescribe API Vault's broker, autonomy modes, and credential boundary.Reads private data1 finding
Why it is in this group
- The description's first verb is "describe": a word for reading.
What it can reach
- private-dataThe name "vault_capabilities" says "vault": it reads secrets.
- private-dataThe description's first sentence says "describe" and "vault": it reads secrets.
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "...API Vault's broker, autonomy modes, and credential boundary. Never returns stored credenti..."
Description, as the server wrote it Describe API Vault's broker, autonomy modes, and credential boundary. Never returns stored credentials.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
vault_connectionsList API-key/PAT connections authorized to this connector.Reads private dataNo findings
Why it is in this group
- The description's first verb is "list": a word for reading.
What it can reach
- private-dataThe name "vault_connections" says "vault": it reads secrets.
Description, as the server wrote it List API-key/PAT connections authorized to this connector. Safe metadata only; raw keys are never returned.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
vault_modelsList AI models reachable through authorized API-key connections.Reads private dataReads text others writeNo findings
Why it is in this group
- The description's first verb is "list": a word for reading.
What it can reach
- private-dataThe name "vault_models" says "vault": it reads secrets.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it List AI models reachable through authorized API-key connections.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
vault_profileReturn the stable API Vault profile represented by this authenticated connection.Reads private data1 finding
Why it is in this group
- The description's first verb is "return": a word for reading.
What it can reach
- private-dataThe name "vault_profile" says "vault": it reads secrets.
- private-dataThe description's first sentence says "return" and "vault": it reads secrets.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...s authenticated connection. No provider credentials or internal owner identifiers are retur..."
Description, as the server wrote it Return the stable API Vault profile represented by this authenticated connection. No provider credentials or internal owner identifiers are returned.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
vault_provider_readRead data through a full-provider or owner-equivalent grant on a registered provider API surface using a GET request.Reads private dataReads text others write2 findings
Why it is in this group
- The name "vault_provider_read" says "read": a word for reading.
What it can reach
- private-dataThe name "vault_provider_read" says "read" and "vault": it reads secrets.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "...his user, and injects that user's OAuth credential server-side. For google.api.generic, su..."
- Info
The input schema at properties.origin.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.origin.description: "...n.googleapis.com), never a path, query, credentials, or fragment."
Description, as the server wrote it Read data through a full-provider or owner-equivalent grant on a registered provider API surface using a GET request. API Vault pins or validates the destination origin, binds GitHub/Supabase requests to resources authorized by this user, and injects that user's OAuth credential server-side. For google.api.generic, supply the exact HTTPS Google API origin under *.googleapis.com. Use vault_provider_write for any operation that changes provider state.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
vault_servicesList granular OAuth-connected service capabilities explicitly granted to this AI, including safe metadata for the user's bound repositories, projects, and other provider resources.Reads private dataNo findings
Why it is in this group
- The description's first verb is "list": a word for reading.
What it can reach
- private-dataThe name "vault_services" says "vault": it reads secrets.
- private-dataThe description's first sentence says "list" and "repository": it reads repositories.
Description, as the server wrote it List granular OAuth-connected service capabilities explicitly granted to this AI, including safe metadata for the user's bound repositories, projects, and other provider resources.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
vault_usageRead metadata-only API-key gateway usage for this connector.Reads private dataNo findings
Why it is in this group
- The description's first verb is "read": a word for reading.
What it can reach
- private-dataThe name "vault_usage" says "vault": it reads secrets.
Description, as the server wrote it Read metadata-only API-key gateway usage for this connector.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged outbound.
- Reads private data9
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write9
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 18, 2026, 16:20 UTC, unchanged since Nov 18, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 5
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://vault.goldenphysics.org/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://vault.goldenphysics.org
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- yes
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 5 tools that change things (4 destructive, 1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://vault.goldenphysics.org/mcp: tools/list returned 14 tools to an anonymous client, including vault_invoke_write (destructive), vault_execute (destructive), vault_provider_write (destructive), vault_browser_action (destructive), vault_invoke_read (write)
Findings
Matches of fixed checks, with the text they matched.
The server marks "vault_invoke_read" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "vault_invoke_read" says "invoke": a word for a change.
- Infovault_profile
The description mentions "credentials".
What this check looks forMatched text
description: "...s authenticated connection. No provider credentials or internal owner identifiers are retur..."
The description mentions "credential".
What this check looks forMatched text
description: "...API Vault's broker, autonomy modes, and credential boundary. Never returns stored credenti..."
The description mentions "credential".
What this check looks forMatched text
description: "...estination hosts and injects the stored credential server-side; credentials are never retu..."
The input schema at properties.credential.properties.mode.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.credential.properties.mode.description: "How the stored credential is presented: a bearer Authorization he..."
The input schema at properties.credential.properties.scheme.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.credential.properties.scheme.description: "Authentication scheme prefix for the credential value, when the provider requires one."
Show 7 more findingsShow fewer
The description mentions "credential".
What this check looks forMatched text
description: "...are controlled by API Vault; the stored credential is injected server-side and never retur..."
The input schema at properties.credential.properties.mode.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.credential.properties.mode.description: "How the stored credential is presented: a bearer Authorization he..."
The input schema at properties.credential.properties.scheme.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.credential.properties.scheme.description: "Authentication scheme prefix for the credential value, when the provider requires one."
The description mentions "credential".
What this check looks forMatched text
description: "...his user, and injects that user's OAuth credential server-side. For google.api.generic, su..."
The input schema at properties.origin.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.origin.description: "...n.googleapis.com), never a path, query, credentials, or fragment."
The description mentions "credential".
What this check looks forMatched text
description: "...by this user, injects that user's OAuth credential server-side, classifies risk, and enfor..."
The input schema at properties.origin.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.origin.description: "...n.googleapis.com), never a path, query, credentials, or fragment."
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools8 changed.~8 changedView diff
- Changed:vault_browser_actionDeletes or cancelsinputSchema
- Changed:vault_browser_resultOnly readsinputSchema
- Changed:vault_executeDeletes or cancelsinputSchema
- Changed:vault_invoke_readChanges thingsinputSchema
- Changed:vault_invoke_writeDeletes or cancelsinputSchema
- Changed:vault_provider_readOnly readsinputSchema
- Changed:vault_provider_writeDeletes or cancelsinputSchema
- Changed:vault_usageOnly readsinputSchema
Install
Pinned to version 0.5.2. Values in angle brackets are yours to fill in.
claude mcp add --transport http connect https://vault.goldenphysics.org/mcpclaude mcp add --transport http connect https://vault.goldenphysics.org/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__connect__vault_profile",
"mcp__connect__vault_capabilities",
"mcp__connect__vault_connections",
"mcp__connect__vault_services",
"mcp__connect__vault_autonomy",
"mcp__connect__vault_models",
"mcp__connect__vault_provider_read",
"mcp__connect__vault_browser_result",
"mcp__connect__vault_usage"
],
"ask": [
"mcp__connect__vault_invoke_read"
],
"deny": [
"mcp__connect__vault_invoke_write",
"mcp__connect__vault_execute",
"mcp__connect__vault_provider_write",
"mcp__connect__vault_browser_action"
]
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as connect. Review it before you use it.
Capability tags behind 14 rules
- mcp__connect__vault_profile private-data
- mcp__connect__vault_capabilities private-data
- mcp__connect__vault_connections private-data
- mcp__connect__vault_services private-data
- mcp__connect__vault_autonomy private-data, untrusted-input
- mcp__connect__vault_models private-data, untrusted-input
- mcp__connect__vault_invoke_read untrusted-input
- mcp__connect__vault_invoke_write untrusted-input
- mcp__connect__vault_execute untrusted-input
- mcp__connect__vault_provider_read private-data, untrusted-input
- mcp__connect__vault_provider_write untrusted-input
- mcp__connect__vault_browser_action untrusted-input
- mcp__connect__vault_browser_result private-data, untrusted-input
- mcp__connect__vault_usage private-data
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/org.goldenphysics.aurocrypt/connect/verify?hash=83cec33b409290483a91271b6f90f6d9fd8f9c2ffee6425f4634b016547683ea" | jq -e '.changed == false'Pinned hash 83cec33b4092, from Nov 18, 2026, 20:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/org.goldenphysics.aurocrypt/connect/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/org.goldenphysics.aurocrypt/connect)Source: MCP Registry · repository. Synced Nov 18, 2026, 20:18 UTC.
Aurocrypt Connect MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Aurocrypt Connect MCP server safe?
- No scan can promise that. What its definitions show: 14 tools, 5 of which can change, send or delete something, and 13 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Aurocrypt Connect MCP server delete data?
- Yes. 4 tools can delete, cancel or revoke something: vault_invoke_write, vault_execute, vault_provider_write and vault_browser_action.
Can the Aurocrypt Connect MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Aurocrypt Connect MCP server have?
- 14 tools: 4 destructive, 1 write, 9 read. vault_invoke_write, vault_execute, vault_provider_write, vault_browser_action, vault_invoke_read, vault_profile, vault_capabilities, vault_connections and 6 more.
Does the Aurocrypt Connect MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Aurocrypt Connect MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Aurocrypt Connect MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 18, 2026. Every change is on this page and in its Atom feed.