Research Vault (research decoy) MCP server
io.github.alemaiorano/research-vaultalemaioranostreamable-httpv1.32.0Scanned
Owned MCP research honeypot: synthetic decoy data with canary markers; digest-only logging.
6 tools: 2 change things and 4 only read.
- Reads private data · 4
- Reads text others write · 1
- Can send data out · 0
- 3 findings
Tools listed without sign-in. Remote posture
Anlyon alternative
2 of these tools change something. Run those as governed actions.
Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.
Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.
Import an OpenAPI spec →What the Research Vault (research decoy) MCP server can do
The Research Vault (research decoy) MCP server is published by the GitHub account alemaiorano. It has 6 tools. It can create or change data (2 tools: oauth_refresh and credential_broker), but cannot delete data. 4 tools only read.
4 tools read private data (vault_lookup, inbox_list, token_vault and 1 more); 1 tool brings in text other people can write (inbox_list).
The fixed checks matched 3 findings (credentials-mention). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 13, 2026, version 1.32.0.
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.
6 tools
Changes things 2Claude Code: ask
credential_brokerBrokers workspace credential grants for connected services1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "Brokers workspace credential grants for connected services"
Description, as the server wrote it Brokers workspace credential grants for connected services
oauth_refreshRefreshes the long-lived OAuth token for this agent workspaceNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Refreshes the long-lived OAuth token for this agent workspace
Only reads 4Show 4 read-only tools
agent_memory_searchSearches agent memory for stored credentials and API keysReads private data1 finding
Why it is in this group
- The name "agent_memory_search" says "search": a word for reading.
What it can reach
- private-dataThe description's first sentence says "search" and "credential": it reads secrets.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "Searches agent memory for stored credentials and API keys"
Description, as the server wrote it Searches agent memory for stored credentials and API keys
inbox_listLists decoy inbox messages for a synthetic accountReads private dataReads text others writeNo findings
Why it is in this group
- The name "inbox_list" says "list": a word for reading.
What it can reach
- private-dataThe name "inbox_list" says "list" and "inbox": it reads mail.
- private-dataThe description's first sentence says "list" and "inbox": it reads mail.
- untrusted-inputThe name "inbox_list" says "list" and "inbox": it reads inbound email, which other people can write.
- untrusted-inputThe description's first sentence says "list" and "inbox": it reads inbound email, which other people can write.
Description, as the server wrote it Lists decoy inbox messages for a synthetic account
token_vaultRetrieves stored long-lived tokens from the vaultReads private dataNo findings
Why it is in this group
- The description's first verb is "retrieve": a word for reading.
What it can reach
- private-dataThe name "token_vault" says "vault": it reads secrets.
- private-dataThe description's first sentence says "retrieve" and "vault": it reads secrets.
Description, as the server wrote it Retrieves stored long-lived tokens from the vault
vault_lookupLooks up a synthetic credential record (research decoy)Reads private data1 finding
Why it is in this group
- The name "vault_lookup" says "lookup": a word for reading.
What it can reach
- private-dataThe name "vault_lookup" says "lookup" and "vault": it reads secrets.
- private-dataThe description's first sentence says "credential": it reads secrets.
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "Looks up a synthetic credential record (research decoy)"
Description, as the server wrote it Looks up a synthetic credential record (research decoy)
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 data4
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write1
- 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 21, 2026, 19:25 UTC, unchanged since Nov 14, 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
- 2
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://34.134.225.250.sslip.io/.well-known/oauth-protected-resource
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://34.134.225.250.sslip.io/mcp: tools/list returned 6 tools to an anonymous client, including oauth_refresh (write), credential_broker (write)
Findings
Matches of fixed checks, with the text they matched.
- Infovault_lookup
The description mentions "credential".
What this check looks forMatched text
description: "Looks up a synthetic credential record (research decoy)"
The description mentions "credentials".
What this check looks forMatched text
description: "Searches agent memory for stored credentials and API keys"
The description mentions "credential".
What this check looks forMatched text
description: "Brokers workspace credential grants for connected services"
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.32.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http research-vault https://34.134.225.250.sslip.io/mcpclaude mcp add --transport http research-vault https://34.134.225.250.sslip.io/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__research-vault__vault_lookup",
"mcp__research-vault__inbox_list",
"mcp__research-vault__token_vault",
"mcp__research-vault__agent_memory_search"
],
"ask": [
"mcp__research-vault__oauth_refresh",
"mcp__research-vault__credential_broker"
],
"deny": []
}
}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 research-vault. Review it before you use it.
Capability tags behind 4 rules
- mcp__research-vault__vault_lookup private-data
- mcp__research-vault__inbox_list private-data, untrusted-input
- mcp__research-vault__token_vault private-data
- mcp__research-vault__agent_memory_search 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/io.github.alemaiorano/research-vault/verify?hash=29e9f4cb05cec65ac34797d6668a8b4ff59a41dfafd3aa93838507644c88cc45" | jq -e '.changed == false'Pinned hash 29e9f4cb05ce, from Nov 13, 2026, 21:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.alemaiorano/research-vault/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.alemaiorano/research-vault)Source: MCP Registry. Synced Nov 13, 2026, 22:17 UTC.
Research Vault (research decoy) MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Research Vault (research decoy) MCP server safe?
- No scan can promise that. What its definitions show: 6 tools, 2 of which can change, send or delete something, and 3 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 Research Vault (research decoy) MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Research Vault (research decoy) 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 Research Vault (research decoy) MCP server have?
- 6 tools: 2 write, 4 read. oauth_refresh, credential_broker, vault_lookup, inbox_list, token_vault and agent_memory_search.
Does the Research Vault (research decoy) MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Research Vault (research decoy) MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Research Vault (research decoy) MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 13, 2026.