WorkingMemory MCP server
ai.workingmemory/memoryworkingmemory.aistreamable-httpv1.0.0Scanned
Persistent personal memory for AI assistants — save, search, and recall across every MCP client.
4 tools: 1 can delete or cancel things, 1 do something that can't be undone, 1 change things and 1 only read.
- Reads private data · 1
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here can delete or cancel things and 1 does something that can't be undone. 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 WorkingMemory MCP server can do
The WorkingMemory MCP server is published by workingmemory.ai, a domain the MCP Registry verified. It has 4 tools. It can delete or cancel things (1 tool: manage_memory), do things that cannot be undone, such as sending, paying or publishing (capture_memory) and create or change data (1 tool: save_memory). 1 tool only reads.
1 tool reads private data (search_memory).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 9, 2026, version 1.0.0.
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.
4 tools
Deletes or cancels 1Claude Code: deny
manage_memoryManage an existing memory item.No 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).
Description, as the server wrote it Manage an existing memory item. Currently supports deleting a memory by id (soft delete — recoverable for 30 days). Use search_memory to find the id first.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: false
Can't be undone 1Claude Code: ask
capture_memoryCapture durable facts from a task you just completed (drafting an email, summarizing a document, making a decision), as a byproduct — the user does nothing.No findings
Why it is in this group
- The name "capture_memory" says "capture": a word that usually means money moves, which cannot be taken back.
Description, as the server wrote it Capture durable facts from a task you just completed (drafting an email, summarizing a document, making a decision), as a byproduct — the user does nothing. Pass the task output/content; durable facts are extracted and stored automatically. Always include your conversation id in client.conversation_id. Returns immediately; extraction happens in the background.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
Changes things 1Claude Code: ask
save_memorySave a thought, insight, fact, or todo to the user's Working Memory.No findings
Why it is in this group
- The name "save_memory" says "save": a word for a change.
Description, as the server wrote it Save a thought, insight, fact, or todo to the user's Working Memory. The text is parsed and stored as one or more structured memory items, searchable a moment later via search_memory. Also use this when the user pastes memories or notes brought from another assistant — pass the full pasted text; it is split into individual memories automatically.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
Only reads 1Show 1 read-only tool
search_memorySearch the user's Working Memory for relevant past notes and facts.Reads private dataNo findings
Why it is in this group
- The name "search_memory" says "search": a word for reading.
What it can reach
- private-dataThe description's first sentence says "search" and "note": it reads notes.
Description, as the server wrote it Search the user's Working Memory for relevant past notes and facts. Use this when the user references something they may have stored earlier, or to find related context before answering. Always include your conversation id in client.conversation_id.
Annotations the server declares
- readOnlyHint: 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 untrusted-input or outbound.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- 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 20, 2026, 18:28 UTC, unchanged since Oct 22, 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
- 3
- Protocol version
- 2025-11-25
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://app.workingmemory.ai/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://app.workingmemory.ai
- 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 3 tools that change things (1 destructive, 1 irreversible, 1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://app.workingmemory.ai/mcp: tools/list returned 4 tools to an anonymous client, including manage_memory (destructive), capture_memory (irreversible), save_memory (write)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
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 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http memory https://app.workingmemory.ai/mcpclaude mcp add --transport http memory https://app.workingmemory.ai/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__memory__search_memory"
],
"ask": [
"mcp__memory__save_memory",
"mcp__memory__capture_memory"
],
"deny": [
"mcp__memory__manage_memory"
]
}
}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 memory. Review it before you use it.
Capability tags behind 1 rule
- mcp__memory__search_memory 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/ai.workingmemory/memory/verify?hash=8c73213356796c4cebdc5b7f77525dc6bb6f7201f34045fa3b64f41013e7bf1e" | jq -e '.changed == false'Pinned hash 8c7321335679, from Nov 9, 2026, 18:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ai.workingmemory/memory/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ai.workingmemory/memory)Source: MCP Registry. Synced Oct 21, 2026, 17:44 UTC.
WorkingMemory MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the WorkingMemory MCP server safe?
- No scan can promise that. What its definitions show: 4 tools, 3 of which can change, send or delete something, and 0 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 WorkingMemory MCP server delete data?
- Yes. 1 tool can delete, cancel or revoke something: manage_memory.
Can the WorkingMemory MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: capture_memory.
What tools does the WorkingMemory MCP server have?
- 4 tools: 1 destructive, 1 irreversible, 1 write, 1 read. manage_memory, capture_memory, save_memory and search_memory.
Does the WorkingMemory MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the WorkingMemory MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the WorkingMemory MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 9, 2026.