WorkingMemory
REMOTE · APP.WORKINGMEMORY.AI · SCANNED SEP 20
Persistent personal memory for AI assistants — save, search, and recall across every MCP client.
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 Security92
- 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
- The authorisation server supports Client ID Metadata Documents, the current MCP client-registration mechanism. View diagnostics → Pass
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability70
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 716 tokens (~179/item across 4 items; 4 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 Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
How do I install the WorkingMemory MCP server?
WorkingMemory is a hosted endpoint at https://app.workingmemory.ai/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 · app.workingmemory.ai
claude mcp add --transport http ai-workingmemory-memory 'https://app.workingmemory.ai/mcp'
{
"mcpServers": {
"ai-workingmemory-memory": {
"url": "https://app.workingmemory.ai/mcp"
}
}
} {
"servers": {
"ai-workingmemory-memory": {
"type": "http",
"url": "https://app.workingmemory.ai/mcp"
}
}
} [mcp_servers.ai-workingmemory-memory] url = "https://app.workingmemory.ai/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"ai-workingmemory-memory": {
"type": "remote",
"url": "https://app.workingmemory.ai/mcp",
"enabled": true
}
}
} openclaw mcp add ai-workingmemory-memory --url 'https://app.workingmemory.ai/mcp' --transport streamable-http
mcp_servers:
ai-workingmemory-memory:
url: "https://app.workingmemory.ai/mcp" {
"McpServers": {
"ai-workingmemory-memory": {
"Transport": "http",
"Url": "https://app.workingmemory.ai/mcp"
}
}
} assistant mcp add ai-workingmemory-memory -t streamable-http -u 'https://app.workingmemory.ai/mcp'
{
"mcpServers": {
"ai-workingmemory-memory": {
"type": "http",
"url": "https://app.workingmemory.ai/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.
- 7 Sept 26 0
- Stability: 0.97 → pass security
- 6 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 3 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 1 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.
- 30 Aug 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.
- 28 Aug 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.
- 26 Aug 26 +2
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 24 Aug 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.
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://app.workingmemory.ai/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=workingmemory.ai | CN=WE1,O=Google Trust Services,C=US | 24 Jul 2026 | 22 Oct 2026 | ECDSA 256 | ECDSA-SHA256 | da6c49ec4f6085290e1bd9fa7ec16db4 |
| SANs: workingmemory.ai, app.workingmemory.ai, *.app.workingmemory.ai | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of app.workingmemory.ai. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| ai. | present | 3799 | 8 | Verified |
| workingmemory.ai. | 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://app.workingmemory.ai/.well-known/oauth-protected-resource"
Bearer resource_metadata="https://app.workingmemory.ai/.well-known/oauth-protected-resource"Protected resource metadata
| Document | https://app.workingmemory.ai/.well-known/oauth-protected-resource |
|---|---|
| Retrieved | Yes |
| Resource | https://app.workingmemory.ai/mcp |
| Authorisation server | https://app.workingmemory.ai |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://app.workingmemory.ai/mcp | Verified | 200 | |
| http (plaintext) | http://app.workingmemory.ai/mcp | HTTPS enforced | 301 | https://app.workingmemory.ai/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 →
capture_memory Capture memory ~137
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.
| Name | Type | Req | Description |
|---|---|---|---|
| client | object | – | Current client session context. Pass your conversation/thread id as conversation_id. |
| task_content | string | yes | The task output/content to mine for durable facts (max 32KB). |
| task_description | string | – | Optional one-line description of the task, as extraction framing. |
No output schema declared.
No examples provided.
manage_memory Manage memory ~67
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.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | The management action to perform. |
| id | string | yes | The memory item id to act on. |
No output schema declared.
No examples provided.
save_memory Save to memory ~129
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.
| Name | Type | Req | Description |
|---|---|---|---|
| client | object | – | Optional context about the originating client session. Helps users later find saves from a specific conversation. `conversation_id` groups multiple saves; `conversation_title` is human-readable. |
| text | string | yes | The thought or note to save. |
No output schema declared.
No examples provided.
search_memory Search memory ~209
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.
| Name | Type | Req | Description |
|---|---|---|---|
| client | object | – | Context about the CURRENT client session. Pass your conversation/thread id as `conversation_id` — it identifies this session for cross-session memory instrumentation and does NOT filter results (use… |
| conversation_id | string | – | Optional. Restrict results to notes stamped with this conversation_id at save_memory time. Empty / whitespace-only values are treated as absent. |
| dedupe_recent | boolean | – | Optional. When false, semantic matches that are also recent are still returned in `relevant` (raw semantic results rather than RAG-deduped). Defaults to true. |
| k | number | – | Max results (1–20). Defaults to a sensible value. |
| query | string | yes | Semantic query. |
No output schema declared.
No examples provided.
What is the WorkingMemory MCP server?
WorkingMemory is an MCP server listed in the public MCP registry as ai.workingmemory/memory. Persistent personal memory for AI assistants, save, search, and recall across every MCP client. This page covers its hosted endpoint (https://app.workingmemory.ai/mcp).
Is the WorkingMemory MCP server safe to use?
WorkingMemory scores 91 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 WorkingMemory MCP server expose?
WorkingMemory exposes 4 tools: save_memory, search_memory, manage_memory, capture_memory. Their descriptions and schemas cost roughly 542 tokens of context every time the server is loaded.
Does the WorkingMemory MCP server require authentication?
Yes. WorkingMemory 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 WorkingMemory MCP server still maintained?
WorkingMemory 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.