Skip to content

MemoryRouter MCP server

ai.memoryrouter/memoryroutermemoryrouter.aistreamable-httpv1.1.0Scanned

Persistent AI memory shared across Claude, ChatGPT, coding agents, and compatible MCP clients.

10 tools: 2 can delete or cancel things, 3 change things and 5 only read.

Tools: 2 delete, 0 irreversible, 3 write, 5 read.
  • Reads private data · 2
  • Reads text others write · 1
  • Can send data out · 0
  • 1 finding

Tools listed without sign-in. Remote posture

With Anlyon

2 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.
Govern this server →

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 MemoryRouter MCP server can do

The MemoryRouter MCP server is published by memoryrouter.ai, a domain the MCP Registry verified. It has 10 tools. It can delete or cancel things (2 tools: forget_all_memories and delete_memories) and create or change data (3 tools: store_memory, consolidate_memories and commit_reflections). 5 tools only read.

2 tools read private data (search_memories and memory_status); 1 tool brings in text other people can write (search_memories).

The fixed checks matched 1 finding (credentials-mention). 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 9, 2026, version 1.1.0.

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.

10 tools

Deletes or cancels 2Claude Code: deny
  • delete_memoriesUse this only when the user explicitly asks to delete specific memories and confirms after seeing what will be deleted.No findings

    Why it is in this group

    • The name "delete_memories" says "delete": a word for removing or ending something.
    • The description says "Permanently deletes".
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Use this only when the user explicitly asks to delete specific memories and confirms after seeing what will be deleted. Permanently deletes the identified memories from the connected vault by their ids from search or inspect results. Deleting a raw memory does not delete reflections built from it. This cannot be undone. For deleting everything, forget_all_memories is the separate whole-vault tool.

    Annotations the server declares

    • readOnlyHint: false
    • openWorldHint: false
    • destructiveHint: true
    • idempotentHint: true
  • forget_all_memoriesUse this only after the user explicitly requests a full-vault deletion, receives a permanent whole-vault warning, and provides the exact confirmation phrase in a later turn.No findings

    Why it is in this group

    • The description says "Permanently deletes".
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Use this only after the user explicitly requests a full-vault deletion, receives a permanent whole-vault warning, and provides the exact confirmation phrase in a later turn. Permanently deletes every memory in the OAuth-selected vault. This cannot delete one memory; use delete_memories for specific items. Requires separate memories:delete authorization and destructive host confirmation.

    Annotations the server declares

    • readOnlyHint: false
    • openWorldHint: false
    • destructiveHint: true
    • idempotentHint: true
Changes things 3Claude Code: ask
  • commit_reflectionsUse this to complete a consolidation started with consolidate_memories.No findings

    Why it is in this group

    • The name "commit_reflections" says "commit": a word for a change.
    Description, as the server wrote it
    Use this to complete a consolidation started with consolidate_memories. Submits the reflection entries you wrote for the checked-out batch. Each entry is standalone prose with an importance rating from 1 to 10. The server stores the reflections, links them to their source memories, and marks the sources consolidated. Safe to retry: committing the same batch twice returns the original result.

    Annotations the server declares

    • readOnlyHint: false
    • openWorldHint: false
    • destructiveHint: false
    • idempotentHint: true
  • consolidate_memoriesUse this when the user asks to consolidate, reflect on, or organize their memories, or when memory_status or a search result reports that consolidation is available.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.
    Description, as the server wrote it
    Use this when the user asks to consolidate, reflect on, or organize their memories, or when memory_status or a search result reports that consolidation is available. Checks out a batch of unconsolidated memories from the connected vault under a 15 minute lease and returns their texts plus server instructions for writing reflection entries. Follow the returned instructions to write the entries, then call commit_reflections with the batch_id. Nothing is modified until commit.

    Annotations the server declares

    • readOnlyHint: false
    • openWorldHint: false
    • destructiveHint: false
    • idempotentHint: false
  • store_memoryUse this after each user message that contains anything worth knowing later, even if the user does not say 'remember this'.1 finding

    Why it is in this group

    • The name "store_memory" says "store": a word for a change.

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "...ve passwords, API keys, tokens or other credentials, payment card numbers, government ID nu..."

      What this check looks for
    Description, as the server wrote it
    Use this after each user message that contains anything worth knowing later, even if the user does not say 'remember this'. Default to saving: a missed memory costs far more than a redundant one, so when in doubt, save. Each of these is a trigger on its own: the user makes a decision, states a preference, gives a fact about a person, project, company, or tool, sets a plan or commitment, makes a correction, or reports progress or an outcome. Save one concise, self-contained memory per call, written so it makes sense on its own later, with the exact wording, numbers, dates, names, and identifiers the user gave; several facts in one message mean several calls. Record what the user actually said, not your inference. There is no update tool: to supersede outdated information, save the corrected fact and say what it replaces. Never save passwords, API keys, tokens or other credentials, payment card numbers, government ID numbers, or protected health information, and never save whole transcripts. Writes one memory to the user's OAuth-selected vault. If the user asks what was saved, answer truthfully from the tool result.

    Annotations the server declares

    • readOnlyHint: false
    • openWorldHint: false
    • destructiveHint: false
    • idempotentHint: false
Only reads 5Show 5 read-only tools
  • date_search_memoriesUse this to retrieve memories from a specific time window, for questions like 'what happened last week' or 'most important things this month or lately'.No findings

    Why it is in this group

    • The name "date_search_memories" says "search": a word for reading.
    Description, as the server wrote it
    Use this to retrieve memories from a specific time window, for questions like 'what happened last week' or 'most important things this month or lately'. Tier guide: tier 3 holds the highest-level consolidated reflections (identity, principles, what matters most), tier 2 holds reflections of specific meaningful events, tier 1 holds raw verbatim memories. Match filters to the question. Time-bounded 'most important things last month' questions: tiers [3], importance 8 or higher, generous max_tokens. Big-picture overviews of a period like 'what do you know about July': tiers [3] with no importance filter. Specific lookups in a window like 'find the decision about X': omit tiers to include all tiers and leave importance unset; a high importance filter hides the specific detail you are looking for. Specific meaningful events without raw noise: tiers [2] or [2, 3]. Exact verbatim detail: if the detail is not already in context, drill down by lineage: search tiers [3] to find the relevant thread, then use inspect_memory on the result to see the tier 2 reflections it consolidated, then inspect those to reach the raw memories underneath. Direct tiers [1] search works when you know exact wording to match. Mixing tiers is legitimate; adjust the importance threshold to the question rather than always setting it high. Only reflections (tiers 2 and 3) carry importance ratings. Omit query for a chronological review; include query to rank by relevance within the window. Resolve relative phrases like 'lately' to concrete ISO dates before calling. Reads only the OAuth-selected vault and does not modify it.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
    • destructiveHint: false
  • inspect_memoryUse this when exact details or provenance matter: when the user asks why the assistant believes something, or wants to see the source memories behind a reflection.No findings

    Why it is in this group

    • The name "inspect_memory" says "inspect": a word for reading.
    Description, as the server wrote it
    Use this when exact details or provenance matter: when the user asks why the assistant believes something, or wants to see the source memories behind a reflection. Given a memory id from a search result, returns the lower-tier memories that reflection was built from, or, for a raw memory, which reflections it was consolidated into. Use repeatedly to drill down from a high-level reflection to the tier 2 reflections and raw memories beneath it. Read only.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
    • destructiveHint: false
  • memory_statusUse this when the user asks whether MemoryRouter is connected, which opaque vault binding is active, or how many memories/tokens the connected vault contains.Reads private dataNo findings

    Why it is in this group

    • The name "memory_status" says "status": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "vault": it reads secrets.
    Description, as the server wrote it
    Use this when the user asks whether MemoryRouter is connected, which opaque vault binding is active, or how many memories/tokens the connected vault contains. Does not reveal the memory key.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
    • destructiveHint: false
  • search_memoriesUse this before responding to each new user message, to retrieve context relevant to the message and ongoing conversation, even when the user does not explicitly ask you to remembe…Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "search_memories" says "search": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "message": it reads messages.
    • untrusted-inputThe description's first sentence says "message": it reads messages, which other people can write.
    Description, as the server wrote it
    Use this before responding to each new user message, to retrieve context relevant to the message and ongoing conversation, even when the user does not explicitly ask you to remember. Form a concise semantic query using the people, projects, preferences, goals, decisions, or events implied by the message; for follow-ups, include enough recent conversational context to make the query meaningful. Search all tiers (omit tiers and importance) unless there is a reason to narrow. If a MemoryRouter recall block was already supplied for this message, that search already ran; search again only for more detail. Read only: searches the user's OAuth-selected vault. Tier guide: tier 3 holds the highest-level consolidated reflections (identity, principles, what matters most), tier 2 holds reflections of specific meaningful events, tier 1 holds raw verbatim memories. Match filters to the question. Broad 'most important things we have done' questions: tiers [3], importance 8 or higher, large limit such as 250. Big-picture overviews like 'what do you know about this area or period': tiers [3] with no importance filter. Specific lookups like 'find the decision about X': omit tiers to search all tiers blended and leave importance unset; a high importance filter hides the specific detail you are looking for. Specific meaningful events without raw noise: tiers [2] or [2, 3]. Exact verbatim detail: if the detail is not already in context, drill down by lineage: search tiers [3] to find the relevant thread, then use inspect_memory on the result to see the tier 2 reflections it consolidated, then inspect those to reach the raw memories underneath. Direct tiers [1] search works when you know exact wording to match. Mixing tiers is legitimate; adjust the importance threshold to the question rather than always setting it high. Only reflections (tiers 2 and 3) carry importance ratings. For time-window questions like 'what happened last week' or 'lately' use date_search_memories instead.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: false
    • destructiveHint: 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 data2
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.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:26 UTC, unchanged since Nov 20, 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
8
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://mcp.memoryrouter.ai/.well-known/oauth-protected-resource/mcp
Authorization servers
https://auth.memoryrouter.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 8 tools that change things (3 destructive, 5 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.memoryrouter.ai/mcp: tools/list returned 14 tools to an anonymous client, including forget_all_memories (destructive), delete_memories (destructive), revoke_memory_share (destructive), store_memory (write), consolidate_memories (write) and 3 more

    What this check looks for

Posture changes

  1. Nov 20, 2026
    • Tools that change things, listed without credentials: 5 to 8

Findings

Matches of fixed checks, with the text they matched.

1 info
  • The description mentions "credentials".

    Matched text

    description: "...ve passwords, API keys, tokens or other credentials, payment card numbers, government ID nu..."

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. PostureRemote posture changed. Tools that change things, listed without credentials: 5 -> 8.View diff
    • Tools that change things, listed without credentials: 5 to 8
  2. Tools3 changed.~3 changedView diff

Install

Pinned to version 1.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http memoryrouter https://mcp.memoryrouter.ai/mcp
claude mcp add --transport http memoryrouter https://mcp.memoryrouter.ai/mcp

Run 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.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__memoryrouter__search_memories",
      "mcp__memoryrouter__date_search_memories",
      "mcp__memoryrouter__memory_status",
      "mcp__memoryrouter__inspect_memory",
      "mcp__memoryrouter__search"
    ],
    "ask": [
      "mcp__memoryrouter__store_memory",
      "mcp__memoryrouter__consolidate_memories",
      "mcp__memoryrouter__commit_reflections"
    ],
    "deny": [
      "mcp__memoryrouter__forget_all_memories",
      "mcp__memoryrouter__delete_memories"
    ]
  }
}

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 memoryrouter. Review it before you use it.

Capability tags behind 2 rules
  • mcp__memoryrouter__search_memories private-data, untrusted-input
  • mcp__memoryrouter__memory_status 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.memoryrouter/memoryrouter/verify?hash=57bc2bd5213ca0aa7aa1f3a6dcdd56a4ac1881c705def3cbf15d7d685e772f10" | jq -e '.changed == false'

Pinned hash 57bc2bd5213c, from Nov 9, 2026, 17:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/ai.memoryrouter/memoryrouter/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for ai.memoryrouter/memoryrouter
[![Anlyon Radar](https://radar.anlyon.com/badge/ai.memoryrouter/memoryrouter.svg)](https://radar.anlyon.com/servers/ai.memoryrouter/memoryrouter)

Source: MCP Registry. Synced Oct 21, 2026, 17:42 UTC.

MemoryRouter MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the MemoryRouter MCP server safe?

No scan can promise that. What its definitions show: 10 tools, 5 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the MemoryRouter MCP server delete data?

Yes. 2 tools can delete, cancel or revoke something: forget_all_memories and delete_memories.

Can the MemoryRouter 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 MemoryRouter MCP server have?

10 tools: 2 destructive, 3 write, 5 read. forget_all_memories, delete_memories, store_memory, consolidate_memories, commit_reflections, search_memories, date_search_memories, memory_status and 2 more.

Does the MemoryRouter MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the MemoryRouter MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the MemoryRouter MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 9, 2026. Every change is on this page and in its Atom feed.