MemoryRouter
Server Details
Persistent AI memory shared across Claude, ChatGPT, coding agents, and compatible MCP clients.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 14 tools
Most tools target a distinct resource+action, and the risky pairs are explicitly separated in their descriptions (delete_memories vs forget_all_memories; consolidate_memories vs commit_reflections). The remaining overlap is retrieval: search, search_memories and date_search_memories all query the same vault, with `search` being a self-declared legacy alias and date_search_memories overlapping heavily with search_memories' tier/time guidance. An agent can resolve these from the text, but they are genuinely confusable.
Nearly all names are snake_case verb_noun (store_memory, delete_memories, create_memory_share, revoke_memory_share), which is predictable. Minor deviations: date_search_memories inverts the noun/verb order, memory_status is a bare noun phrase, and search is a lone bare verb alias. Still readable and largely coherent.
14 tools is squarely in the well-scoped range, and each maps to a real operation across recall, consolidation, sharing, and destruction. The one arguably unnecessary member is the `search` legacy alias, which is a small blemish rather than bloat.
The surface covers the full lifecycle: write (store_memory), read (search/date_search/inspect), consolidate (consolidate_memories + commit_reflections), delete at item and vault level, and a complete share lifecycle (create/list/revoke/import) plus status. The notable gap is the absence of an update/edit tool, which the description concedes and works around by re-saving a corrected fact, plus no direct get-by-id read outside inspect_memory.
Available Tools
14 toolscommit_reflectionsCommit reflectionsAIdempotentInspect
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.
Inputs: entries (required), batch_id (required). Returns: debt, tier, committed, entries_created, +2 more
consolidate_memoriesConsolidate memories (checkout)AInspect
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.
Inputs: tier, max_tokens. Returns: tier, count, covers, message, +5 more
date_search_memoriesSearch memories by dateARead-onlyInspect
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.
Inputs: from (required), to, query, tiers, +2 more. Returns: to, from, count, window, +4 more
delete_memoriesDelete specific memoriesADestructiveIdempotentInspect
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.
Inputs: ids (required), confirmation (required). Returns: failed, deleted, message, vaultRef, +1 more
forget_all_memoriesDelete all memories in connected vaultADestructiveIdempotentInspect
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.
Inputs: confirmation (required). Returns: deleted, message, vaultRef
inspect_memoryInspect memory lineageARead-onlyInspect
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.
Inputs: memory_id (required). Returns: tier, covers, sources, memory_id, +4 more
memory_statusCheck memory statusARead-onlyInspect
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.
Inputs: no named parameters. Returns: storage, vaultRef, connected, reflection, +4 more
searchSearch MemoryRouter knowledgeARead-onlyInspect
Use this legacy compatibility alias when a client explicitly requests a tool named search. It searches the OAuth-selected MemoryRouter vault without modifying it. For normal ChatGPT recall, prefer search_memories; this tool does not provide citable item permalinks or Company Knowledge fetch support.
Inputs: query (required). Returns: results
search_memoriesSearch memoriesARead-onlyInspect
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.
Inputs: query (required), limit, tiers, importance. Returns: count, query, memories, consolidation_available
store_memorySave memoryAInspect
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.
Inputs: content (required), tags. Returns: source, status, accepted, vaultRef
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Persistent memory for AI agents across Claude, ChatGPT and any MCP client.
Persistent memory shared across Claude, ChatGPT, Grok and other MCP clients.
Persistent memory for AI assistants. Save once; recall from Claude, ChatGPT, or any MCP client.
Shared AI memory. ChatGPT, Claude, Cursor and any MCP app read and write the same memory.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceGives AI persistent personal memory with hybrid search, temporal decay, and knowledge graph. Works with Claude and any MCP client.12 npm10MIT
- AlicenseNot gradedqualityDmaintenancePersistent memory with semantic search for Claude and MCP-compatible clients, storing context that survives conversations and can be retrieved intelligently.1MIT
- AlicenseNot gradedqualityDmaintenanceShared memory for any MCP-compatible AI, enabling cross-platform knowledge persistence and retrieval so users' context, preferences, and project info follow them everywhere.3AGPL 3.0
- AlicenseAqualityDmaintenanceGives Claude Code, Claude Desktop, Cursor, VS Code Copilot, and other MCP-compatible tools persistent memory.1848 npm1MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.