XMemo
Server Details
XMemo is a secure, user-owned memory substrate and context engine for AI agents, CLIs, IDEs, and LLM workspaces. Exposed over Streamable HTTP MCP, it empowers agents with cross-session memory, task continuity, and personalized context. Key Features:
Personalized Context: Stores and recalls developer preferences, project guidelines, and coding patterns via semantic vector search.
Agent Daily Memory: Tracks active tasks, episodic event timelines, reminders, pending decisions, and session restart snapshots.
Self-Improving Reflection: A background worker that automatically summarizes episodic details, promotes facts, and manages memory decay.
Privacy & Governance: Complete control over user data with owner-scoped access, explicit token scopes, audit trails, and secure redaction (forget) flows.
Built for Developers: Works natively with IDE assistants (Cursor, Claude Desktop, VS Code), CLI scripts, and autonomous agent frameworks.
- Status
- Healthy
- Last Tested
- Transport
- Streamable HTTP
- URL
Glama MCP Gateway
Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.
Full call logging
Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.
Tool access control
Enable or disable individual tools per connector, so you decide what your agents can and cannot do.
Managed credentials
Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.
Usage analytics
See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.
Tool Definition Quality
Score is being calculated. Check back soon.
Available Tools
49 toolsadd_expenseAdd an expense to XMemoInspect
Record one expense in the XMemo Ledger. Call this whenever the user states a concrete expense, purchase, income, or refund — for example, 'I spent 25 on lunch' or 'log this expense' — not only on an explicit 'record this'. Capture date, amount, currency, item, and merchant/category when present.
| Name | Required | Description | Default |
|---|---|---|---|
| item | Yes | The purchased item or service, for example 2 watermelons or Nintendo Switch 2. | |
| note | No | Optional completion note. | |
| path | No | A simple user-facing category or path for this memory, such as preferences, projects/xmemo, or personal/travel. | finance/ledger/expenses |
| scope | No | Optional scope that narrows memory access; leave blank for the token default. | |
| amount | Yes | Positive transaction amount as a number. | |
| bucket | No | Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads. | private |
| team_id | No | Optional team/workspace identifier for team-scoped memory access. | |
| agent_id | No | Optional client-supplied agent label for memory attribution. | |
| category | No | Optional spending category, such as food, transport, or electronics. | |
| currency | No | Currency code or label, such as CNY, RMB, JPY, yen, or USD. For ledger search/list tools, leave blank unless the user explicitly requested one currency; labels are normalized to codes. | CNY |
| merchant | No | Optional merchant or store name. | |
| device_id | No | Optional client-supplied device identifier for attribution. | |
| device_label | No | Optional human-readable device label for attribution. | |
| payment_method | No | Optional payment method, such as card, cash, Alipay, or WeChat Pay. | |
| transaction_date | No | Transaction date in YYYY-MM-DD. Leave blank to use today's UTC date. | |
| agent_instance_id | No | Optional stable, non-secret agent instance ID for per-client attribution. |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
analyze_memory_textAnalyze XMemo memory textRead-onlyIdempotentInspect
Count a word or phrase across XMemo memories, optionally grouped by month, agent, location, or type. Call this when the user asks how often a word/topic appears.
| Name | Required | Description | Default |
|---|---|---|---|
| scope | No | Optional scope that narrows memory access; leave blank for the token default. | |
| since | No | Only include memories or activity on or after this ISO 8601 timestamp. | |
| until | No | Only include memories or activity on or before this ISO 8601 timestamp. | |
| phrase | Yes | Exact word or phrase to count across visible XMemo memories. | |
| group_by | No | Optional grouping: none, month, agent, location, memory_type, type, source, path, bucket, day, or comma-separated advanced fields. | none |
| match_mode | No | How to match phrase: exact, case_insensitive, or regex_lite. | exact |
| memory_type | No | Memory type/category filter or value, such as episodic, identity, procedural, semantic, working, auto, or %. | % |
| output_json | No | Return a machine-readable JSON response instead of a human-readable summary. | |
| path_filter | No | Memory path filter; % matches all paths. | % |
| max_examples | No | Maximum number of short snippets to include. | |
| max_memories | No | Maximum number of memories to inspect while analyzing text. | |
| include_examples | No | Whether to include a few short matching memory snippets. |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
complete_memory_todoComplete XMemo memory TODOInspect
Mark a TODO/action item completed. Call this when the user says a saved task is done, resolved, or no longer needed; use the exact reference from list_memory_todos.
| Name | Required | Description | Default |
|---|---|---|---|
| note | No | Optional completion note. | |
| todo_id | Yes | The memory TODO/action-item ID to complete. |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
complete_reminderAdvanced: complete XMemo legacy reminderInspect
Complete a TODO item. Alias for complete_memory_todo.
| Name | Required | Description | Default |
|---|---|---|---|
| note | No | Optional completion note. | |
| reminder_id | Yes | The memory TODO/action-item ID to complete. |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
create_memory_todoCreate XMemo memory TODOInspect
Create a TODO/action item in XMemo with an optional due time. Call this when the user asks to save a task, follow-up, action item, or reminder-style item to revisit later.
| Name | Required | Description | Default |
|---|---|---|---|
| scope | No | Optional scope that narrows memory access; leave blank for the token default. | |
| bucket | No | Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads. | work |
| due_at | No | Optional due time for a memory TODO/action item, preferably ISO 8601. | |
| content | Yes | Text body to save, such as a memory, TODO/action item, event note, or state summary. | |
| metadata_json | No | Optional JSON object string with extra metadata for the operation. | {} |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
create_pending_decisionCreate Pending DecisionInspect
Record an unresolved decision with its options to revisit later. Use for open choices, not ordinary TODOs.
| Name | Required | Description | Default |
|---|---|---|---|
| scope | No | Optional scope that narrows memory access; leave blank for the token default. | |
| bucket | No | Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads. | work |
| due_at | No | Optional due time for a memory TODO/action item, preferably ISO 8601. | |
| context | Yes | Short context explaining a memory usage event or pending decision. | |
| options_json | No | JSON array of candidate options for a pending decision. | [] |
| metadata_json | No | Optional JSON object string with extra metadata for the operation. | {} |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
create_reminderAdvanced: create XMemo legacy reminderInspect
Create a TODO item. Alias for create_memory_todo.
| Name | Required | Description | Default |
|---|---|---|---|
| scope | No | Optional scope that narrows memory access; leave blank for the token default. | |
| bucket | No | Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads. | work |
| due_at | No | Optional due time for a memory TODO/action item, preferably ISO 8601. | |
| content | Yes | Text body to save, such as a memory, TODO/action item, event note, or state summary. | |
| metadata_json | No | Optional JSON object string with extra metadata for the operation. | {} |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
create_restart_snapshotCreate Restart SnapshotInspect
Save active state, recent events, TODOs, and pending decisions for restart. Call this before handoff or when context may be lost.
| Name | Required | Description | Default |
|---|---|---|---|
| scope | No | Optional scope that narrows memory access; leave blank for the token default. | |
| bucket | No | Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads. | work |
| state_key | No | Working-state key to save, snapshot, or restore, such as active_task. | active_task |
| session_id | No | Optional session identifier associated with the event, timeline query, or snapshot. | |
| ttl_seconds | No | Time-to-live in seconds for working state or restart snapshot records. | |
| metadata_json | No | Optional JSON object string with extra metadata for the operation. | {} |
| decision_limit | No | Maximum number of pending decisions to include in a restart snapshot. | |
| reminder_limit | No | Maximum number of TODO/reminder items to include in a restart snapshot. | |
| timeline_limit | No | Maximum number of recent timeline events to include in a restart snapshot. |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
delete_current_memoryDelete current XMemo memoryDestructiveInspect
Permanently delete the single active memory (no ID needed). Call this only when exactly one memory exists and the user explicitly asks to delete it; refused if zero or multiple match.
| Name | Required | Description | Default |
|---|---|---|---|
| reason | No | Optional user-facing reason for the deletion. |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
explain_memoryExplain XMemo memoryRead-onlyIdempotentInspect
Explain why a memory exists or matched a query. Call this when the user asks why something was saved or why it was retrieved.
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | Natural-language question or search text. | |
| memory_id | Yes | Exact XMemo memory reference shown by search or recall. | |
| output_json | No | Return a machine-readable JSON response instead of a human-readable summary. | |
| include_embedding | No | Whether to include embedding/vector metadata in the returned explanation. |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
forgetForget XMemo memoryDestructiveInspect
Permanently delete one memory by natural target ('latest', 'current', or an exact ID). Call this only when the user explicitly asks to forget/delete a specific memory; search or check activity first if the target is ambiguous.
| Name | Required | Description | Default |
|---|---|---|---|
| reason | No | Optional user-facing reason for the deletion. | |
| target | No | The memory to forget: current or an exact memory ID shown by search. | current |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
forget_memorySoft-delete XMemo memoryDestructiveInspect
Delete a memory (recoverable) by exact reference, when the user explicitly asks to remove or hide it. Use forget or delete_current_memory for permanent deletion.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | Deletion mode for forget_memory, such as soft_delete, hard_delete, or redact when supported. | soft_delete |
| reason | No | Optional user-facing reason for the deletion. | |
| memory_id | Yes | Exact XMemo memory reference shown by search or recall. | |
| metadata_json | No | Optional JSON object string with extra metadata for the operation. | {} |
| replacement_content | No | Replacement text to store when redacting or replacing deleted memory content. |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
get_mcp_identityCheck XMemo connectionRead-onlyIdempotentInspect
Check XMemo connection status and the connected account/agent. Call this when the user asks whether XMemo is connected.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
get_monthly_ledger_summaryShow XMemo monthly spending summaryRead-onlyIdempotentInspect
Summarize Ledger totals by month and currency. Call this when the user asks for monthly spending, income, refunds, net balance, budget review, or spending trends.
| Name | Required | Description | Default |
|---|---|---|---|
| scope | No | Optional scope that narrows memory access; leave blank for the token default. | |
| bucket | No | Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads. | % |
| months | No | Number of recent ledger months to summarize. | |
| currency | No | Currency code or label, such as CNY, RMB, JPY, yen, or USD. For ledger search/list tools, leave blank unless the user explicitly requested one currency; labels are normalized to codes. | |
| output_json | No | Return a machine-readable JSON response instead of a human-readable summary. | |
| transaction_type | No | Optional ledger type filter: expense, income, refund, or transfer. |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
get_recall_policyGet Recall PolicyRead-onlyIdempotentInspect
Inspect XMemo retrieval policy (debug/admin). For actual recall use recall_context/recall/search_memory.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
get_safety_policyGet Safety PolicyRead-onlyIdempotentInspect
Show the account safety policy. Useful before custom memory-writing that may include sensitive content; normal writes are already sanitized server-side.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
get_system_statsAdvanced: query XMemo memory statsRead-onlyIdempotentInspect
Detailed memory stats with filters and grouping. For a quick summary use memory_overview or memory_stats.
| Name | Required | Description | Default |
|---|---|---|---|
| scope | No | Optional scope that narrows memory access; leave blank for the token default. | |
| since | No | Only include memories or activity on or after this ISO 8601 timestamp. | |
| top_n | No | Maximum number of aggregate groups to return. | |
| until | No | Only include memories or activity on or before this ISO 8601 timestamp. | |
| source | No | Optional source filter for system statistics. | |
| status | No | Memory status filter or update value, such as active, archived, deleted, or %. | % |
| team_id | No | Optional team/workspace identifier for team-scoped memory access. | |
| group_by | No | Optional grouping: none, month, agent, location, memory_type, type, source, path, bucket, day, or comma-separated advanced fields. | |
| memory_type | No | Memory type/category filter or value, such as episodic, identity, procedural, semantic, working, auto, or %. | % |
| output_json | No | Return a machine-readable JSON response instead of a human-readable summary. | |
| path_filter | No | Memory path filter; % matches all paths. | % |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
get_timelineGet TimelineRead-onlyIdempotentInspect
Show recent events. Call this when the user asks what happened recently or when resuming work that may depend on recent events.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of results to return. | |
| scope | No | Optional scope that narrows memory access; leave blank for the token default. | |
| bucket | No | Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads. | % |
| event_type | No | Timeline event type, such as event, milestone, decision, or handoff. | |
| session_id | No | Optional session identifier associated with the event, timeline query, or snapshot. |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
list_ledger_transactionsShow XMemo expensesRead-onlyIdempotentInspect
Show XMemo Ledger records. Call this when the user asks about past expenses, purchases, or spending history, or before answering a finance question that depends on recorded transactions. For item searches use query and leave currency blank unless a currency was requested.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of results to return. | |
| query | No | Natural-language question or search text. | |
| scope | No | Optional scope that narrows memory access; leave blank for the token default. | |
| bucket | No | Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads. | % |
| offset | No | Number of matching records to skip for pagination. | |
| date_to | No | Only include ledger transactions on or before this YYYY-MM-DD date. | |
| category | No | Optional spending category, such as food, transport, or electronics. | |
| currency | No | Currency code or label, such as CNY, RMB, JPY, yen, or USD. For ledger search/list tools, leave blank unless the user explicitly requested one currency; labels are normalized to codes. | |
| date_from | No | Only include ledger transactions on or after this YYYY-MM-DD date. | |
| max_amount | No | Only include ledger transactions with amount less than or equal to this value. | |
| min_amount | No | Only include ledger transactions with amount greater than or equal to this value. | |
| output_json | No | Return a machine-readable JSON response instead of a human-readable summary. | |
| transaction_type | No | Optional ledger type filter: expense, income, refund, or transfer. |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
list_memory_conflictsList Memory ConflictsRead-onlyIdempotentInspect
List conflicting/inconsistent memories. Call this when the user/admin asks to review unresolved conflicts.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of results to return. | |
| output_json | No | Return a machine-readable JSON response instead of a human-readable summary. | |
| unresolved_only | No | Whether to show only unresolved memory conflicts. |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
list_memory_todosList XMemo memory TODOsRead-onlyIdempotentInspect
List open or completed TODO/action items. Call this when the user asks what tasks, follow-ups, or saved action items are pending or done.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of results to return. | |
| scope | No | Optional scope that narrows memory access; leave blank for the token default. | |
| bucket | No | Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads. | % |
| due_before | No | Only show memory TODO/action items due before this time. | |
| item_status | No | Optional memory TODO/action-item status filter. | open |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
list_memory_versionsList Memory VersionsRead-onlyIdempotentInspect
Show version history for a memory. Call this when the user asks for previous content or changes over time.
| Name | Required | Description | Default |
|---|---|---|---|
| memory_id | Yes | Exact XMemo memory reference shown by search or recall. | |
| output_json | No | Return a machine-readable JSON response instead of a human-readable summary. |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
list_pending_decisionsList Pending DecisionsRead-onlyIdempotentInspect
List open/unresolved decisions. Call this when the user asks what decisions are pending, or before planning work that depends on unresolved choices.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of results to return. | |
| scope | No | Optional scope that narrows memory access; leave blank for the token default. | |
| bucket | No | Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads. | % |
| due_before | No | Only show memory TODO/action items due before this time. | |
| item_status | No | Optional memory TODO/action-item status filter. | open |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
list_remindersAdvanced: list XMemo legacy remindersRead-onlyIdempotentInspect
List TODO items. Alias for list_memory_todos.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of results to return. | |
| scope | No | Optional scope that narrows memory access; leave blank for the token default. | |
| bucket | No | Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads. | % |
| due_before | No | Only show memory TODO/action items due before this time. | |
| item_status | No | Optional memory TODO/action-item status filter. | open |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
mark_memory_usedMark Memory UsedInspect
Record that a recalled memory was used in the answer. Call this after a retrieved memory actually influenced your response (not for ignored results).
| Name | Required | Description | Default |
|---|---|---|---|
| action | No | Usage action or audit-event action filter, depending on the tool. | used |
| context | No | Short context explaining a memory usage event or pending decision. | |
| memory_id | Yes | Exact XMemo memory reference shown by search or recall. | |
| metadata_json | No | Optional JSON object string with extra metadata for the operation. | {} |
| usage_tracking_id | No | Optional tracking ID that links a recalled memory to later usage feedback. |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
memory_activityShow XMemo memory activityRead-onlyIdempotentInspect
Show recent memory activity — writes, deletions, TODO changes, ledger changes, and timeline events. Call this when the user asks what changed recently, or before deleting 'latest/recent' memory so the user can confirm the preview.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of results to return. | |
| since | No | Only include memories or activity on or after this ISO 8601 timestamp. | |
| until | No | Only include memories or activity on or before this ISO 8601 timestamp. | |
| output_json | No | Return a machine-readable JSON response instead of a human-readable summary. | |
| activity_type | No | Activity filter: all, writes, deletions, reads, reminders, ledger, or timeline. | all |
| include_timeline | No | Whether to include timeline events in recent memory activity. |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
memory_overviewShow XMemo memory overviewRead-onlyIdempotentInspect
Show a summary of XMemo memories and recent activity. Call this when the user asks what XMemo remembers without a specific query.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
memory_statsShow XMemo memory statisticsRead-onlyIdempotentInspect
Show aggregate statistics for XMemo memories — counts by type, source, location, and optional time range. Call this when the user asks for counts, breakdowns, or distributions.
| Name | Required | Description | Default |
|---|---|---|---|
| scope | No | Optional scope that narrows memory access; leave blank for the token default. | |
| since | No | Only include memories or activity on or after this ISO 8601 timestamp. | |
| top_n | No | Maximum number of aggregate groups to return. | |
| until | No | Only include memories or activity on or before this ISO 8601 timestamp. | |
| group_by | No | Optional grouping: none, month, agent, location, memory_type, type, source, path, bucket, day, or comma-separated advanced fields. | |
| memory_type | No | Memory type/category filter or value, such as episodic, identity, procedural, semantic, working, auto, or %. | % |
| output_json | No | Return a machine-readable JSON response instead of a human-readable summary. | |
| path_filter | No | Memory path filter; % matches all paths. | % |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
query_audit_eventsQuery Audit EventsRead-onlyIdempotentInspect
Advanced audit query by action/time/target. For normal users prefer memory_activity.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of results to return. | |
| scope | No | Optional scope that narrows memory access; leave blank for the token default. | |
| since | No | Only include memories or activity on or after this ISO 8601 timestamp. | |
| until | No | Only include memories or activity on or before this ISO 8601 timestamp. | |
| action | No | Usage action or audit-event action filter, depending on the tool. | |
| bucket | No | Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads. | |
| offset | No | Number of matching records to skip for pagination. | |
| target_id | No | Optional audit target ID to filter audit events. |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
query_consolidation_auditQuery Consolidation AuditRead-onlyIdempotentInspect
Inspect consolidation/lifecycle/reflection audit records (admin). Not for normal recall/save.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of results to return. | |
| scope | No | Optional scope that narrows memory access; leave blank for the token default. | |
| since | No | Only include memories or activity on or after this ISO 8601 timestamp. | |
| until | No | Only include memories or activity on or before this ISO 8601 timestamp. | |
| bucket | No | Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads. | |
| offset | No | Number of matching records to skip for pagination. | |
| action_type | No | Consolidation, lifecycle, or reflection audit action type to filter by. |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
recallRecall XMemo memoryRead-onlyIdempotentInspect
Recall the few most relevant saved memories before answering, when prior preferences, known facts, past decisions, or project context may directly affect the response. Use recall_context when many memories are needed.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of results to return. | |
| query | Yes | Natural-language question or search text. | |
| explain | No | Whether to include retrieval explanation details with search or recall results. | |
| agent_id | No | Optional client-supplied agent label for memory attribution. | |
| memory_type | No | Memory type/category filter or value, such as episodic, identity, procedural, semantic, working, auto, or %. | % |
| path_filter | No | Memory path filter; % matches all paths. | % |
| prefer_working | No | Whether to prioritize working/session-state memories in retrieval. | |
| agent_instance_id | No | Optional stable, non-secret agent instance ID for per-client attribution. |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
recall_contextBuild XMemo contextRead-onlyIdempotentInspect
Build a context pack from XMemo memories. Call this before answering or planning when the task could benefit from multiple saved memories — preferences, prior conversations, projects, decisions, TODOs, or long-running work.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of results to return. | |
| query | Yes | Natural-language question or search text. | |
| scope | No | Optional scope that narrows memory access; leave blank for the token default. | |
| bucket | No | Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads. | % |
| team_id | No | Optional team/workspace identifier for team-scoped memory access. | |
| agent_id | No | Optional client-supplied agent label for memory attribution. | |
| max_items | No | Maximum number of memory items to include. | |
| max_tokens | No | Approximate maximum response size. | |
| memory_type | No | Memory type/category filter or value, such as episodic, identity, procedural, semantic, working, auto, or %. | auto |
| output_json | No | Return a machine-readable JSON response instead of a human-readable summary. | |
| path_filter | No | Memory path filter; % matches all paths. | % |
| prefer_working | No | Whether to prioritize working/session-state memories in retrieval. | |
| agent_instance_id | No | Optional stable, non-secret agent instance ID for per-client attribution. |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
recall_planPlan with XMemoRead-onlyIdempotentInspect
Plan which memory searches to run before retrieval. Use only for complex tasks; for ordinary answers call recall_context or recall directly.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Natural-language question or search text. | |
| scope | No | Optional scope that narrows memory access; leave blank for the token default. | |
| bucket | No | Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads. | % |
| team_id | No | Optional team/workspace identifier for team-scoped memory access. | |
| memory_type | No | Memory type/category filter or value, such as episodic, identity, procedural, semantic, working, auto, or %. | % |
| output_json | No | Return a machine-readable JSON response instead of a human-readable summary. | |
| path_filter | No | Memory path filter; % matches all paths. | % |
| prefer_working | No | Whether to prioritize working/session-state memories in retrieval. |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
record_eventRecord EventInspect
Record a significant session event, milestone, decision, or handoff note useful for reconstructing recent work. Not for durable facts/preferences (use remember).
| Name | Required | Description | Default |
|---|---|---|---|
| scope | No | Optional scope that narrows memory access; leave blank for the token default. | |
| bucket | No | Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads. | work |
| content | Yes | Text body to save, such as a memory, TODO/action item, event note, or state summary. | |
| event_type | No | Timeline event type, such as event, milestone, decision, or handoff. | event |
| session_id | No | Optional session identifier associated with the event, timeline query, or snapshot. | |
| metadata_json | No | Optional JSON object string with extra metadata for the operation. | {} |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
record_recall_eval_judgmentRecord Recall Eval JudgmentInspect
Evaluation only — record whether a returned memory was relevant for a query. Do not use in normal conversation.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Natural-language question or search text. | |
| reason | No | Optional user-facing reason for the deletion. | |
| position | No | One-based rank position of the memory in the recall results, or 0 if not returned. | |
| relevant | Yes | Whether the memory was relevant to the recall-evaluation query. | |
| memory_id | Yes | Exact XMemo memory reference shown by search or recall. | |
| metadata_json | No | Optional JSON object string with extra metadata for the operation. | {} |
| expected_relevant_total | No | Expected number of relevant memories for this recall-evaluation query. |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
record_recall_feedbackRecord Recall FeedbackInspect
Record recall corrections. Call this when the user says relevant context was missing or wrong, or supplies memories that should have been found.
| Name | Required | Description | Default |
|---|---|---|---|
| notes | No | Freeform notes explaining recall feedback or corrections. | |
| query | Yes | Natural-language question or search text. | |
| metadata_json | No | Optional JSON object string with extra metadata for the operation. | {} |
| missing_ids_json | No | JSON array of relevant memory IDs that were missing from recall results. | [] |
| returned_ids_json | No | JSON array of memory IDs returned by the recall query. | [] |
| corrected_ids_json | No | JSON array of memory IDs that should have been returned for the recall query. | [] |
| missing_memories_json | No | JSON array of memory snippets or objects that should exist but were missing. | [] |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
redact_memoryRedact MemoryDestructiveInspect
Redact sensitive content from a memory while keeping an audit trail. Call this only when the user explicitly asks to redact.
| Name | Required | Description | Default |
|---|---|---|---|
| reason | No | Optional user-facing reason for the deletion. | |
| memory_id | Yes | Exact XMemo memory reference shown by search or recall. | |
| metadata_json | No | Optional JSON object string with extra metadata for the operation. | {} |
| replacement_content | No | Replacement text to store when redacting or replacing deleted memory content. | [REDACTED] |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
reflectReflectDestructiveInspect
Maintenance tool. Use only when the user/admin asks to summarize, promote, expire, decay, or archive via reflection. Prefer dry_run unless changes are explicitly requested.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of results to return. | |
| scope | No | Optional scope that narrows memory access; leave blank for the token default. | |
| since | No | Only include memories or activity on or after this ISO 8601 timestamp. | |
| until | No | Only include memories or activity on or before this ISO 8601 timestamp. | |
| bucket | No | Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads. | % |
| dry_run | No | Preview the maintenance action without applying changes. | |
| team_id | No | Optional team/workspace identifier for team-scoped memory access. | |
| actions_csv | No | Comma-separated maintenance actions to run, such as summarize, promote, expire, decay, or archive. | summarize,promote,expire,decay,archive |
| path_filter | No | Memory path filter; % matches all paths. | % |
| owner_filter | No | Optional owner/user filter for administrative maintenance tools. | |
| time_window_hours | No | Number of recent hours to inspect during reflection maintenance. |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
rememberRemember in XMemoInspect
Save a memory so it can be recalled in future conversations. Call this whenever the user states a durable fact, preference, instruction, identity or profile detail, project detail, or recurring workflow likely useful later — you do not need an explicit 'remember this'. Skip transient chit-chat. For spending, income, refunds, or bookkeeping requests, use add_expense.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | A simple user-facing category or path for this memory, such as preferences, projects/xmemo, or personal/travel. | |
| scope | No | Optional scope that narrows memory access; leave blank for the token default. | |
| bucket | No | Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads. | public |
| dedupe | No | Whether to check for and merge likely duplicate memories before saving. | |
| content | Yes | Text body to save, such as a memory, TODO/action item, event note, or state summary. | |
| team_id | No | Optional team/workspace identifier for team-scoped memory access. | |
| agent_id | No | Optional client-supplied agent label for memory attribution. | |
| device_id | No | Optional client-supplied device identifier for attribution. | |
| memory_id | No | Exact XMemo memory reference shown by search or recall. | |
| confidence | No | Confidence score for the saved or updated memory, from 0.0 to 1.0. | |
| expires_at | No | Optional ISO 8601 expiration timestamp for the memory. | |
| importance | No | Importance score for the saved or updated memory, from 0.0 to 1.0. | |
| memory_type | No | Memory type/category filter or value, such as episodic, identity, procedural, semantic, working, auto, or %. | auto |
| device_label | No | Optional human-readable device label for attribution. | |
| semantic_key | No | Optional stable semantic key used to identify or upsert a memory concept. | |
| metadata_json | No | Optional JSON object string with extra metadata for the operation. | {} |
| embedding_json | No | Optional JSON array or object containing a precomputed embedding; leave blank for normal use. | |
| provenance_json | No | Optional JSON object string describing memory source, evidence, or attribution. | {} |
| agent_instance_id | No | Optional stable, non-secret agent instance ID for per-client attribution. |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
resolve_decisionResolve DecisionInspect
Record the chosen option for a previously saved pending decision. Call this when the user states their decision.
| Name | Required | Description | Default |
|---|---|---|---|
| resolution | Yes | Chosen resolution text for a pending decision. | |
| decision_id | Yes | Exact pending-decision ID returned by list_pending_decisions. |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
resolve_memory_conflictResolve Memory ConflictDestructiveInspect
Resolve a listed memory conflict. Call this only when the user/admin explicitly chooses a resolution strategy.
| Name | Required | Description | Default |
|---|---|---|---|
| conflict_id | Yes | Exact memory-conflict ID returned by list_memory_conflicts. | |
| merge_content | No | Merged memory content to apply when resolving a conflict with a merge strategy. | |
| metadata_json | No | Optional JSON object string with extra metadata for the operation. | {} |
| winning_memory_id | No | Memory ID that should win when resolving a conflict. | |
| resolution_strategy | No | Conflict resolution strategy, such as mark_conflict, keep_existing, replace, or merge. | mark_conflict |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
restore_memoryRestore XMemo memoryDestructiveInspect
Restore a previously deleted memory. Call this only when the user explicitly asks to restore or undo a deletion.
| Name | Required | Description | Default |
|---|---|---|---|
| reason | No | Optional user-facing reason for the deletion. | |
| memory_id | Yes | Exact XMemo memory reference shown by search or recall. | |
| metadata_json | No | Optional JSON object string with extra metadata for the operation. | {} |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
restore_restart_snapshotRestore Restart SnapshotDestructiveInspect
Resume previous work from a saved snapshot. Call this when the user asks to resume/restart or after context loss.
| Name | Required | Description | Default |
|---|---|---|---|
| scope | No | Optional scope that narrows memory access; leave blank for the token default. | |
| bucket | No | Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads. | work |
| state_key | No | Working-state key to save, snapshot, or restore, such as active_task. | |
| snapshot_id | No | Exact restart snapshot memory ID to restore. | |
| ttl_seconds | No | Time-to-live in seconds for working state or restart snapshot records. | |
| restore_state | No | Whether restore_restart_snapshot should restore the saved working-state record. | |
| source_session_id | No | Session ID whose saved restart snapshot should be restored. | |
| target_session_id | No | Session ID to associate with restored state and restore events. | |
| record_restore_event | No | Whether to write a timeline event after restoring a restart snapshot. |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
run_lifecycleRun LifecycleDestructiveInspect
Maintenance tool. Use only when the user/admin explicitly asks to expire, archive, decay, or dry-run lifecycle processing.
| Name | Required | Description | Default |
|---|---|---|---|
| decay | No | Whether lifecycle maintenance should decay low-value memories. | |
| limit | No | Maximum number of results to return. | |
| scope | No | Optional scope that narrows memory access; leave blank for the token default. | |
| bucket | No | Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads. | % |
| expire | No | Whether lifecycle maintenance should expire memories that reached their expiration policy. | |
| archive | No | Whether lifecycle maintenance should archive stale memories. | |
| dry_run | No | Preview the maintenance action without applying changes. | |
| team_id | No | Optional team/workspace identifier for team-scoped memory access. |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
run_recall_evalRun Recall EvalInspect
Admin/evaluation only — aggregate stored recall judgments and optionally tune retrieval. Not for normal conversation.
| Name | Required | Description | Default |
|---|---|---|---|
| since | No | Only include memories or activity on or after this ISO 8601 timestamp. | |
| until | No | Only include memories or activity on or before this ISO 8601 timestamp. | |
| auto_tune | No | Whether recall evaluation may tune retrieval settings from recorded judgments. |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
search_memorySearch XMemo memoriesRead-onlyIdempotentInspect
Search XMemo memories by natural-language query. Call this when the user asks about saved or past information, AND proactively before answering any question where prior preferences, facts, projects, decisions, or history could change the answer. To delete a memory, use forget.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of results to return. | |
| query | Yes | Natural-language question or search text. | |
| scope | No | Optional scope that narrows memory access; leave blank for the token default. | |
| explain | No | Whether to include retrieval explanation details with search or recall results. | |
| team_id | No | Optional team/workspace identifier for team-scoped memory access. | |
| agent_id | No | Optional client-supplied agent label for memory attribution. | |
| memory_type | No | Memory type/category filter or value, such as episodic, identity, procedural, semantic, working, auto, or %. | % |
| path_filter | No | Memory path filter; % matches all paths. | % |
| prefer_working | No | Whether to prioritize working/session-state memories in retrieval. | |
| agent_instance_id | No | Optional stable, non-secret agent instance ID for per-client attribution. |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
store_memoryAdvanced: store XMemo memoryInspect
Low-level memory write with full field control. Use only when a caller needs explicit field-level control; for normal conversational capture use remember.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | A simple user-facing category or path for this memory, such as preferences, projects/xmemo, or personal/travel. | |
| scope | No | Optional scope that narrows memory access; leave blank for the token default. | |
| bucket | No | Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads. | public |
| content | Yes | Text body to save, such as a memory, TODO/action item, event note, or state summary. | |
| team_id | No | Optional team/workspace identifier for team-scoped memory access. | |
| agent_id | No | Optional client-supplied agent label for memory attribution. | |
| device_id | No | Optional client-supplied device identifier for attribution. | |
| confidence | No | Confidence score for the saved or updated memory, from 0.0 to 1.0. | |
| expires_at | No | Optional ISO 8601 expiration timestamp for the memory. | |
| importance | No | Importance score for the saved or updated memory, from 0.0 to 1.0. | |
| memory_type | No | Memory type/category filter or value, such as episodic, identity, procedural, semantic, working, auto, or %. | semantic |
| device_label | No | Optional human-readable device label for attribution. | |
| semantic_key | No | Optional stable semantic key used to identify or upsert a memory concept. | |
| metadata_json | No | Optional JSON object string with extra metadata for the operation. | {} |
| embedding_json | No | Optional JSON array or object containing a precomputed embedding; leave blank for normal use. | |
| provenance_json | No | Optional JSON object string describing memory source, evidence, or attribution. | {} |
| agent_instance_id | No | Optional stable, non-secret agent instance ID for per-client attribution. |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
update_memoryUpdate XMemo memoryDestructiveInspect
Update the content, location, or type of an existing memory. Call this only when the user explicitly asks to correct, revise, move, or reclassify a specific saved memory.
| Name | Required | Description | Default |
|---|---|---|---|
| path | No | A simple user-facing category or path for this memory, such as preferences, projects/xmemo, or personal/travel. | |
| scope | No | Optional scope that narrows memory access; leave blank for the token default. | |
| bucket | No | Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads. | |
| status | No | Memory status filter or update value, such as active, archived, deleted, or %. | |
| content | No | Text body to save, such as a memory, TODO/action item, event note, or state summary. | |
| team_id | No | Optional team/workspace identifier for team-scoped memory access. | |
| memory_id | Yes | Exact XMemo memory reference shown by search or recall. | |
| confidence | No | Confidence score for the saved or updated memory, from 0.0 to 1.0. | |
| expires_at | No | Optional ISO 8601 expiration timestamp for the memory. | |
| importance | No | Importance score for the saved or updated memory, from 0.0 to 1.0. | |
| memory_type | No | Memory type/category filter or value, such as episodic, identity, procedural, semantic, working, auto, or %. | |
| semantic_key | No | Optional stable semantic key used to identify or upsert a memory concept. | |
| metadata_json | No | Optional JSON object string with extra metadata for the operation. | {} |
| merge_metadata | No | Whether to merge new metadata with existing metadata instead of replacing it. | |
| provenance_json | No | Optional JSON object string describing memory source, evidence, or attribution. | {} |
| detect_conflicts | No | Whether to detect possible conflicts with existing memories during an update. | |
| merge_provenance | No | Whether to merge new provenance with existing provenance instead of replacing it. | |
| supersession_reason | No | Reason the updated memory supersedes older content. |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
update_stateUpdate StateInspect
Save the current working state during long-running work — active task, next action, or blocker — so future turns/sessions can resume. For durable user facts use remember.
| Name | Required | Description | Default |
|---|---|---|---|
| scope | No | Optional scope that narrows memory access; leave blank for the token default. | |
| bucket | No | Memory bucket or namespace to read from or write to; use % only for tools that support wildcard reads. | work |
| content | No | Text body to save, such as a memory, TODO/action item, event note, or state summary. | |
| state_key | No | Working-state key to save, snapshot, or restore, such as active_task. | active_task |
| next_action | No | Next action to persist so future turns can resume the work. | |
| ttl_seconds | No | Time-to-live in seconds for working state or restart snapshot records. | |
| current_task | No | Current task or work item to persist for later resume. | |
| metadata_json | No | Optional JSON object string with extra metadata for the operation. | {} |
| blocked_reason | No | Short explanation of why the current work is blocked. |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
Discussions
No comments yet. Be the first to start the discussion!