Skip to main content
Glama
524,441 tools. Updated 2026-09-06 15:49

"Understanding or Using Memory Lists" matching MCP tools:

  • Permanently delete one memory by UUID. When to use: user asks to remove outdated or incorrect context, or to free plan storage. When NOT: fix content → update (mode=replace); find the ID first → list_memories or recall. Requires delete OAuth scope. Non-idempotent: deleting the same memory_id twice fails. Errors: Memory not found, Not authorized to delete this memory. Side effects: removes the memory row and vector embedding with no recovery; invalidates plan cache. The target workspace is always the one the memory itself belongs to (echoed in resolved_workspace); optionally pass workspace: <name> as a safety confirmation — the call fails if the memory is not actually in that workspace.
    Connector
    Destructive
    No auth
  • Update an existing memory by ID. Use mode replace (default) to patch fields, or append to extend content. Re-embeds only when content changes. The target workspace is always the one the memory itself belongs to (echoed in resolved_workspace); optionally pass workspace: <name> as a safety confirmation — the call fails if the memory is not actually in that workspace.
    ConnectorNo auth
  • A table of contents for this user's memory: which sources are connected (email, calendar, docs, …), how many items each holds, and the top people, topics and projects. It is an index rather than an answer — it contains no message bodies, no dates and no content, so it establishes that a source exists without saying anything about what is in it. The content behind any entry it lists is retrievable with cortex_ask.
    ConnectorNo auth
  • Open the Project Workspace. With no project reference it always opens Project Workspaces Home — the caller's authorized project list — even when exactly one project is accessible. An exact project_id, or a project name/alias matching exactly one authorized project, opens that project's eight tabs (overview, memory, todo, decisions, documents, conversations, timeline, settings); multiple or no matches return Home with candidates or an honest no-match state. For a quick text-only status, blockers, or next-actions answer use get_project_summary. Explicit standalone TODO or Ledger intent keeps using open_todo_board or open_ledger.
    ConnectorOAuth
  • Retrieve the full content and metadata of one memory by its UUID. Use after list_memories or recall returned a truncated preview and you need the complete text. Returns content, memory_type, tags, collection, importance, and the creation timestamp. Get the UUID from a prior list_memories or recall result. The workspace this memory belongs to is determined by its ID and echoed in resolved_workspace; optionally pass workspace: <name> to confirm the memory belongs to that team workspace (errors if it does not).
    ConnectorNo auth
  • Delete one memory, TODO, or Ledger transaction by natural target ('latest', 'current', an exact memory ID (with memory_id accepted as an equivalent exact-reference alias), an exact TODO ID from the current TODO listing, or an exact Ledger transaction ID from ledger(action='list')). Defaults to a recoverable soft delete (restore later with restore_memory); pass mode='hard' only after the user has explicitly confirmed a permanent, unrecoverable deletion in this conversation. Call this only when the user explicitly asks to delete a specific memory, TODO, or expense/income record; list/search or check activity first if the target is ambiguous.
    Connector
    Destructive
    OAuth

Matching MCP Servers

Matching MCP Connectors

  • Persistent semantic memory storage, associative recall, and recent memory index by namespace.

  • Cultural color and colour intelligence API. Every colour anchored to a named person, a documented year, and a consequence. 34 archives spanning literary, cultural, pigment, and national traditions. Ask it what color could get you executed in the Ottoman Empire.

  • Scans a block of text against all published Arco Lexicon terms using deterministic string matching — no LLM calls. Returns two lists: terms whose canonical names appear explicitly in the text (detected), and terms whose concepts are present but whose canonical names are absent (suggested). Maximum 10,000 characters. Use this to audit an article or passage for correct and complete Arco terminology. Use verify_alignment instead when you want a scored alignment report rather than a term discovery list.
    ConnectorNo auth
  • Reference / metadata for the PIP dataset. table="versions" lists available data releases & PPP rounds; table="aux_list" lists all auxiliary tables; any other value (e.g. "countries", "regions", "poverty_lines", "indicators", "dictionary") returns that auxiliary table. Use to look up valid country codes, region mappings, or supported indicators.
    ConnectorNo auth
  • Memory health: per-source ingest and embed counts plus last sync times. Use when you need to know whether the memory is fresh or still ingesting, or when a search came back empty and you need to tell the user whether that means "no data yet" or "nothing matched".
    ConnectorNo auth
  • Read one exact authorized XMemo memory in character windows. Use a memory ID returned by recall or search, then continue long content with next_offset. Embeddings are never returned.
    ConnectorOAuth
  • Published Truss information by topic. Localized topics (overview, about, services, engagement, fit, faq) use locale, default en; pass he for Hebrew. Language-independent topics (identity, certifications, testimonials, clients, contact) ignore locale for content selection. Prefer get_truss_overview or topic overview for broad business understanding; prefer list_truss_services for the complete service catalog.
    ConnectorNo auth
  • List the Hunter.io lead lists connected to this account. Use it to find a listId before sync_lead_list, or to check whether a list already exists before create_lead_list makes a duplicate. These are Hunter.io's lists, which are separate from the leads stored locally — list_leads shows those. Reads only, costs no credits, takes no parameters. Requires an API key and a connected Hunter.io account. An empty result means no lists exist yet.
    ConnectorNo auth
  • UNDERSTANDING — CATALOG-WIDE operation search: which providers expose a path matching your terms. "Who has a POST /refunds" had no answer before this — tags are what a company says about itself, a path is what its API accepts. Terms match path SEGMENTS (all must appear), so q="payment intents" finds /payments/v1/intents. Add method to narrow by verb, deprecated=true for the retiring ones. One row per real operation: a provider's spec is split per tag, so the same call can live in several of its documents, and `apis` lists them all. Reads matching providers' surfaces up to max_providers (cap 100) and tells you in `meta.query.truncated` when more matched than were read.
    ConnectorNo auth
  • Retrieve the full, unabridged content of a specific memory by its ID from Memwyre. Use this when `search_memwyre` returns a snippet with `[ID: mem_XXX]` and you need to read the complete original document, report, or note. Args: memory_id: The ID of the memory (e.g., 'mem_73').
    ConnectorAPI key
  • Free catalog lookup. Lists the raw Japanese public-sector business-opportunity datasets on this gateway (open tender notices, subsidy programs, procurement sanction lists) with per-call x402 pricing (0.05 USDC per call). Use the search/get tools or the returned api_url to retrieve data.
    ConnectorNo auth
  • Permanently delete a playbook and all of its contents (persona, skills, memory, API keys, canvas, and secrets). This cannot be undone. Requires playbooks:write or full permission, and only the owner may delete. Do not use this to reset a persona (delete_persona) or remove a single skill or memory; those have dedicated tools.
    Connector
    Destructive
    No auth
  • Save or update a living memory/document by title in the Memwyre Vault. If a memory with a matching title already exists in this workspace, it will be updated in-place with the new text and re-indexed (preventing duplicate entries). If no existing memory matches the title, a new memory is created. Use this tool when maintaining living documents (e.g. project architecture, meeting notes, benchmarks, user preferences). Args: title: Unique title or topic name (e.g., 'Production Retrieval Benchmark' or 'System Architecture'). text: The full content to save or update (Markdown fully supported, do not summarize). source: Source of memory (default 'mcp'). tags: Optional list of categorization tags (e.g., ['benchmarks', 'architecture']). workspace_name: Optional workspace name to scope this memory.
    ConnectorAPI key
  • Returns the complete Trident 2D specification including grammar, syntax rules, coordinate system, containers, nodes, connections, shapes, and icon reference. Use this when you need deep understanding of the Trident DSL.
    ConnectorNo auth
  • List Categories List all agent categories with counts. Returns every category in the directory along with the number of agents in each. Useful for building category filters or understanding the directory's coverage areas. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json **Example Response:** ```json [ { "category": "Category", "count": 1 } ] ```
    ConnectorNo auth
  • Get aggregate statistics about missions on the HomeVisto platform. Returns total counts, status breakdown, and average bounty information. Useful for understanding platform activity.
    ConnectorNo auth
  • Simulate int8 or int4 quantization of float32 embedding vectors. Reduces storage by 4x (int8) or 8x (int4). Returns quantized values, scale factor, and precision loss (MSE). Useful for understanding vector DB compression trade-offs.
    ConnectorNo auth