Turbo Quant Memory MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TQMEMORY_EMBEDDING_BACKEND | No | The embedding backend to use. Set to 'fastembed' to use ONNX Runtime instead of PyTorch. | sentence-transformers |
| TQMEMORY_SECRETS_PASSPHRASE | No | Passphrase for the secrets vault. Must be a passphrase, not a raw key. Used only if you intend to use the secrets vault. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Use remember_note(..., kind=..., scope="project") to store typed project notes, promote reusable knowledge into global scope, deprecate stale notes without deleting history, retrieve compact project/global/hybrid memory, hydrate fuller local context through hydrate(...), index Markdown roots through index_paths(...), and run lint_knowledge_base(...) to detect broken links, orphans, and duplicate titles. To exclude directories or files from indexing, create a .tqmemoryignore file in the project root with glob patterns (one per line, # for comments). Example patterns: 'workspace-' skips dirs matching the glob, 'data/reports/.md' skips specific paths. When several agents share one working tree: call workspace_status at session start, announce_work when starting a feature and finish_work when done; read the workspace field whenever a response carries it and re-read any file another session changed before writing it; file_history and restore_file recover overwritten files. Call workspace_status before editing a file another session may have touched, and before every commit while other sessions are live. While other sessions are live, never run destructive git commands (checkout -- ., reset --hard, stash, clean, branch switch) without the human's explicit confirmation. A session under idle_sessions made no tqmemory call for 30+ minutes and is not an active peer; a session's mere presence or old last_activity_at is never a reason to postpone work, only overlaps and recent_changes are.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| healthD | – |
| server_infoD | – |
| list_scopesD | – |
| list_projectsB | List saved projects with labels and explicitly bound folders. |
| select_projectB | Select an existing project by ID for this connection; omit ID to reset. Вибирає наявний проєкт для цього підключення; без ідентифікатора скидає вибір. |
| set_project_labelsB | Set display-only labels for an existing project id. |
| bind_projectA | Bind a folder to an existing project and use it in this MCP session. The folder must already exist. This does not index its files. Use the exact project_id from list_projects; labels are never identifiers. |
| unbind_projectB | Remove an exact folder binding; reset this session if it used it. |
| self_testD | – |
| remember_noteA | Store a typed project note. kind must be exactly one of: lesson, decision, pattern, handoff. tags: 2-3 lowercase tags are strongly recommended — tags are the only way
to FILTER notes; an untagged note is reachable by semantic_search alone.
source_refs: the files / notes / issues this note is about. Pass them as
entity URIs (note://, file://<relative/path>, issue://KEY,
https://...) and they are auto-linked into the knowledge graph as
After storing, connect the note with link_entities(source_uri="note://", ...) when it relates to a file, issue, or prior note — the response echoes the note's uri and hints this when the note still has no relations. |
| promote_noteD | – |
| deprecate_noteD | – |
| semantic_searchA | Compact memory retrieval (dense vector + BM25, fused via RRF). By default only the source_filter narrows results by source type: |
| hydrateD | – |
| index_pathsC | Register and index Markdown directories into project memory. Supports .tqmemoryignore files (placed in project root or any indexed
directory) with glob patterns to exclude paths from indexing.
One pattern per line, # for comments. Example patterns:
|
| lint_knowledge_baseD | – |
| link_entitiesC | Create a Knowledge Graph link between two entities. Entities are specified using URIs:
|
| unlink_entitiesB | Remove a Knowledge Graph link between two entities. source_uri / target_uri use the same URI forms as link_entities: note://<note_id>, file://<relative/path>, issue://KEY, https://... |
| get_related_entitiesA | Query relations involving a specific entity URI. uri: the entity to look up, as note://<note_id>, file://<relative/path>, issue://KEY, task://KEY, or https://... — the same URI forms link_entities accepts. Returns nothing for an entity that has no links yet. |
| set_secretA | Store an encrypted secret in the active project's vault. The value is encrypted with AES-256-GCM under a per-project master
key resolved from TQMEMORY_SECRETS_PASSPHRASE or the OS keyring.
Secrets are NEVER indexed, embedded, or returned via
|
| get_secretA | Fetch a project secret by exact name. Returns the value in a dedicated |
| list_secretsA | List secret names in the active project. Never returns values. |
| delete_secretC | Delete a project secret by exact name. |
| recent_contextA | Query-free session bootstrap: the most recently updated notes. Call this FIRST when starting a new session or resuming after a context
compaction, when you do not yet know what to search for. Returns notes
ordered by recency (newest first), NOT by relevance — including
scope: 'project' (default), 'global', or 'hybrid'. Use 'hybrid' to also surface promoted cross-project knowledge. tier_filter: defaults to all tiers (so handoffs are included). Pass e.g. ["durable"] to exclude episodic session notes. format: 'json' (default); 'text' — compact plain text, one line per note with its hydrate handle (about 20% of the JSON size); 'hook' — the same text as Claude Code SessionStart hook output. Use 'hook' from a SessionStart mcp_tool hook: Claude Code shows the model only an mcp_tool hook's JSON additionalContext, never its plain text. |
| announce_workC | Tell the other agents in this working tree what you are changing. feature: short name of the work. areas: workspace-relative files or directories (globs allowed). Returns the peers whose announced areas overlap yours and recent changes inside them. Inferred writers are guesses from announced areas, never facts. |
| finish_workB | Clear the work this session announced with announce_work. |
| workspace_statusA | Overview of the sessions sharing this working tree: peers, overlaps and recent file changes. Call it at session start. Inferred writers are guesses from announced areas, never facts.
Peers that made no tqmemory call for a long time are listed under |
| file_historyA | Journaled versions of one file in this working tree, newest first. Versions are snapshots taken while several sessions share the tree. Use restore_file with a version id to bring one back; the overwritten content is kept as a new version. |
| restore_fileA | Write a journaled version of one file back into the working tree. version: a version id from file_history, or "HEAD" for the committed content. The content being overwritten is kept as a new version, so the restore can be undone. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 29 tools
Core clusters (notes, secrets, knowledge-graph links, multi-agent work) are reasonably distinct and the richer descriptions clarify boundaries like semantic_search vs recent_context. However, several tools have no description at all (self_test, health, server_info, list_scopes, hydrate, promote_note, deprecate_note, lint_knowledge_base), and the diagnostics trio plus list_scopes/list_projects and select_project/bind_project invite confusion. select_project's description is partially non-English, further reducing clarity.
Names are overwhelmingly snake_case with a verb_noun or noun_state pattern (remember_note, link_entities, set_secret, list_secrets, index_paths, restore_file). Minor deviations are noun-only forms like health, hydrate, server_info, workspace_status, file_history, which are still readable and idiomatic. No camelCase/snake_case mixing.
29 tools is heavy and spans five subdomains (notes, secrets, projects/indexing, multi-agent coordination, file journaling, plus diagnostics). Each cluster mostly earns its place, but the three overlapping diagnostics tools (self_test, health, server_info) look like padding that inflates the surface. It borders on too many for a 'memory' server.
Coverage is strong: full secret CRUD, note lifecycle (remember/promote/deprecate) plus retrieval and KG links, project bind/unbind/label/index, and coordination with file history/restore. Gaps exist, notably no update/edit or delete operation for notes and no explicit project creation tool (only binding to an existing project_id).