Skip to main content
Glama

YantrikDB MCP Server

Kognitives Gedächtnis für KI-Agenten. Funktioniert mit Claude Code, Cursor, Windsurf und jedem MCP-kompatiblen Client.

Website: yantrikdb.com · Dokumentation: yantrikdb.com/guides/mcp · GitHub: yantrikos/yantrikdb-mcp

Installation

pip install yantrikdb-mcp

Related MCP server: memex

Konfiguration

Der MCP-Server verfügt über drei Bereitstellungsmodi. Wählen Sie denjenigen, der zu Ihrem Setup passt.

Modus 1 — Lokal (Standard, empfohlen für Einzelbenutzer)

Der MCP-Server führt die Engine innerhalb des Prozesses mit einer lokalen SQLite-Datenbank aus. Schnell, privat, keine Abhängigkeiten.

{
  "mcpServers": {
    "yantrikdb": {
      "command": "yantrikdb-mcp"
    }
  }
}

Das ist alles. Der Agent ruft automatisch Kontext ab, erinnert sich an Entscheidungen und erkennt Widersprüche — kein Prompting erforderlich.

Modus 2 — HTTP-Cluster (empfohlen für gemeinsam genutzte/Multi-Maschinen-Setups)

Leiten Sie alle Tool-Aufrufe an einen YantrikDB HTTP-Cluster weiter, anstatt eine eingebettete Engine zu verwenden. Der MCP-Server ist ein schlanker, zustandsloser Client — alle Erinnerungen befinden sich im Cluster und sind von jeder Maschine aus zugänglich.

Vorteile: gemeinsamer Speicher über Maschinen hinweg, hohe Verfügbarkeit, kein lokaler Download des Embedders, keine lokale Datenbank.

{
  "mcpServers": {
    "yantrikdb": {
      "command": "yantrikdb-mcp",
      "env": {
        "YANTRIKDB_SERVER_URL": "http://node1:7438,http://node2:7438",
        "YANTRIKDB_TOKEN": "ydb_your_database_token"
      }
    }
  }
}
  • Kommagetrennte Auflistung mehrerer Knoten für die automatische Erkennung des Raft-Clusters

  • Automatisches Leader-Following bei Failover

  • 15s Anfrage-Timeout

  • Token vom Cluster abrufen: yantrikdb token create --db your_database

Modus 3 — SSE-Server (Legacy, einzelne Remote-Instanz)

Führen Sie den MCP-Server selbst als langlebigen SSE-Server mit einer eigenen eingebetteten Datenbank aus. Clients verbinden sich über HTTP-Streaming.

# Generate a secure API key
export YANTRIKDB_API_KEY=$(python -c "import secrets; print(secrets.token_urlsafe(32))")

# Start SSE server
yantrikdb-mcp --transport sse --port 8420
{
  "mcpServers": {
    "yantrikdb": {
      "type": "sse",
      "url": "http://your-server:8420/sse",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

Unterstützt sse und streamable-http Transporte. Hinweis: SSE-Verbindungen können bei Leerlauf abbrechen — Modus 2 (HTTP-Cluster) ist für gemeinsam genutzte Bereitstellungen zuverlässiger.

Umgebungsvariablen

Variable

Verwendet in Modus

Standard

Beschreibung

YANTRIKDB_SERVER_URL

Cluster

(nicht gesetzt → lokaler Modus)

Kommagetrennte Cluster-Knoten-URLs

YANTRIKDB_TOKEN

Cluster

(keine)

Bearer-Token für die Cluster-Datenbank

YANTRIKDB_DB_PATH

Lokal

~/.yantrikdb/memory.db

Pfad zur Datenbankdatei

YANTRIKDB_EMBEDDING_MODEL

Lokal

all-MiniLM-L6-v2

Sentence-Transformer-Modell

YANTRIKDB_EMBEDDING_DIM

Lokal

384

Embedding-Dimension

YANTRIKDB_API_KEY

SSE-Server

(keine)

Bearer-Token bei Bereitstellung von SSE/HTTP

Warum kein dateibasiertes Gedächtnis?

Dateibasiertes Gedächtnis (CLAUDE.md, Speicherdateien) lädt alles bei jedem Gespräch in den Kontext. YantrikDB ruft nur das ab, was relevant ist.

Benchmark: 15 Abfragen × 4 Skalen

Erinnerungen

Dateibasiert

YantrikDB

Einsparungen

Präzision

100

1.770 Token

69 Token

96%

66%

500

9.807 Token

72 Token

99,3%

77%

1.000

19.988 Token

72 Token

99,6%

84%

5.000

101.739 Token

53 Token

99,9%

88%

Selektiver Abruf ist O(1). Dateibasiertes Gedächtnis ist O(n).

  • Bei 500 Erinnerungen überschreitet dateibasiertes Gedächtnis 32K Kontextfenster

  • Bei 5.000 passt es in kein Kontextfenster — nicht einmal 200K

  • YantrikDB bleibt bei ~70 Token pro Abfrage, unter 60ms Latenz

  • Die Präzision verbessert sich mit mehr Daten — das Gegenteil von Context Stuffing

Führen Sie den Benchmark selbst aus: python benchmarks/bench_token_savings.py

Tools

15 Tools, volle Engine-Abdeckung:

Tool

Aktionen

Zweck

remember

single / batch

Erinnerungen speichern — Entscheidungen, Präferenzen, Fakten, Korrekturen

recall

search / refine / feedback

Semantische Suche, Verfeinerung und Abruf-Feedback

forget

single / batch

Erinnerungen löschen

correct

—

Falsche Erinnerung korrigieren (bewahrt Historie)

think

—

Konsolidierung + Konflikterkennung + Mustererkennung

memory

get / list / search / update_importance / archive / hydrate

Einzelne Erinnerungen verwalten + Stichwortsuche

graph

relate / edges / link / search / profile / depth

Wissensgraph-Operationen

conflict

list / get / resolve / reclassify

Widersprüche behandeln und Substitutionsmuster lehren

trigger

pending / history / acknowledge / deliver / act / dismiss

Proaktive Erkenntnisse und Warnungen

session

start / end / history / active / abandon_stale

Sitzungslebenszyklus-Management

temporal

stale / upcoming

Zeitbasierte Speicherabfragen

procedure

learn / surface / reinforce

Prozedurales Gedächtnis — Strategien lernen und wiederverwenden

category

list / members / learn / reset

Substitutionskategorien für Konflikterkennung

personality

get / set

KI-Persönlichkeitsmerkmale aus Speichermustern

stats

stats / health / weights / maintenance

Engine-Statistiken, Status, Gewichte und Index-Neuerstellungen

Siehe yantrikdb.com/guides/mcp für die vollständige Dokumentation.

Beispiele

1. Automatischer Abruf zu Beginn des Gesprächs

Benutzer: "Was haben wir bezüglich der Datenbankmigration entschieden?"

Der Agent ruft automatisch recall("database migration decision") auf und ruft relevante Erinnerungen ab, bevor er antwortet — kein manuelles Prompting erforderlich.

2. Entscheidungen merken + Wissensgraph aufbauen

Benutzer: "Wir entscheiden uns für PostgreSQL für den neuen Dienst. Alice wird die Migration leiten."

Der Agent ruft auf:

  • remember(text="Decided to use PostgreSQL for the new service", domain="architecture", importance=0.8)

  • remember(text="Alice owns the PostgreSQL migration", domain="people", importance=0.7)

  • graph(action="relate", entity="Alice", target="PostgreSQL Migration", relationship="owns")

3. Konflikterkennung

Nachdem "Wir verwenden Python 3.11" gespeichert wurde und später "Wir haben auf Python 3.12 aktualisiert", erkennt der Aufruf von think() den Konflikt. Der Agent weist darauf hin:

"Ich habe einen Widerspruch gefunden: Sie sagten zuvor Python 3.11, erwähnten aber kürzlich Python 3.12. Was ist aktuell?"

Löst dann mit conflict(action="resolve", conflict_id="...", strategy="keep_b") auf.

Datenschutzrichtlinie

YantrikDB MCP Server speichert alle Daten lokal auf Ihrem Computer (Standard: ~/.yantrikdb/memory.db). Es werden keine Daten an externe Server gesendet, keine Telemetrie erfasst und während des Betriebs werden keine Drittanbieterdienste kontaktiert.

  • Datenerfassung: Nur das, was Sie explizit über das remember-Tool speichern oder was der KI-Agent in Ihrem Namen speichert.

  • Datenspeicherung: Lokale SQLite-Datenbank auf Ihrem Dateisystem. Sie steuern den Pfad über YANTRIKDB_DB_PATH.

  • Weitergabe an Dritte: Keine. Daten verlassen Ihren Computer im lokalen (stdio) Modus niemals.

  • Netzwerkmodus: Bei Verwendung des SSE/HTTP-Transports fließen Daten zwischen Ihrem Client und Ihrem selbst gehosteten Server. Es sind keine Anthropic- oder Drittanbieter-Server beteiligt.

  • Embedding-Modell: Verwendet ein lokales ONNX-Modell (all-MiniLM-L6-v2). Modelldateien werden bei der ersten Verwendung einmal vom Hugging Face Hub heruntergeladen und dann lokal zwischengespeichert.

  • Aufbewahrung: Daten bleiben bestehen, bis Sie sie löschen (forget-Tool) oder die Datenbankdatei löschen.

  • Kontakt: developer@pranab.co.in

Vollständige Richtlinie: yantrikdb.com/privacy

Mitwirken

Siehe CONTRIBUTING.md für ein venv-Setup, das Ausführen von pytest und das Öffnen von PRs.

Support

Lizenz

Dieser MCP-Server ist unter MIT lizenziert — verwenden Sie ihn frei in jedem Projekt.

Hinweis: Dieses Paket hängt von yantrikdb (der kognitiven Speicher-Engine) ab, die unter AGPL-3.0 lizenziert ist. Die AGPL gilt für die Engine selbst — wenn Sie die Engine modifizieren und verbreiten oder als Netzwerkdienst bereitstellen, müssen diese Modifikationen ebenfalls AGPL-3.0 sein. Die Verwendung der Engine wie sie ist über diesen MCP-Server löst keine AGPL-Verpflichtungen für Ihren Code aus.

Available Tools

21 tools
atlasA
Read-onlyIdempotent

Export this store's Memory Atlas (a static page: every memory, its entity links, claims, revision history and tasks) and serve it on 127.0.0.1. Read-only; nothing leaves the machine.

ACTIONS:

  • "export": (default) export and serve; returns the local URL, the output directory and the exporter's report. Re-running refreshes the files under the same URL.

  • "status": the atlas servers this process is running.

Args: out_dir: Output directory (default <store>.atlas/ beside the store). port: Local port (0 = free one). label: Provenance label shown in the page header. open_browser: Also open the URL in the browser.

Embedded mode only (cluster mode: use the yantrikdb atlas CLI on a node). Needs an engine that ships yantrikdb/atlas/.

Inputs: port, label, action, out_dir, +1 more. Returns: result

categoryA
Destructive

Substitution categories for conflict detection — list, inspect, teach, or reset.

ACTIONS:

  • "list": Show all categories with member counts.

  • "members": Show members of a specific category (needs category_name).

  • "learn": Teach new members (needs category_name + members as [[token, confidence], ...]).

  • "reset": Reset category to seed state (needs category_name).

EXAMPLES:

  • category() → list all categories

  • category(action="members", category_name="databases")

  • category(action="learn", category_name="databases", members=[["tidb", 0.35]])

  • category(action="reset", category_name="editors_tools")

Args: action: "list", "members", "learn", "reset". category_name: Required for members/learn/reset. members: For learn: [[token, confidence], ...]. source: For learn: "llm_suggested", "user_confirmed", "seed".

Inputs: action, source, members, category_name. Returns: result

conflictA
Destructive

Manage memory conflicts (contradictions) — list, resolve, dismiss, reclassify, or batch-burn-down the unambiguous ones (v0.8.0+).

ACTIONS:

  • "list": List conflicts. Optional status filter.

  • "get": Get single conflict by conflict_id.

  • "resolve": Resolve with strategy: "keep_a"/"keep_b"/"keep_both"/"merge"/"dismiss".

  • "reclassify": Reclassify conflict type.

  • "auto_resolve": v0.8.0 — burn down unambiguous conflicts in one pass. Set dry_run=False to actually persist.

Args: action: "list", "get", "resolve", "reclassify", "auto_resolve". conflict_id / status / strategy / winner_rid / new_text / resolution_note / new_type / limit: see action docs above. dry_run: For auto_resolve — preview without persisting.

Inputs: limit, action, status, dry_run, +6 more. Returns: result

conversationA
Destructive

Bounded encrypted working-memory ring buffer for raw conversation turns (v0.9.0 engine conversation primitive).

Unlike remember (which stores extracted semantic memories), this stores verbatim turns — useful for short-horizon working memory, e.g. "what exactly did the user say two messages ago". The ring is bounded per namespace; oldest turns evict when max_turns is exceeded.

ACTIONS:

  • "record": Append a turn (needs role + content).

  • "recent": Retrieve last N turns, oldest-first.

  • "clear": Drop the buffer for a namespace.

Args: action: "record" | "recent" | "clear". namespace: Ring buffer namespace (separate buffers per agent / topic). role: "user" | "assistant" | "system" | "tool" — caller's choice. content: The verbatim turn text. max_turns: Ring size at record time (default 10). limit: How many recent turns to return.

Inputs: action (required), role, limit, content, +2 more. Returns: result

correctA
Destructive

Correct an existing memory in-place with a revision-history entry (engine v0.7.20+, Issue #47).

WHEN TO USE: When the user corrects a recalled fact.

  • "Actually, we're using Python 3.12, not 3.11" → correct the memory.

Preserves history via an append-only revision entry keyed on reason. Entity relationships stay attached to the same rid (in-place mutation, not a tombstone+new-rid dance).

Args: rid: The memory ID to correct. reason: Required — why the correction was made. Non-empty. Recorded on the revision-history entry so future recall + audit can reconstruct why the memory changed. new_text: Optional new text (pass None to keep existing). new_importance: Optional updated importance (0.0-1.0). new_valence: Optional updated valence (-1.0 to 1.0). metadata_merge: Optional dict to merge into existing metadata (None = keep as-is).

Inputs: rid (required), reason (required), new_text, new_valence, +2 more. Returns: result

forgetA
DestructiveIdempotent

Permanently forget (tombstone) one or more memories.

WHEN TO USE: When the user explicitly asks to forget something, or when a memory is clearly wrong and correction isn't appropriate. Prefer correct over forget when the memory just needs updating.

Args: rid: Single memory ID to forget. rids: List of memory IDs to forget (batch mode).

Inputs: rid, rids. Returns: result

gapsA
Read-onlyIdempotent

Surface knowledge gaps — frequently-asked, poorly-answered queries (v0.9.0 engine demand log).

The substrate logs every recall and tracks how often each query is asked

  • what top scores it surfaces. knowledge_gaps() returns the queries that are asked often but answered poorly — the substrate's "known unknowns". Use this to drive proactive learning: when the agent sees a gap, it can ask the user, fetch info, or note the limitation.

Args: min_count: Only surface queries asked at least this many times. max_avg_top_score: Only surface queries whose best recall score averages below this (lower = poorer answer). limit: Max gaps to return.

Inputs: limit, min_count, max_avg_top_score. Returns: result

graphB

Knowledge graph operations — entity relationships, memory↔entity links, record-to-record links, co-occurrence auto-relate, and link-expanded recall.

ACTIONS:

  • "relate": Entity↔entity relationship (legacy).

  • "edges": Get all relationships for entity.

  • "link": Link a memory (rid) to an entity (legacy).

  • "search": Find entities by pattern.

  • "profile": Rich entity profile.

  • "depth": How deeply the system knows an entity.

  • "auto_relate": v0.8.0 — co-occurrence-driven edge backfill. Set dry_run=False to persist.

  • "record_link": v0.9.0 — add a record-to-record link (needs source_rid + target_rid + link_type).

  • "record_unlink": v0.9.0 — remove a record-to-record link.

  • "linked_records": v0.9.0 — traverse links from rid (direction = "outbound" | "inbound" | "both", optional link_type filter).

  • "recall_with_links": v0.9.0 — semantic recall with N-hop link expansion.

Args: action: One of the actions above. entity / target / relationship / weight / rid / pattern / limit / days / namespace: Legacy entity-graph args. source_rid / target_rid / link_type: For record_link / record_unlink. direction: For linked_records — "outbound" / "inbound" / "both". dry_run: For auto_relate — preview without persisting. max_edges: For auto_relate — cap edges proposed/created. query: For recall_with_links — natural language search. top_k: For recall_with_links — max seed results. expand_links: For recall_with_links — hop budget for traversal.

Inputs: action (required), rid, days, limit, +15 more. Returns: result

memoryA

Manage individual memories — get, list, search, update importance, archive, hydrate, relevance feedback, fetch a chain-shaped namespace's head, or query revision history.

ACTIONS:

  • "get": Retrieve a single memory by rid.

  • "list": Browse memories with filters.

  • "search": Keyword substring search.

  • "update_importance": Change a memory's importance score.

  • "archive": Move to cold storage.

  • "hydrate": Restore archived memory.

  • "feedback": v0.10 — relevance feedback on a recalled memory (needs rid + feedback="relevant"|"irrelevant"). Call after USING a recalled memory; it tunes future retrieval. (Moved here from recall, which is now read-only.)

  • "chain_head": The CURRENT value of a chain-shaped namespace (narrative / decision / config chains). Use this — not recall — for "what is the current/latest X": similarity search favors the most-similar revision, chain_head returns the newest.

  • "history": v0.8.0 — revision history for a single rid (needs rid).

Args: See action docs above. New args: namespace: Required for chain_head — the chain-shaped namespace. rid: Required for history/feedback — the record acted on. feedback: For feedback — "relevant" or "irrelevant". feedback_query: For feedback — the query that surfaced the memory. feedback_score / feedback_rank: For feedback — retrieval context.

Inputs: action (required), rid, limit, domain, +10 more. Returns: result

packA
Destructive

Signed, portable memory bundles — inspect, install, and trust packs.

A pack is a sealed corpus another agent or vendor published. Mounted pack memories are recallable alongside your own but are DOWN-WEIGHTED (tier_multiplier < 1.0): what the user told you locally always outranks imported knowledge.

READ ACTIONS (always available):

  • "list": Installed + mounted packs (id, name, origin, trust, rows).

  • "inspect": Read a pack file's manifest WITHOUT installing it. path=. Shows origin, signature, embedder, rows — always inspect before you install.

  • "publishers": Public keys this database trusts.

  • "embedder_identity": This database's embedding fingerprint. A pack must be sealed against a matching space to mount.

WRITE ACTIONS (operator-gated; set YANTRIKDB_ENABLE_PACK_WRITES=1):

  • "install": Install + mount a pack. path=.

  • "uninstall": Remove a pack and its rows. pack_id=.

  • "mount"/"unmount"/"unmount_all": Session-scoped mount control.

  • "trust": Trust a publisher key. pubkey=, label=.

  • "untrust": Revoke a publisher key. pubkey=.

Args: action: One of the read/write actions above. path: Pack file path (inspect / install / mount). pack_id: Pack identifier, e.g. "origin@1.0.0" (uninstall / unmount). pubkey: Publisher public key hex (trust / untrust). label: Human label for a trusted publisher (trust). allow_unverified_embedder: Mount despite an unverified embedder. Does NOT override a hard dimension mismatch.

Inputs: action (required), path, label, pubkey, +2 more. Returns: result

personalityA
Idempotent

AI personality traits derived from memory patterns.

ACTIONS:

  • "get": Get current personality profile. Use recompute=True to refresh.

  • "set": Set a trait manually (needs trait_name + score).

Traits: warmth, depth, energy, attentiveness (0.0-1.0).

Args: action: "get" or "set". trait_name: For set: warmth, depth, energy, attentiveness. score: For set: 0.0-1.0. recompute: For get: re-derive from memory patterns first.

Inputs: score, action, recompute, trait_name. Returns: result

procedureA

Procedural memory — learn, surface, and reinforce strategies.

ACTIONS:

  • "learn": Store a procedure (needs text). What worked in a specific context.

  • "surface": Find relevant procedures (needs query). Returns ranked by effectiveness.

  • "reinforce": Update effectiveness (needs rid + outcome 0.0-1.0).

EXAMPLES:

  • procedure(action="learn", text="For this repo, always run tests before committing", domain="work")

  • procedure(action="surface", query="how to handle code review in this repo")

  • procedure(action="reinforce", rid="abc", outcome=0.9)

Args: action: "learn", "surface", "reinforce". text: Procedure description (for learn). query: What you're about to do (for surface). rid: Procedure ID (for reinforce). domain: Task domain. task_context: What kind of task (for learn). effectiveness: Initial effectiveness 0.0-1.0 (for learn). outcome: How well it worked 0.0-1.0 (for reinforce). top_k: Max results (for surface). namespace: Namespace.

Inputs: action (required), rid, text, query, +6 more. Returns: result

recallA
Read-onlyIdempotent

Search memories by semantic similarity, or refine low-confidence results.

MODES:

  • Search (default): recall("project architecture decisions")

  • Refine: recall("PostgreSQL vs MySQL decision", refine_from="database choice", refine_exclude=["rid1"])

ORDER: "recency" | "first_mention" (alias "chronological") | "certainty". Re-sorts the top_k already found; hints omitted. (Relevance feedback moved to memory(action="feedback") in v0.10 — recall is now purely read-only.)

WHEN TO USE: conversation start (summarize the user's first message); when the user references past decisions, people, preferences, or "last time"; when unsure about something the user assumes you know. Refine when first confidence < 0.5. After USING a recalled memory, reinforce it via memory(action="feedback", rid=..., feedback="relevant"). For "what is the CURRENT/latest X", prefer memory(action="chain_head") — similarity favors the most-similar revision, not the newest. For "what happened , in what order" ("tonight", "this week") use temporal(action="range") or since/until here — those words name the time frame, not the content; bare similarity cannot see the window.

QUERY: one short natural-language sentence (5-10 words), NOT a keyword list — keyword stuffing degrades quality. One focused question per call; separate calls for separate topics.

TRUST SIGNALS: each hit's why_retrieved may carry staleness warnings ("aged", "rarely confirmed", "superseded by a newer record"). Treat flagged hits as weak evidence — prefer fresher results or chain_head, and note the flag if you act on one anyway.

Args: query: Short natural language sentence (5-10 words). NOT a keyword list. top_k: Max results (default 10). 3-5 for focused, 10-20 for broad. memory_type: Filter: "semantic", "episodic", "procedural". domain: Filter: "work", "preference", "architecture", "people", etc. source: Filter: "user", "inference", "document", "system". namespace: Filter by namespace. include_consolidated: Include merged memories. include_superseded: v0.10 — recall EXCLUDES superseded records by default (current-by-default). Set True only for history / archaeology over a revision chain. expand_entities: Use knowledge graph boosting (default True). min_score_ratio: Drop hits scoring below this fraction of the TOP hit (0.8 = keep only near-as-good matches). Semantic search always returns top_k, even when one result is relevant and the rest are noise; this trims the tail instead of making you judge it. since: Only memories from this instant on — "2026-08-01", "2026-08-01T14:30:00Z", "6h"/"7d" (ago), or unix seconds. Filters BEFORE ranking: top_k is chosen inside the window. until: Window end (same formats; default now). Alone = up to then. refine_from: Original query text to refine from. query becomes the refinement. refine_exclude: Memory IDs to exclude when refining.

Inputs: query (required), order, since, top_k, +11 more. Returns: result

rememberA

Store one or more memories in persistent cognitive memory.

WHEN TO USE: Call proactively whenever the conversation reveals something worth remembering — decisions, preferences, facts about people, project context. Do NOT store ephemeral task details, code snippets, or git-derivable info.

SINGLE: remember(text="User prefers dark mode", domain="preference", importance=0.7) BATCH: remember(memories=[{"text": "Alice is DevOps lead", "domain": "people"}, ...]) DRAFT: remember(summary="...long end-of-session summary...") — v0.8.0+ engine atomizes the summary into linked semantic facts; useful for the end-of-session auto-capture pattern.

IMPORTANCE: 0.8-1.0 critical decisions | 0.5-0.7 useful context | 0.3-0.5 background

Args: text: Memory text (for single memory). Be specific and searchable. memory_type: "semantic" (facts), "episodic" (events), "procedural" (how-to). importance: 0.0-1.0. Higher = remembered longer. domain: "work", "preference", "architecture", "people", "infrastructure", "health", "finance", "general". source: "user", "inference", "document", "system". valence: Emotional tone (-1.0 to 1.0). 0.0 neutral. metadata: Optional key-value pairs. namespace: For per-project isolation. certainty: Confidence 0.0-1.0. emotional_state: joy, frustration, excitement, concern, neutral. memories: List of memory dicts for batch. summary: For draft mode — long summary that the engine atomizes. idempotency_key: v0.10 engine — makes the write exactly-once: retrying with the same key + same text returns the SAME rid with no second write; same key + different text is an error. Engine-embedder (bundled) backend only. On batch, the key scopes per item as "{key}:{index}" if the atomic batch path is unavailable. created_at: v0.14 engine — BACKDATE the memory to when it was actually true, not when you imported it. Use for backfill (chat logs, migrations). Without it every imported memory stamps "now", which makes temporal(action="as_of") report history that never happened and flattens staleness/decay. Same formats as as_of: "2026-08-01", "2026-08-01T14:30:00Z", "7d" (ago), or unix seconds. Omit for anything learned in the present conversation. claims: v0.19 engine — facts this memory states, as [{"subject", "relation", "object"}]; state one for any fact you want tracked (contradiction, succession, multi-hop). Subject and object must occur in the text, relation is snake_case; ungrounded ones are reported back, not stored. Batch items take their own "claims". A claim may carry "valid_from"/"valid_to" (created_at formats). event_time: when the memory is ABOUT, not when written (created_at formats). Time-travel recall reads it and every claim on the memory inherits it as valid_from, so an older fact is the predecessor of a newer one, not its contradiction.

Inputs: text, claims, domain, source, +12 more. Returns: result

sessionA

Session lifecycle — start, end, history, active check, stale cleanup, and the v0.9.0 boot-time digest.

ACTIONS:

  • "start": Begin a new session. Returns session_id.

  • "end": End a TRACKED session (needs session_id). Returns stats. This closes session bookkeeping — it does NOT capture memories.

  • "capture": Segment a free-text session summary into atomic candidate memories (needs summary; NO session_id — it operates on the text, not on tracked-session state). Returns drafted rids. Use at end of substantial work so the session leaves a trace.

  • "history": View past sessions.

  • "active": Check if there's a running session.

  • "abandon_stale": Clean up orphaned sessions older than abandon_stale_hours.

  • "digest": One-call boot-time briefing (v0.9.0) — narrative chain head, open decisions/conflicts/triggers, top stale memories. Call this at conversation start instead of N separate recalls. Set include_gaps=True to fold known-unknowns (frequently-asked, poorly-answered queries) into the briefing — the active-learning loop. Set scope to filter content aggregates to one namespace for a per-tenant digest.

Args: action: "start", "end", "capture", "history", "active", "abandon_stale", "digest". session_id: For end. namespace: Memory namespace. client_id: Client identifier. metadata: For start — optional dict. summary: For end — optional closing note. For capture — REQUIRED, the session summary to segment into memories. domain: For capture — domain stamped on drafted memories. limit: For history. abandon_stale_hours: For abandon_stale — max age in hours. narrative_namespace: For digest — namespace for the narrative chain. scope: For digest — filter content aggregates to one namespace (per-tenant isolation); omit for a whole-DB digest. include_gaps: For digest — fold top knowledge gaps into the briefing. max_gaps: For digest — cap on gaps surfaced when include_gaps=True. max_decisions / max_conflicts / max_triggers: For digest — surface caps. snippet_chars: For digest — text-snippet length per item.

Inputs: action (required), limit, scope, domain, +13 more. Returns: result

skillA

Substrate-native agent skill catalog — define, surface, record outcomes.

Skills are structured catalog entries (skill_id, applies_to, body, type) — different from loose how-to memories (use procedure for those). Writes go to the skill_substrate namespace so every yantrikdb consumer (this MCP, yantrikdb-hermes-plugin, Lane B SDK, WisePick) sees the same catalog.

Schema-validated at write time:

  • skill_id: lowercase dot-separated segments, e.g. "workflow.git.commit_clean"

  • body: 50–5000 chars

  • applies_to: 1–10 lowercase_underscore identifiers (no hyphens)

  • skill_type: one of procedure | reference | lesson | pattern | rule

ACTIONS:

  • "define": Create a skill (needs skill_id, body, skill_type, applies_to).

  • "surface": Find relevant skills (needs query). Returns ranked by score.

  • "outcome": Append a use outcome (needs skill_id, succeeded).

  • "get": Fetch a single skill by id.

  • "list": Catalog browse (filter by applies_to / skill_type).

EXAMPLE: skill(action="define", skill_id="workflow.git.commit_clean", body="Before commit: run pytest + lint...", skill_type="procedure", applies_to=["git", "release"]) — then surface(query=...) before similar work, and outcome(skill_id=..., succeeded=True/False) after using one.

Args: action: "define", "surface", "outcome", "get", "list". skill_id: Dot-separated id (for define/get/outcome). body: Skill body, 50–5000 chars (for define). skill_type: procedure|reference|lesson|pattern|rule (for define). applies_to: Non-empty identifier list ≤10 entries (for define; optional filter for surface/list). triggers: Optional list of trigger phrases (for define). on_conflict: "reject" (default) or "replace" if skill_id exists. version: Optional semver-shaped version string. supersedes: Optional skill_id this one replaces. query: Natural-language search (for surface). top_k: Max results for surface. succeeded: Outcome boolean (for outcome). note: Optional outcome note. limit: Max results for list.

Inputs: action (required), body, note, limit, +10 more. Returns: result

statsA
Read-onlyIdempotent

Engine statistics, health check, learned weights, privacy/leak audit, and skill substrate counts. Read-only — index maintenance moved to think(maintenance_op=...) in v0.10.

ACTIONS:

  • "stats": Detailed memory statistics (default).

  • "health": Quick health check with latency.

  • "weights": Show adapted recall scoring weights.

  • "audit_leak": v0.8.0 windowed leak-candidate audit — surfaces recent records that may have leaked sensitive content. Use for privacy review.

  • "skill_outcomes": v0.9.0 — total skill outcomes recorded in the durable timeline.

Args: action: One of the actions above. namespace: Filter for stats. max_rids: For audit_leak — max candidate rids to inspect.

Inputs: action, max_rids, namespace. Returns: result

taskA
Destructive

Substrate-backed task / chore store (v0.9.0 engine).

A thin general-purpose to-do tracker baked into yantrikdb — survives sessions, lives next to memories so future agents see open tasks at session_digest time.

ACTIONS:

  • "add": Create a task (needs title; optional priority + parent_id).

  • "get": Fetch one task by id.

  • "list": List tasks in a namespace, optionally filtered by status.

  • "update": Update status and/or priority (needs task_id).

  • "delete": Delete a task (needs task_id).

PRIORITY: "low" | "medium" | "high" — priority-ordered in list. STATUS: typically "open" | "doing" | "done" | "blocked".

Args: action: "add" | "get" | "list" | "update" | "delete". namespace: Per-project / per-agent isolation. title: Task description (for add). priority: "low" | "medium" | "high" (for add / update). parent_id: Optional parent task id (for add — sub-task tree). task_id: Task id (for get / update / delete). status: Filter (for list) or new value (for update).

Inputs: action (required), title, status, task_id, +3 more. Returns: result

temporalA
Read-onlyIdempotent

Find stale or upcoming memories, recall the past, or scan a time window.

ACTIONS:

  • "stale": Important memories not accessed recently.

  • "upcoming": Memories with approaching deadlines/events.

  • "as_of": Time-travel recall — excludes anything recorded after as_of, so you see the belief held then, not today's. Engine v0.12+.

  • "range": Everything in a time window, oldest first — the surface for "what happened tonight / this week, in what order". Period and sequence questions are SET queries over a window; similarity search cannot answer them — route them here.

Args: action: "stale", "upcoming", "as_of", or "range". days: Inactivity threshold (stale) or look-ahead window (upcoming). limit: Max results. namespace: Optional filter. query: Search text (required for "as_of"; optional for "range": given = relevance-selected within the window, omitted = the window's newest limit records). as_of: Past instant (required for "as_of"): "2026-08-01", "2026-08-01T14:30:00Z", "7d"/"24h" (ago), or unix seconds. since: Window start (required for "range"), same formats as as_of. until: Window end for "range" — defaults to now.

Inputs: action (required), days, as_of, limit, +4 more. Returns: result

thinkA

Run incremental cognitive maintenance — processes a small batch per call.

DESIGNED TO BE CALLED OFTEN: Each call processes ~5 memories (configurable). Running regularly (e.g. at end of conversation) gradually maintains the entire database without blocking. Safe to call frequently.

MODES:

  • Default: incremental think() — consolidation + conflict scan + (optional) pattern mining on a small batch.

  • maintenance_cycle=True: run the v0.9.0 autonomous-hygiene "sleep cycle" — think + burn-down-conflicts + prune-triggers + recalibrate-importance + backfill-entities + auto-relate (+ optional split_oversized + repair_artifacts).

  • last_cycle_only=True: just fetch the last persisted maintenance-cycle summary (read-only, no work performed).

  • maintenance_op="backfill_entities"|"rebuild_vec_index"|"rebuild_graph_index": run ONE targeted index-maintenance op and return. (Moved here from stats in v0.10 so stats could become read-only.)

Args: run_consolidation: Merge similar memories (default on). run_conflict_scan: Detect contradictions (default on). run_pattern_mining: Mine cross-domain patterns (default off, slow). consolidation_time_window_days: Only consolidate memories within this window (default 7 days). consolidation_limit: Batch size — max memories to process per call (default 5). Keep small for fast returns. maintenance_cycle: Run the full autonomous hygiene cycle instead. last_cycle_only: Just fetch the last cycle summary (read-only). dry_run: For maintenance_cycle — preview without persisting changes. burn_down_conflicts / prune_triggers_too / max_pending_triggers / recalibrate_importance / backfill_entities / auto_relate_in_cycle / max_auto_relate_edges / split_oversized / split_min_chars / repair_artifacts: Maintenance-cycle knobs.

Inputs: dry_run, maintenance_op, last_cycle_only, split_min_chars, +15 more. Returns: result

triggerA
Idempotent

Manage proactive triggers + v0.8.0 bounded-backlog pruning.

ACTIONS:

  • "pending": Get pending triggers (default).

  • "history": View past triggers.

  • "acknowledge": Mark trigger as seen.

  • "deliver": Mark as shown to user.

  • "act": Mark as acted upon.

  • "dismiss": Dismiss as irrelevant.

  • "prune": v0.8.0 — expire overdue triggers + evict oldest when over max_pending. Set dry_run=False to actually persist.

Args: action: One of the actions above. trigger_id: Required for acknowledge/deliver/act/dismiss. trigger_type: Filter by type (for pending/history). limit: Max results. dry_run: For prune — preview without persisting. max_pending: For prune — soft cap on the pending backlog (default 64).

Inputs: limit, action, dry_run, trigger_id, +2 more. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4/5.0

    Scored across 21 tools

    Disambiguation4/5

    Most tools target a distinct subsystem—write/retrieve/correct/forget memories, graph, temporal, conflicts, triggers, sessions, tasks—and action enums keep sub-operations separate. The main ambiguity is procedure vs skill, which both store and surface reusable knowledge, and memory/recall/temporal overlap in retrieval but with clear usage notes.

    Naming Consistency4/5

    All tools are single lowercase tokens, which is a consistent style, but there's no verb_noun convention and names mix nouns (memory, graph) with verbs (remember, forget, recall, think). The action-based subcommands add internal consistency, so the overall pattern is predictable.

    Tool Count3/5

    21 tools is on the heavy side for one server, and several tools (category, personality, pack) serve niche features. Still, the server's scope is broad—memory, graph, temporal, conflict, session, task, skill—so the count is defensible but borderline.

    Completeness5/5

    The surface covers the full memory lifecycle (create/read/update/delete/correct), multiple retrieval modes, graph relationships, conflict resolution, maintenance, sessions, tasks, and even pack import/export. There are no obvious dead ends for the stated purpose.

    Maintenance

    ActivityNo data
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Persistent memory and human approval for any AI agent. Give your AI agents the ability to remember across sessions and ask humans for approval before sensitive actions. Works with Claude, Cursor, OpenClaw, and any MCP-compatible client.
      6
      MIT
    • A
      license
      Not graded
      quality
      A
      maintenance
      Zettelkasten-based persistent memory for AI coding agents. Auto-saves atomic knowledge cards with \[\[bidirectional links]] after tasks and auto-recalls before new ones. No vector DB — plain markdown files with git sync. Works as Claude Code plugin or MCP server for Cursor, VS Code Copilot, Codex, and Windsurf.
      332 npm
      144
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Self-hosted MCP-native agent memory server. Gives AI agents persistent, decay-weighted memory via 83 MCP tools — no cloud, full control. RocksDB+HNSW backend. Works with Claude Code, Cursor, and any MCP-compatible agent.
      14
      9
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      A local-first MCP server that gives AI coding agents persistent memory and controlled commands. Features a git-backed markdown knowledge vault with FTS5 search, surgical section edits, token-aware context budgeting, and a sandboxed command engine with human approval gates. Works with Claude Code, Cursor, Copilot, Gemini, and more.
      62
      1
      Apache 2.0