Skip to main content
Glama

🧠 Prism Coder

🌐 Read in your language: πŸ‡¬πŸ‡§ English Β· πŸ‡ͺπŸ‡Έ EspaΓ±ol Β· πŸ‡«πŸ‡· FranΓ§ais Β· πŸ‡΅πŸ‡Ή PortuguΓͺs Β· πŸ‡·πŸ‡΄ RomΓ’nΔƒ Β· πŸ‡ΊπŸ‡¦ Π£ΠΊΡ€Π°Ρ—Π½ΡΡŒΠΊΠ° Β· πŸ‡·πŸ‡Ί Русский Β· πŸ‡©πŸ‡ͺ Deutsch Β· πŸ‡―πŸ‡΅ ζ—₯本θͺž Β· πŸ‡°πŸ‡· ν•œκ΅­μ–΄ Β· πŸ‡¨πŸ‡³ δΈ­ζ–‡ Β· πŸ‡ΈπŸ‡¦ Ψ§Ω„ΨΉΨ±Ψ¨ΩŠΨ©

Persistent memory + tool-calling intelligence for AI agents. (formerly Prism MCP)

A Model Context Protocol server that gives Claude, Cursor, and other AI tools a Mind Palace β€” long-term memory that survives across sessions, with semantic search, cognitive routing, a visual dashboard, and the open-weights prism-coder:7b / prism-coder:14b LLM fleet for offline tool-calling (BFCL Gold Certified, 100 % JSON validity).

npm MCP Registry Smithery License: BUSL-1.1

Renamed in v14.0.0: the project is now Prism Coder to cover both the Mind Palace memory server and the prism-coder:7b / prism-coder:14b LLM fleet on HuggingFace + Ollama. The npm package stays prism-mcp-server so existing install URLs and mcp.json entries keep working β€” the prism-coder binary has been the canonical entry point since v12.


What Prism Coder does

πŸ’Ύ Your AI remembers across sessions

Every conversation feeds the Mind Palace. Next session, your AI agent loads the right context automatically β€” no re-explaining.

πŸ” Semantic search over your history

Ask "what did I decide about the auth flow last month?" and get the answer with citations. Vector search + keyword + graph traversal.

🧬 Cognitive routing

Different memory types live in different stores: episodic (what happened), semantic (what's true), procedural (how to do X). The router picks where to store and where to retrieve.

πŸ”„ Proactive session drift detection (new in v15)

Your AI agent can now detect when it has drifted from your original goals β€” mid-session, automatically β€” and self-correct before you notice the problem.

Three direct Prism calls:

  1. session_save_ledger β€” snapshot current state

  2. session_cognitive_route β€” compare current work against original goals, returns on_track / minor_drift / major_drift

  3. session_compact_ledger β€” if drifted, compress and reload only what matters

When major drift is detected, the alert routes to the Synalux portal so it's visible across sessions and devices β€” not just in the current conversation.

Real example it caught: A training session promised BFCL β‰₯90% for three AI models. The agent spent 3 hours debugging audio bugs instead. The drift check surfaced: "Training goal unmet. Layer3 corpus missing from all training sets. 0 BFCL scores measured." The session immediately re-aligned.

No scripts. No cron. No hooks. Three tool calls, Prism handles the rest.

πŸ›‘ Local-first

Free tier runs entirely on your machine β€” SQLite, local embedding model, no API keys, no cloud. Paid tier adds cloud sync via Synalux portal.

⚑ Zero-search retrieval

Holographic Reduced Representations (HRR) for instant similarity lookups without an index. ~5ms over 100K memories.

🌐 Multi-agent Hivemind

Multiple AI agents share the same Mind Palace. Each agent has a role (dev / qa / pm / etc.) and sees scoped context. Heartbeat + roster for coordination.


Related MCP server: Knowledge Graph MCP Server

Get started

# Install globally
npm install -g prism-mcp-server

# Or use npx (no install)
npx prism-mcp-server

Add to Claude Desktop / Cursor config:

{
  "mcpServers": {
    "prism": {
      "command": "npx",
      "args": ["-y", "prism-mcp-server"]
    }
  }
}

That's it. Open Claude / Cursor and your AI now has memory.

More setup details in docs/SETUP_GEMINI.md.


How AI agents use it

Tool

What it does

session_load_context

Recover prior session's state on boot

session_save_ledger

Append immutable session log entry

session_save_handoff

Save live state for the next session

knowledge_search

Semantic + keyword search over all memories

query_memory_natural

Natural-language Q&A over your Mind Palace

extract_entities

Pull people / projects / decisions from text

session_synthesize_edges

Auto-link related memories into a graph

(35+ tools total β€” full TypeScript signatures in src/tools/. Architecture overview in docs/ARCHITECTURE.md.)

The LLM context window is treated as ephemeral scratch space. All durable state lives in Prism's persistent store (SQLite / Supabase). Context compaction is a non-event.

Boot protocol β€” every session (including post-compaction) begins with a mandatory session_load_context call, enforced via CLAUDE.md. The agent is fully oriented before writing a single byte of response.

Two persistent stores:

  • session_save_ledger β€” immutable append-only work log (decisions, files changed, summaries)

  • session_save_handoff β€” versioned live-state snapshot (current task, TODOs, open context)

Ledger compaction (session_compact_ledger) β€” when a project exceeds a threshold (default: 50 entries), Prism summarizes old entries via LLM into a rollup row, soft-archives originals, and links them via spawned_from graph edges. Runs on a 12-hour background scheduler.

β†’ Full details: docs/COMPACTION.md


Plans

Free (local)

Paid (Synalux portal)

Local SQLite memory

βœ…

βœ…

Semantic search

βœ… (local embedding)

βœ… (cloud-backed)

Cross-device sync

β€”

βœ…

Hivemind multi-agent

βœ… local team

βœ… + cloud roster

Auto-Scholar (web research β†’ memory)

β€”

βœ…

HRR Zero-Search retrieval

βœ…

βœ…

Custom domains / SSO

β€”

Enterprise

The thin-client architecture: when authenticated to Synalux, Prism Coder routes through the portal for paid features. When not authenticated (or PRISM_FORCE_LOCAL=1), runs purely local. Same binary.

Pricing β†’


What you can build with it

  • Persistent coding assistant that remembers your codebase, your decisions, your team's conventions

  • Research agent that builds knowledge over time β€” Auto-Scholar pipeline ingests papers / docs and synthesizes

  • Clinical scribe that retains patient context across visits (HIPAA-compliant cloud + local)

  • Customer support agent that learns from every ticket

  • Writing assistant that knows your voice, your prior drafts, and what you've already published


Companions

Synalux β€” VS Code Extension

Memory-augmented AI inside VS Code, backed by Prism. 20 multimodal tools, multi-agent orchestration, 12-language support. Works offline (Ollama) or cloud (OpenRouter). HIPAA-compliant healthcare workflows.

VS Marketplace

# Install from terminal
code --install-extension synalux-ai.synalux

Or open VS Code β†’ Extensions (β‡§βŒ˜X) β†’ search "Synalux" β†’ Install.

PrismAAC

AAC communication app for non-speaking users. Powered by Prism's spreading-activation phrase ranking + on-device 7B model. macOS / iOS / Android via web. β†’ github.com/dcostenco/prism-aac


πŸ†• Prism as Foundation (v14.0.0)

As of v14.0.0, Prism's algorithm exports are a stable public contract under SemVer. External systems can port actrActivation.ts (ACT-R cognitive decay), spreadingActivation.ts (the 0.7 similarity + 0.3 activation hybrid score), routerExperience.ts (experience bias with MIN_SAMPLES=5 cold-start gate), compactionHandler.ts (the 25KB prompt-budget cap), and graphMetrics.ts (warning ratios) with citations and pin a Prism version.

Reference consumers

Consumer

What it uses from Prism

Audit hooks framework

ACT-R decay (d=0.25 lesson rate), spreading activation hybrid score (0.7/0.3), experience bias (MIN_SAMPLES=5, MAX_BIAS_CAP=0.15), graph-metrics warning ratios (0.20 / 0.30 / 0.40), compaction's 25KB prompt-budget. 327 tests pin every constant β€” CI catches divergence automatically.

PrismAAC

Spreading-activation phrase ranking (recency Γ— frequency Γ— per-user history). Caregiver corrections auto-harvest into the personalization corpus via the audit-hooks postflight harvester. The on-device 7B model + this algorithm stack is what makes PrismAAC defensible.

Synalux portal

Tier-aware model routing using experience bias on prior outcomes per fingerprint. HIPAA-compliant clinical scribe with on-device-first privacy guarantees.

See docs/WOW_FEATURES.md for the algorithm catalogue. Release notes in docs/releases/v14.0.0-prism-as-foundation.md.


Detailed docs in this repo:

The original 1933-line README is preserved in git history. To browse the prior version (full feature catalog, Cognitive Architecture v7.8, Autonomous Cognitive OS v9.0, HRR Zero-Search, Adversarial Evaluation walkthroughs, Universal Import patterns, competitive analysis vs LangMem/MemGPT/Letta/Zep, v12.5 Unified Billing details, v11.6 Hivemind, v11.5.1 Auto-Scholar): git show HEAD~1:README.md.


License

BUSL-1.1 β€” Business Source License. Free for non-production use. Production use requires a Synalux subscription or commercial license. After 2 years, converts to MIT.

Available Tools

43 tools
api_analyticsA

View API usage analytics per project or system-wide. Shows call counts, success rates, latency, token usage, top tools, and daily trends.

Scopes:

  • project β€” Analytics for a specific project

  • system β€” System-wide aggregate analytics

Inputs: scope (required), days, project.

backup_databaseA

Create, list, or restore SQLite database backups.

Actions:

  • create β€” Create a new backup now

  • list β€” List available backups with sizes and ages

  • restore β€” Restore from a specific backup file

  • configure β€” Set backup schedule (hourly/daily/weekly)

Backups are stored in ~/.prism/backups/ by default. Automatic retention pruning keeps only the configured maximum.

Inputs: action (required), schedule, backup_path, max_backups.

brave_answersB

Returns direct AI answers grounded in Brave Search using Brave AI Grounding. Uses an OpenAI-compatible chat completions endpoint and is best for concise answer generation with live web grounding.

Inputs: query (required), model.

brave_local_search_code_modeA

Performs a local search using Brave APIs, and then runs a custom JavaScript code string against the RAW API RESPONSE in a secure QuickJS sandbox. This reduces context window usage by only returning the output of your script. Use this for local/business lookups when you only need specific fields from large local payloads. Your script should read the 'DATA' global variable (a JSON string payload) and use console.log() to print the desired output.

Inputs: code (required), query (required), count, language.

brave_web_search_code_modeA

Performs a web search using the Brave Search API, and then runs a custom JavaScript code string against the RAW API RESPONSE in a secure QuickJS sandbox. This drastically reduces context window usage by only returning the output of your script. Use this for broad information gathering, recent events, or when you need diverse web sources and only need specific parts of the result. Your script should read the 'DATA' global variable (a JSON string of the API response), process it, and use console.log() to print the desired output.

Inputs: code (required), query (required), count, offset, +1 more.

code_mode_transformA

A universal code-mode transformer. Takes RAW TEXT or JSON output from ANY MCP tool (GitHub, Firecrawl, chrome-devtools, camoufox, codegraphcontext, videoMcp, arxiv, etc.) and runs a custom JavaScript code string against it in a secure QuickJS sandbox. Use this as a second step after calling any tool that returns large payloads β€” pass the raw output as 'data' and a JS extraction script as 'code'. Your script reads the 'DATA' global variable (a string of the tool output) and uses console.log() to print only the fields you need. NEW in v2.1: Pass 'template' instead of 'code' for instant extraction. Available templates: github_issues, github_prs, jira_tickets, dom_links, dom_headings, api_endpoints, slack_messages, csv_summary. Example: { data: '', template: 'github_issues' } β€” no custom code needed.

Inputs: data (required), code, language, template, +1 more.

configure_notificationsA

Configure real-time notifications for memory events via webhook, Slack, or email.

Actions:

  • status β€” Show current notification configuration

  • add_channel β€” Add a notification channel (webhook/slack/email)

  • remove_channel β€” Remove a channel by URL

  • test β€” Send a test notification to all configured channels

Events: health_degradation, compaction_complete, backup_complete, backup_failed, memory_threshold, new_graduated_insight, scheduler_error

Inputs: action (required), channel_url, channel_type, min_severity.

deep_storage_purgeA

v5.1 Deep Storage Mode: Purge high-precision float32 embedding vectors for entries that already have TurboQuant compressed blobs, reclaiming ~90% of vector storage. Only affects entries older than the specified threshold (default: 30 days, minimum: 7). Entries without compressed blobs are NEVER touched. Use dry_run=true to preview the impact before executing.

When to use: After running TurboQuant backfill (session_backfill_embeddings), call this tool to reclaim disk space from legacy float32 vectors that are no longer needed for search.

Safety: Tier-2 search (TurboQuant) maintains 95%+ accuracy with compressed blobs. Tier-3 (FTS5 keyword) search is completely unaffected.

Inputs: dry_run, project, older_than_days.

extract_entitiesA

Extract named entities from raw text using rule-based + optional LLM extraction. Automatically identifies technologies, file paths, decisions, TODOs, people, projects, and configuration values without explicit tagging.

Entity types: PERSON, PROJECT, TECH, FILE, DECISION, TODO, CONFIG

Use this to auto-enrich session context with structured metadata from raw conversation text.

Inputs: text (required), project, use_llm.

gemini_research_paper_analysisA

Performs in-depth analysis of research papers using Google's Gemini-2.0-flash model. Ideal for academic research, literature reviews, and deep understanding of scientific papers. Can extract key findings, provide critical evaluation, summarize complex research, and place papers within the broader research landscape. Best for long-form academic content that requires expert analysis.

Inputs: paperContent (required), analysisType, additionalContext.

inference_metricsA

Returns the current session's local-model inference metrics β€” call count, local vs cloud split, token totals, per-model breakdown, and average latency. Read-only, no arguments. Reflects prism_infer delegation usage only, not the host model's (Claude's) own token spend (use /cost for that).

Inputs: no named parameters.

knowledge_downvoteA

Downvote a memory entry to decrease its importance. Importance cannot go below 0.

Inputs: id (required).

knowledge_forgetA

Selectively forget (delete) accumulated knowledge entries. Like a brain pruning bad memories β€” remove outdated, incorrect, or irrelevant session entries to keep the knowledge base clean and relevant.

Forget modes:

  • By project: Clear all knowledge for a specific project

  • By category: Remove entries matching a category (e.g. 'debugging')

  • By age: Forget entries older than N days

  • Full reset: Wipe everything (requires confirm_all=true)

⚠️ This permanently deletes ledger entries. Handoff state is preserved unless explicitly cleared.

Inputs: dry_run, project, category, confirm_all, +2 more.

knowledge_ingestA

Ingest source code or documentation into the knowledge graph. Feed your codebase to Prism so knowledge_search can retrieve it at inference time. Accepts raw source code, file paths, or a git repo URL. The content is chunked, Q&A pairs are generated, and stored in the knowledge graph. Use this when the user says 'learn this code', 'index my repo', or 'ingest this file'.

Inputs: project (required), content, file_path, chunk_size, +1 more.

knowledge_set_retentionA

Set an automatic data retention policy (TTL) for a project's memory. Entries older than ttl_days will be soft-deleted (archived) automatically on every server startup and every 12 hours while running.

Use cases:

  • Set ttl_days: 90 to auto-expire sessions older than 3 months

  • Set ttl_days: 0 to disable auto-expiry (default)

Note: Rollup/compaction entries are never expired β€” only raw sessions.

Inputs: project (required), ttl_days (required).

knowledge_sync_rulesA

Auto-sync graduated insights (importance >= 7) into your project's IDE rules file (.cursorrules or .clauderules). This bridges behavioral memory with static IDE context β€” turning dynamic agent learnings into always-on rules.

How it works:

  1. Fetches graduated insights from the ledger

  2. Formats them as markdown rules inside sentinel markers

  3. Idempotently writes them into the target file at the project's configured repo_path

Requirements: The project must have a repo_path configured in the dashboard.

Idempotency: Uses <!-- PRISM:AUTO-RULES:START --> / <!-- PRISM:AUTO-RULES:END --> sentinel markers. Running this tool multiple times produces the same file. User-maintained content outside the sentinels is never touched.

Inputs: project (required), dry_run, target_file.

knowledge_upvoteA

Upvote a memory entry to increase its importance (graduation). Entries with importance >= 7 become 'graduated' insights that always surface in behavioral warnings.

Inputs: id (required).

maintenance_vacuumA

Reclaim disk space after large purge operations by running VACUUM on the local SQLite database.

Best called after deep_storage_purge removes many entries β€” SQLite reclaims page allocations only when explicitly vacuumed, so the file size stays the same until you call this tool.

For remote (Supabase) backends, returns guidance on triggering maintenance via the dashboard.

Note: On large databases this may take up to 60 seconds. The tool runs synchronously so you will know when it is safe to proceed.

Inputs: dry_run.

memory_checkoutA

Time travel! Restores the project's memory to a specific past version. This overwrites the current handoff state with the historical snapshot, like a Git revert β€” the version number moves forward (no data is lost). Call memory_history first to find the correct target_version.

Inputs: project (required), target_version (required).

memory_historyA

View the timeline of past memory states for this project. Use this BEFORE memory_checkout to find the correct version to revert to. Shows version numbers, timestamps, and summaries of each saved state.

Inputs: project (required), limit.

onboarding_wizardA

Interactive setup wizard for new Prism users. Provides a step-by-step guided experience to get productive in under 3 minutes.

Actions:

  • start β€” Begin the wizard from step 1

  • next β€” Advance to the next step

  • status β€” Check current wizard progress

  • skip β€” Skip to completion

Each step returns instructions, code snippets, and progress percentage.

Inputs: action (required), ide_client, project_name.

prism_inferA

Run an inference on a local prism-coder model (Ollama) to save cloud tokens. Picks the largest viable tier β€” 27B / 9B / 4B / 2B β€” based on free RAM at call time, clamped by model_ceiling and what is actually pulled in Ollama. Falls through to the synalux portal cloud cascade (9B β†’ 27B β†’ Claude Opus 4.7) only when local is unviable AND cloud_fallback=true. Use this for code generation, summarisation, classification, or any synth task you would otherwise hand to the cloud model β€” it costs $0 when the local hit succeeds.

Inputs: prompt (required), mode, think, system, +9 more.

query_memory_naturalA

Query memories using natural language instead of structured tool syntax. Automatically classifies intent, extracts keywords, and executes the appropriate search strategy.

Examples:

  • "What did we decide about authentication?"

  • "What's still open on the billing project?"

  • "What files did we change last week?"

  • "Show me recent work on the API"

Returns the parsed intent, search results, and optionally an LLM-synthesized answer.

Inputs: question (required), project, synthesize.

session_backfill_embeddingsA

Repair ledger entries that are missing vector embeddings. This can happen if the Gemini API was temporarily unavailable when the entry was saved.

How it works:

  1. Scans for active ledger entries where embedding IS NULL

  2. Generates embeddings via Gemini text-embedding-004

  3. Patches each row with the generated embedding

Run this periodically or after known API outages to ensure full semantic search coverage.

Inputs: limit, dry_run, project.

session_cognitive_routeB

Resolve an HDC compositional state into a nearest semantic concept with policy-gated routing. Returns concept, confidence, distance, ambiguity, convergence steps, and route outcome. Use this for explainable cognitive recall decisions in v6.5.

Inputs: role (required), state (required), action (required), project (required), +3 more.

session_compact_ledgerA

Auto-compact old session ledger entries by rolling them up into AI-generated summaries. This prevents the ledger from growing indefinitely and keeps deep context loading fast.

How it works:

  1. Finds projects with more entries than the threshold

  2. Summarizes old entries using Gemini (keeps recent entries intact)

  3. Inserts a rollup entry and archives the originals (soft-delete)

Use dry_run=true to preview what would be compacted without executing.

Inputs: dry_run, project, threshold, keep_recent.

session_detect_driftA

Detect whether the current agent session has semantically drifted from its original goal. Scores recent ledger entries against the goal using synalux's HRR embedding stack (GloVe β†’ Gemini/Voyage β†’ cosine similarity), then runs the rolling-window drift detector algorithm.

Triggers:

  • goal-drift β€” cumulative alignment loss is high and monotonic (not random tangents)

  • context-collapse β€” average output quality has dropped below floor

Pre-warning:

  • quality-degrading β€” quality slope steeply negative before collapse

Returns: drifted, reason, warning, drift_score (0..1), goal_alignment, quality_avg, sample_count, adaptive_threshold, recommendation.

Use alongside GATE 5 (60-minute drift check): call this tool instead of session_cognitive_route for goal-alignment drift detection.

Inputs: goal (required), project (required), domain, window_hours, +6 more.

session_export_memoryA

Export all of a project's memory to a local file. Fulfills GDPR Article 20 (Right to Data Portability) and the 'local-first' portability promise.

What is exported:

  • All session ledger entries (summaries, decisions, TODOs, file changes)

  • Current handoff state (live project context)

  • System settings (API keys are "REDACTED" for security)

  • Visual memory index (descriptions, captions, timestamps; not the raw files)

Formats:

  • json β€” machine-readable, suitable for import into another Prism instance

  • markdown β€” human-readable, ideal for static archiving

  • vault β€” Prism-Port: exports a compressed .zip of interrelated Markdown files with proper Obsidian/Logseq YAML frontmatter and [[Wikilinks]]

⚠️ Output directory must exist and be writable. Filenames are auto-generated: prism-export-<project>-<date>.(json|md|zip)

Inputs: output_dir (required), format, project.

session_forget_memoryA

Forget (delete) a specific memory entry by its ID. Supports two modes:

  • Soft delete (default): Tombstones the entry β€” it stays in the database for audit trails but is excluded from all search results. Reversible.

  • Hard delete: Permanently removes the entry from the database. Irreversible. Use only when GDPR Article 17 requires complete erasure.

⚠️ Soft delete is recommended for most use cases. The entry can be restored in the future if needed.

Inputs: memory_id (required), reason, hard_delete.

session_health_checkA

Run integrity checks on the agent's memory (like fsck for filesystems). Scans for missing embeddings, duplicate entries, orphaned handoffs, and stale rollups.

Checks performed:

  1. Missing embeddings β€” entries that can't be found via semantic search

  2. Duplicate entries β€” near-identical summaries wasting context tokens

  3. Orphaned handoffs β€” handoff state with no backing ledger entries

  4. Stale rollups β€” compaction artifacts with no archived originals

Use auto_fix=true to automatically repair missing embeddings and clean up orphans.

Inputs: auto_fix.

session_load_contextA

Load session context for a project using progressive context loading. Use this at the START of a new session to recover previous work state. Three levels available:

  • quick: Just the latest project state β€” keywords and open TODOs (~50 tokens)

  • standard: Project state plus recent session summaries and decisions (~200 tokens, recommended)

  • deep: Everything β€” full session history with all files changed, TODOs, and decisions (~1000+ tokens)

Inputs: project (required), toolAction (required), toolSummary (required), role, +4 more.

session_save_experienceA

Record a typed experience event. Unlike session_save_ledger (flat logs), this captures structured behavioral data for pattern detection.

Event Types:

  • correction: Agent was corrected by user

  • success: Task completed successfully

  • failure: Task failed

  • learning: New knowledge acquired

  • validation_result: Verification sandbox passed or failed

Inputs: action (required), context (required), outcome (required), project (required), +4 more.

session_save_handoffA

Upsert the latest project handoff state for the next session to consume on boot. This is the 'live context' that gets loaded when a new session starts. Calling this replaces the previous handoff for the same project (upsert on project).

v5.4 CRDT Merge: On version conflict, a CRDT OR-Map engine automatically merges your changes with concurrent work (Add-Wins OR-Set for arrays, Last-Writer-Wins for scalars). Pass expected_version to enable concurrency control.

v0.4.0 OCC: If you received a version number from session_load_context, /resume_session prompt, or memory resource attachment, you MUST pass it as expected_version to prevent overwriting another session's changes.

Inputs: project (required), role, open_todos, key_context, +5 more.

session_save_imageA

Save a local image file into the project's permanent visual memory. Use this to remember UI states, diagrams, architecture graphs, or bug screenshots. The image is copied into Prism's media vault and indexed in the handoff metadata. On the next session_load_context, the agent will see a lightweight index of available images.

Inputs: project (required), file_path (required), description (required).

session_save_ledgerA

Save an immutable session log entry to the session ledger. Use this at the END of each work session to record what was accomplished. The ledger is append-only β€” entries cannot be updated or deleted. This creates a permanent audit trail of all agent work sessions.

Inputs: project (required), summary (required), conversation_id (required), role, +3 more.

session_search_memoryA

Search session history semantically (by meaning, not just keywords). Uses vector embeddings to find sessions with similar context, even when the exact wording differs. Requires pgvector extension in Supabase.

Complements knowledge_search (keyword-based) β€” use this when keyword search returns no results or when the query is phrased differently from stored summaries.

Inputs: query (required), limit, project, activation, +3 more.

session_synthesize_edgesA

Step 3A Edge Synthesis: Scans recent project entries with embeddings, finds high-similarity but currently disconnected entries, and creates inferred links as 'synthesized_from'.

On-Demand Graph Enrichment: Use this tool periodically to discover semantic relationships between structurally disconnected memory nodes. It batch processes the newest active entries.

Inputs: project (required), max_entries, randomize_selection, similarity_threshold, +1 more.

session_view_imageA

Retrieve an image from visual memory using its ID. Returns the image as Base64 inline content for the LLM to analyze. Use session_load_context first to see available image IDs.

Inputs: project (required), image_id (required).

verify_behaviorA

Call BEFORE editing behavioral source files (API routes, ordering logic, billing, auth, migrations). Returns a domain-specific scenario you must answer to demonstrate understanding of the end-user impact. Example: editing a KDS route returns 'A cook has a 3-item ticket. One item is voided. What should the cook see?' Answer the scenario concretely before proceeding with the edit.

Inputs: file_path (required), change_summary (required), project, workspace_id.

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    B3.3/5.0

    Scored across 43 tools

    Disambiguation2/5

    The tool set has several ambiguous clusters: session_log vs session_save_decision vs event_note, and memory_search vs knowledge_search vs session_search. The loading-cache family (cache_store, cache_get, cache_stats, cache_clear) is redundant, and maintenance/utility tools (maintenance_vacuum, api_analytics) sit awkwardly alongside data tools.

    Naming Consistency2/5

    Prefixes are mixed across domains (session_, memory_, knowledge_, cache_, tool_, api_), and some tools use bare verbs (prune_history, follow_up, help) that don't indicate their domain. The verb-noun structure is inconsistent β€” some use get_/update_/delete_, but others use action_only names like summarize.

    Tool Count1/5

    43 tools is extreme overkill for a personal memory/assistant server. Clusters like cache_* (5 tools), memory_* (4), session_* (11), and tool_* (6) could each be collapsed into one or two parameterized tools, and the knowledge/session split creates significant redundancy.

    Completeness3/5

    The surface covers the core domain broadly β€” sessions, memory, knowledge, cache, maintenance β€” but is missing simple primitives like a plain 'save_note' toolholistic entry point. Coverage is scattered and defense-in-depth oriented rather than complete.

    Maintenance

    ActivityActive
    ResponsivenessMixed handling

    Related MCP Connectors

    Related MCP Servers

    • -
      license
      Not graded
      quality
      Not graded
      maintenance
      A sophisticated MCP server providing advanced memory capabilities with RAG, hallucination detection, and enterprise-grade AI infrastructure for intelligent agent ecosystems.
      -
    • A
      license
      B
      quality
      D
      maintenance
      Production-grade, autonomous Model Context Protocol (MCP) server that elevates AI models from stateless code generators into persistent, self-verifying software engineers.
      21
      1
      MIT