What can you do with this server?

The BCBA server is an AI-driven MCP platform combining real-time web search, enterprise AI services, data transformation, and optional persistent session memory. Search & Discovery * Web search (brave_web_search): Real-time searches via Brave Search API with pagination, filtering, and up to 20 results per request * Local business search (brave_local_search): Find nearby businesses with addresses, ratings, phone numbers, and hours; auto-falls back to web search if no local results * AI-grounded answers (brave_answers): Concise, direct answers grounded in live web results via Brave's AI Grounding * Enterprise search: Domain-specific document retrieval via Vertex AI Discovery Engine, with a hybrid pipeline that combines and deduplicates web + curated results Data Transformation * Code-mode search variants (brave_web_search_code_mode, brave_local_search_code_mode): Run a search and immediately apply a custom JavaScript script (in a secure QuickJS sandbox) to extract only needed fields, reducing context window usage by 85–95% * Universal transformer (code_mode_transform): Apply custom JavaScript extraction to raw output from any MCP tool — useful for GitHub issues, DOM snapshots, transcripts, and more AI Analysis & Orchestration * Research paper analysis (gemini_research_paper_analysis): Deep academic analysis using Gemini 2.0 Flash — summaries, critiques, key findings, literature reviews, or comprehensive analysis * Multi-model orchestration: Supports Google Gemini and Claude via Vertex AI infrastructure with secure Application Default Credentials (ADC) Session Memory (optional, requires Supabase) * Save immutable session logs, update project state for continuity, progressively load prior context, search accumulated knowledge, and prune old memories Integrations: Brave Search, Google Gemini, Vertex AI, Gmail, Chrome DevTools Protocol, and Supabase

Which integrations are available for this server?

Provides real-time web and local search capabilities, including AI-powered answers, to enhance model context. Facilitates data extraction and automated pipeline processing through Gmail OAuth integration. Orchestrates various Google ecosystem services, including Gemini and Gmail, for cross-platform data retrieval. Leverages Vertex AI infrastructure, specifically Discovery Engine for enterprise search and managed generative model deployment. Enables deep research paper analysis and structured data synthesis using the Google Gemini API. Provides a session memory layer for progressive context loading, work ledgers, and persistent state handoffs via Supabase REST APIs.

Prism MCP — The Mind Palace for AI Agents 🧠

npm version MCP Registry Glama Smithery License: MIT TypeScript Node.js

Your AI agent's memory that survives between sessions. Prism MCP is a Model Context Protocol server that gives Claude Desktop, Cursor, Windsurf, and any MCP client persistent memory, time travel, visual context, multi-agent sync, and multi-engine search — all running locally with zero cloud dependencies.
Built with SQLite + F32_BLOB vector search, optimistic concurrency control, MCP Prompts & Resources, auto-compaction, Gemini-powered Morning Briefings, and optional Supabase cloud sync.

What's New in v2.3.3 — AI Reasoning Engine 🧠

Feature	Description
🕸️ Neural Graph	Interactive knowledge graph on the Mind Palace Dashboard — visualize how projects connect through shared keywords and categories using Vis.js force-directed layout.
🛡️ Prompt Injection Shield	Gemini-powered security scan in `session_health_check` — detects system override attempts, jailbreaks, and data exfiltration hidden in agent memory. Tuned to avoid false positives on normal dev commands.
🧬 Fact Merger	Async LLM contradiction resolution on every handoff save — if old context says "Postgres" and new says "MySQL", Gemini silently merges the facts in the background. Zero latency impact (fire-and-forget).

Feature	Description
🩺 Brain Health Check	`session_health_check` — like Unix `fsck` for your agent's memory. Detects missing embeddings, duplicate entries, orphaned handoffs, and stale rollups. Use `auto_fix: true` to repair automatically.
📊 Mind Palace Health	Brain health indicator on the Mind Palace Dashboard — see your memory integrity at a glance.

Feature	Description
🏠 Local-First SQLite	Run Prism entirely locally with zero cloud dependencies. Full vector search (libSQL F32_BLOB) and FTS5 included.
🔮 Mind Palace UI	A beautiful glassmorphism dashboard at `localhost:3000` to inspect your agent's memory, visual vault, and Git drift.
🕰️ Time Travel	`memory_history` and `memory_checkout` act like `git revert` for your agent's brain — full version history with OCC.
🖼️ Visual Memory	Agents can save screenshots to a local media vault. Auto-capture mode snapshots your local dev server on every handoff save.
📡 Agent Telepathy	Multi-client sync: if your agent in Cursor saves state, Claude Desktop gets a live notification instantly.
🌅 Morning Briefing	Gemini auto-synthesizes a 3-bullet action plan if it's been >4 hours since your last session.
📝 Code Mode Templates	8 pre-built QuickJS extraction templates for GitHub, Jira, OpenAPI, Slack, CSV, and DOM parsing — zero reasoning tokens.
🔍 Reality Drift Detection	Prism captures Git state on save and warns if files changed outside the agent's view.

How Prism Compares

Feature	Prism MCP	MCP Memory	Mem0	Mnemory	Basic Memory
Storage	SQLite (local) + Supabase (cloud)	JSON file	Postgres + Qdrant (hosted or self-hosted)	Qdrant + S3/MinIO	Markdown files
Zero Config	✅ `npx -y prism-mcp-server`	✅	❌ Requires Qdrant/Postgres	✅ `uvx mnemory`	✅ `pip install basic-memory`
Semantic Search	✅ F32_BLOB vectors + FTS5	❌	✅ pgvector	✅ Qdrant vectors	❌ Text search only
Knowledge Graph	✅ Neural Graph (Vis.js dashboard)	✅ Entity/Relation model	❌	✅ Relationship graph	✅ Markdown links
Time Travel	✅ `memory_history` / `memory_checkout`	❌	❌	❌	❌
Fact Merging	✅ Async Gemini (fire-and-forget)	❌	✅ Built-in	✅ Contradiction resolution	❌
Security Scan	✅ Prompt injection detection	❌	❌	✅ Anti-injection in fsck	❌
Health Check	✅ `session_health_check` (fsck)	❌	❌	✅ 3-phase fsck	❌
Visual Dashboard	✅ Mind Palace (localhost:3000)	❌	✅ Cloud dashboard	✅ Management UI	❌
Multi-Agent Sync	✅ Real-time cross-client	❌	❌	❌ Per-user isolation	❌
Visual Memory	✅ Screenshot vault + auto-capture	❌	❌	✅ Artifact store	❌
Auto-Compaction	✅ Gemini rollups	❌	❌	❌	❌
Morning Briefing	✅ Gemini synthesis	❌	❌	❌	❌
OCC (Concurrency)	✅ Version-based	❌	❌	❌	❌
MCP Native	✅ stdio (Claude Desktop, Cursor)	✅ stdio	❌ Python SDK / REST	✅ HTTP + MCP	✅ stdio
Language	TypeScript	TypeScript	Python	Python	Python

When to choose Prism MCP: You want MCP-native memory with zero infrastructure overhead, progressive context loading, and enterprise features (OCC, compaction, time travel, security scanning) that work directly in Claude Desktop — without running Qdrant, Postgres, or cloud services.

Quick Start (Zero Config — Local Mode)

Get the MCP server running with Claude Desktop or Cursor in under 60 seconds. No API keys required for basic local memory!

Option A: npx (Fastest)

Add this to your claude_desktop_config.json or .cursor/mcp.json:

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

That's it — zero env vars needed for local memory, Mind Palace dashboard, Time Travel, and Telepathy.

Optional API keys: Add BRAVE_API_KEY for web search, GOOGLE_API_KEY for semantic search + Morning Briefings + paper analysis. See Environment Variables for the full list.

Option B: Cloud Sync Mode (Supabase)

To share memory across multiple machines or teams, switch to Supabase:

{
  "mcpServers": {
    "prism-mcp": {
      "command": "npx",
      "args": ["-y", "prism-mcp-server"],
      "env": {
        "PRISM_STORAGE": "supabase",
        "SUPABASE_URL": "https://your-project.supabase.co",
        "SUPABASE_KEY": "your-supabase-anon-key"
      }
    }
  }
}

Option C: Clone & Build (Full Control)

git clone https://github.com/dcostenco/prism-mcp.git
cd prism-mcp
npm install
npm run build

Then add to your MCP config:

{
  "mcpServers": {
    "prism-mcp": {
      "command": "node",
      "args": ["/absolute/path/to/prism-mcp/dist/server.js"],
      "env": {
        "BRAVE_API_KEY": "your-brave-api-key",
        "GOOGLE_API_KEY": "your-google-gemini-key"
      }
    }
  }
}

Restart your MCP client. That's it — all tools are now available.

🔮 The Mind Palace Dashboard

Prism MCP spins up a lightweight, zero-dependency HTTP server alongside the MCP stdio process. No frameworks, no build step — just pure glassmorphism CSS served as a template literal.

Open http://localhost:3000 in your browser to see exactly what your AI agent is thinking:

Current State & TODOs — See the exact context injected into the LLM's prompt
Git Drift Detection — Alerts you if you've modified code outside the agent's view
Morning Briefing — AI-synthesized action plan from your last sessions
Time Travel Timeline — Browse historical handoff states and revert any version
Visual Memory Vault — Browse UI screenshots and auto-captured HTML states
Session Ledger — Full audit trail of every decision your agent has made

The dashboard auto-discovers all your projects and updates in real time.

Integration Examples

Copy-paste configs for popular MCP clients. All configs use the npx method.

Add to your claude_desktop_config.json:

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

Add to .cursor/mcp.json in your project root (or ~/.cursor/mcp.json for global):

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

Add to ~/.codeium/windsurf/mcp_config.json:

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

Add to your Continue config.json or Cline MCP settings:

{
  "mcpServers": {
    "prism-mcp": {
      "command": "npx",
      "args": ["-y", "prism-mcp-server"],
      "env": {
        "PRISM_STORAGE": "local",
        "BRAVE_API_KEY": "your-brave-api-key"
      }
    }
  }
}

Use Cases

Scenario	How Prism MCP Helps
Long-running feature work	Save session state at end of day, restore full context the next morning — no re-explaining
Multi-agent collaboration	Telepathy sync lets multiple agents share context in real time
Consulting / multi-project	Switch between client projects with progressive context loading
Research & analysis	Multi-engine search with 94% context reduction via sandboxed code transforms
Team onboarding	New team member's agent loads full project history via `session_load_context("deep")`
Visual debugging	Save screenshots of broken UI to visual memory — the agent remembers what it looked like
Offline / air-gapped	Full SQLite local mode with no internet dependency for memory features

Architecture

graph TB
    Client["AI Client<br/>(Claude Desktop / Cursor / Windsurf)"]
    MCP["Prism MCP Server<br/>(TypeScript)"]
    
    Client -- "MCP Protocol (stdio)" --> MCP
    
    MCP --> Dashboard["Mind Palace Dashboard<br/>localhost:3000"]
    MCP --> Brave["Brave Search API<br/>Web + Local + AI Answers"]
    MCP --> Gemini["Google Gemini API<br/>Analysis + Briefings"]
    MCP --> Sandbox["QuickJS Sandbox<br/>Code-Mode Templates"]
    MCP --> SyncBus["SyncBus<br/>Agent Telepathy"]
    
    MCP --> Storage{"Storage Backend"}
    Storage --> SQLite["SQLite (Local)<br/>libSQL + F32_BLOB vectors"]
    Storage --> Supabase["Supabase (Cloud)<br/>PostgreSQL + pgvector"]
    
    SQLite --> Ledger["session_ledger"]
    SQLite --> Handoffs["session_handoffs"]
    SQLite --> History["history_snapshots<br/>(Time Travel)"]
    SQLite --> Media["media vault<br/>(Visual Memory)"]
    
    style Client fill:#4A90D9,color:#fff
    style MCP fill:#2D3748,color:#fff
    style Dashboard fill:#9F7AEA,color:#fff
    style Brave fill:#FB542B,color:#fff
    style Gemini fill:#4285F4,color:#fff
    style Sandbox fill:#805AD5,color:#fff
    style SyncBus fill:#ED64A6,color:#fff
    style Storage fill:#2D3748,color:#fff
    style SQLite fill:#38B2AC,color:#fff
    style Supabase fill:#3ECF8E,color:#fff

Tool Reference

Search & Analysis Tools

Tool	Purpose
`brave_web_search`	Real-time internet search
`brave_local_search`	Location-based POI discovery
`brave_web_search_code_mode`	JS extraction over web search results
`brave_local_search_code_mode`	JS extraction over local search results
`code_mode_transform`	Universal post-processing with 8 built-in templates
`gemini_research_paper_analysis`	Academic paper analysis via Gemini
`brave_answers`	AI-grounded answers from Brave

Session Memory & Knowledge Tools

Tool	Purpose
`session_save_ledger`	Append immutable session log (summary, TODOs, decisions)
`session_save_handoff`	Upsert latest project state with OCC version tracking
`session_load_context`	Progressive context loading (quick / standard / deep)
`knowledge_search`	Semantic search across accumulated knowledge
`knowledge_forget`	Prune outdated or incorrect memories (4 modes + dry_run)
`session_search_memory`	Vector similarity search across all sessions
`session_compact_ledger`	Auto-compact old ledger entries via Gemini-powered summarization

v2.0 Advanced Memory Tools

Tool	Purpose
`memory_history`	Browse all historical versions of a project's handoff state
`memory_checkout`	Revert to any previous version (non-destructive, like `git revert`)
`session_save_image`	Save a screenshot/image to the visual memory vault
`session_view_image`	Retrieve and display a saved image from the vault

v2.2 Brain Health Tools

Tool	Purpose	Key Args	Returns
`session_health_check`	Scan brain for integrity issues (`fsck`)	`auto_fix` (boolean)	Health report & auto-repairs

Code Mode Templates (v2.1)

Instead of writing custom JavaScript, pass a template name for instant extraction:

Template	Source Data	What It Extracts
`github_issues`	GitHub REST API	`#number [state] title (@author) {labels}`
`github_prs`	GitHub REST API	`#number [state] title (base ← head)`
`jira_tickets`	Jira REST API	`[KEY] summary - Status - Priority - Assignee`
`dom_links`	Raw HTML	All `<a>` links as markdown
`dom_headings`	Raw HTML	H1-H6 hierarchy with indentation
`api_endpoints`	OpenAPI/Swagger JSON	`[METHOD] /path - summary`
`slack_messages`	Slack Web API	`[timestamp] @user: message`
`csv_summary`	CSV text	Column names, row count, sample rows

Usage: { "data": "<raw JSON>", "template": "github_issues" } — no custom code needed.

Environment Variables

Variable	Required	Description
`BRAVE_API_KEY`	No	Brave Search Pro API key (enables web/local search tools)
`PRISM_STORAGE`	No	`"local"` (default) or `"supabase"`
`GOOGLE_API_KEY`	No	Google AI / Gemini — enables paper analysis, Morning Briefings, compaction
`BRAVE_ANSWERS_API_KEY`	No	Separate Brave Answers key for AI-grounded answers
`SUPABASE_URL`	If cloud mode	Supabase project URL
`SUPABASE_KEY`	If cloud mode	Supabase anon/service key
`PRISM_USER_ID`	No	Multi-tenant user isolation (default: `"default"`)
`PRISM_AUTO_CAPTURE`	No	Set `"true"` to auto-capture HTML snapshots of dev servers
`PRISM_CAPTURE_PORTS`	No	Comma-separated ports to scan (default: `3000,3001,5173,8080`)

Progressive Context Loading

Load only what you need — saves tokens and speeds up boot:

Level	What You Get	Size	When to Use
quick	Open TODOs + keywords	~50 tokens	Fast check-in: "what was I working on?"
standard	Above + summary + recent decisions + knowledge cache + Git drift	~200 tokens	Recommended default
deep	Above + full logs (last 5 sessions) + cross-project knowledge	~1000+ tokens	After a long break or when you need complete history

Morning Briefing (Automatic)

If it's been more than 4 hours since your last session, Prism automatically:

Fetches the 10 most recent uncompacted ledger entries
Sends a notification: "🌅 Brewing your Morning Briefing..."
Uses Gemini to synthesize a 3-bullet action plan
Injects the briefing into the session_load_context response

The agent boots up knowing exactly what to do — zero prompting needed.

Time Travel (Version History)

Every successful handoff save creates a snapshot. You can browse and revert any version:

v1 → v2 → v3 → v4 (current)
              ↑
        memory_checkout(v2) → creates v5 with v2's content

This is a non-destructive revert — like git revert, not git reset. No history is ever lost.

Usage

// Browse all versions
{ "name": "memory_history", "arguments": { "project": "my-app" } }

// Revert to version 2
{ "name": "memory_checkout", "arguments": { "project": "my-app", "version": 2 } }

Agent Telepathy (Multi-Client Sync)

When Agent A (Cursor) saves a handoff, Agent B (Claude Desktop) gets notified instantly:

Local Mode: File-based IPC via SQLite polling
Cloud Mode: Supabase Realtime (Postgres CDC)

No configuration needed — it just works.

Reality Drift Detection

Prism captures Git state (branch + commit SHA) on every handoff save. When the agent loads context, it compares the saved state against the current working directory:

⚠️ REALITY DRIFT DETECTED for "my-app":
  Branch changed: feature/auth → main
  Commit changed: abc1234 → def5678
  
  The codebase has been modified since your last session.
  Re-examine before making assumptions.

This prevents the agent from writing code based on stale context.

Visual Memory & Auto-Capture

Manual: Save Screenshots

{ "name": "session_save_image", "arguments": {
  "project": "my-app",
  "image_path": "/path/to/screenshot.png",
  "description": "Login page after CSS fix"
}}

Automatic: HTML Snapshots

Set PRISM_AUTO_CAPTURE=true and Prism silently captures your local dev server's HTML on every handoff save. Supported formats: PNG, JPG, WebP, GIF, SVG, HTML.

Knowledge Accumulation

Every session_save_ledger and session_save_handoff automatically extracts keywords using lightweight, in-process NLP (~0.020ms/call). No LLM calls, no external dependencies.

Example: Saving "Fixed Stripe webhook race condition using database-backed idempotency keys" auto-extracts:

Keywords: stripe, webhook, race, condition, database, idempotency
Categories: cat:debugging, cat:api-integration

Search Knowledge

{ "name": "knowledge_search", "arguments": {
  "project": "ecommerce-api",
  "category": "debugging",
  "query": "Stripe webhook"
}}

Forget Bad Memories

Mode	Example	Effect
By project	`project: "old-app"`	Clear all knowledge
By category	`category: "debugging"`	Forget debugging entries only
By age	`older_than_days: 30`	Forget entries older than 30 days
Dry run	`dry_run: true`	Preview what would be deleted

Supabase Setup (Cloud Mode)

1. Create a Supabase Project

Go to supabase.com and sign in (free tier works)
Click New Project → choose a name and password → select a region
Wait for provisioning (~30 seconds)

2. Apply Migrations

In the SQL Editor, run:

3. Get Credentials

Go to Settings → API and copy:

Project URL (e.g. https://abcdefg.supabase.co)
anon public key (starts with eyJ...)

4. Configure

export SUPABASE_URL="https://your-project.supabase.co"
export SUPABASE_KEY="eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9..."
export PRISM_STORAGE="supabase"

Security

Use the anon key for MCP server config
Enable RLS on both tables
Never commit your SUPABASE_KEY to version control

Hybrid Search Pipeline (Brave + Vertex AI)

Prism can combine real-time web search (Brave) with enterprise-curated search (Vertex AI Discovery Engine) for a hybrid pipeline achieving 94% context reduction and ~17K tokens saved per query.

Metric	Brave (Web)	Discovery Engine	Hybrid
Avg latency	220ms	1,193ms	~1.4s
Raw payload	42.4 KB	28.9 KB	71.3 KB
Reduced payload	3.0 KB	1.2 KB	4.2 KB (94% reduction)
Token savings	~10,103	~7,097	~17,200 / query

See vertex-ai/ for setup and benchmarks.

Project Structure

├── src/
│   ├── server.ts                        # MCP server core + Mind Palace HTTP server
│   ├── config.ts                        # Environment management
│   ├── storage/
│   │   ├── interface.ts                 # StorageBackend abstraction
│   │   ├── sqlite.ts                    # SQLite local storage (libSQL + F32_BLOB)
│   │   ├── supabase.ts                  # Supabase cloud storage
│   │   └── index.ts                     # Backend factory (auto-selects based on PRISM_STORAGE)
│   ├── sync/
│   │   ├── interface.ts                 # SyncBus abstraction (Telepathy)
│   │   ├── localSync.ts                 # File-based IPC for local mode
│   │   ├── supabaseSync.ts             # Supabase Realtime CDC for cloud mode
│   │   └── factory.ts                   # Auto-selects sync backend
│   ├── dashboard/
│   │   └── ui.ts                        # Mind Palace glassmorphism HTML template
│   ├── templates/
│   │   └── codeMode.ts                  # 8 pre-built QuickJS extraction templates
│   ├── tools/
│   │   ├── definitions.ts               # All tool schemas (JSON Schema + type guards)
│   │   ├── handlers.ts                  # Search & analysis handlers
│   │   ├── sessionMemoryDefinitions.ts  # Memory + knowledge tool schemas
│   │   ├── sessionMemoryHandlers.ts     # Memory handlers (OCC, Time Travel, Drift, Briefing)
│   │   └── index.ts                     # Tool registration & re-exports
│   └── utils/
│       ├── braveApi.ts                  # Brave Search REST client
│       ├── googleAi.ts                  # Gemini SDK wrapper
│       ├── executor.ts                  # QuickJS sandbox executor
│       ├── autoCapture.ts               # Dev server HTML snapshot utility
│       ├── healthCheck.ts               # Brain integrity engine (v2.2.0) + security scanner (v2.3.0)
│       ├── factMerger.ts                # Async LLM contradiction resolution (v2.3.0)
│       ├── git.ts                       # Git state capture + drift detection
│       ├── embeddingApi.ts              # Embedding generation (Gemini)
│       └── keywordExtractor.ts          # Zero-dependency NLP keyword extraction
├── supabase/migrations/                 # Cloud mode SQL schemas
├── vertex-ai/                           # Vertex AI hybrid search pipeline
├── index.ts                             # Server entry point
└── package.json

License

MIT

Keywords: MCP server, Model Context Protocol, Claude Desktop memory, persistent session memory, AI agent memory, local-first, SQLite MCP, Mind Palace, time travel, visual memory, agent telepathy, multi-agent sync, reality drift detection, morning briefing, code mode templates, cursor MCP server, windsurf MCP server, cline MCP server, pgvector semantic search, progressive context loading, MCP Prompts, MCP Resources, knowledge management AI, Brave Search MCP, Gemini analysis, optimistic concurrency control, zero config

Install Server

security – no known vulnerabilities

license - permissive license

quality - confirmed to work

How are these scores calculated?

Resources

GitHub Repository

Need Help?

Report Issue

Related Servers

Tools

View all tools