Log inSubmit server
Prism MCP logo

Prism MCP

by dcostenco

Local-first MCP memory with SQLite persistence, cross-client sessions, local routing, savings tracking, and a web dashboard.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Prism MCP

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "dcostenco-prism-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "prism-mcp-server"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

dcostenco/prism-mcp MCP server gives Claude, Cursor, and other MCP clients persistent memory backed by local SQLite. It supports session continuity, shared memory across clients, time-travel session review, local model routing, and token savings accounting through 25 tools, 6 resources, and 4 prompts. Use it when agents need durable project context without an account or API keys, or when you want to inspect and manage that context through the Mind Palace dashboard. Optional Ollama and compatible oMLX setups provide offline inference and routing features.

Use cases

  • Resume project work with memory that survives agent restarts
  • Share context between Claude, Cursor, and other connected clients
  • Review or replay earlier agent sessions
  • Route eligible coding work to local models
  • Audit tokens handled by local inference

Key features

  • SQLite-backed persistent session memory
  • Cross-client memory sharing
  • Mind Palace web dashboard
  • Local Ollama and compatible oMLX routing
  • Session rewind and replay
  • Token-based local savings reporting

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

21/21 checks healthy over the last 79d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 10d ago via OSV.dev · prism-mcp-server (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars156Stargazers on the source repository.
npm downloads5.7kPackage downloads in the last 30 days.
Last commitTodayMost recent push to the default branch.
Directory activity8 viewsConfig copies, upvotes, and views on AllMCPs.

How Prism MCP works

What dcostenco/prism-mcp does

dcostenco/prism-mcp adds durable memory and local-first agent services to MCP-compatible clients. Session information survives restarts, allowing agents to retain handoff notes, recent work, open tasks, and other project context. Memory search can apply ACT-R ranking, combining relevance with recency, frequency, and associations; this behavior can be disabled in preferences or with PRISM_ACTR_ENABLED=false.

The server also provides a Mind Palace web dashboard for inspecting and managing the stored information. Its broader feature set includes cross-client memory sharing, session rewind and replay, code-mode templates, morning briefings, progressive context loading, offline tool routing, and a savings meter for locally served requests.

How it works

The server runs locally and stores its persistent memory in SQLite. MCP clients access the functionality through the server's tools, resources, and prompts. The package exposes 25 tools, 6 resources, and 4 prompts.

Local routing can use installed Ollama models, with automatic selection across 2B, 4B, 9B, and 27B options based on available models, memory, context fit, and subscription entitlements. Eligible text coding tasks can also use a configured compatible oMLX server. The local_savings tool and the prism savings command report locally handled token volume, including local share and per-model detail, along with the assumptions behind the count.

Setup and configuration

Install the prism-mcp-server npm package and connect it to supported clients with prism connect. The connection workflow can configure Claude Code, Claude Desktop, Cursor, Gemini CLI, and Codex while preserving unrelated settings. No account or API key is needed for the local server.

Use prism dashboard to open the web interface. Local AI settings are available under Account & Settings → Local AI, where users can select coding, review, and image backends and test saved model choices. Installing or updating the optional Prism-managed oMLX server is a separate dashboard operation and is supported on compatible Apple Silicon Macs.

Tools and capabilities

  • Persist and retrieve session memory across restarts.
  • Share memory between connected AI clients.
  • Search memories with optional ACT-R ranking.
  • Review, rewind, and replay sessions.
  • Route suitable work to local models without cloud inference.
  • Record local usage and inspect token savings.
  • Load context progressively instead of sending all stored material at once.
  • Use code templates, morning briefings, and dashboard-based memory management.

Limitations and notes

Local model behavior depends on the models installed and their available resources. A passing image diagnostic confirms execution, not visual accuracy. Compatible oMLX servers can handle controlled local PNG requests, while the saved Ollama image option currently does not execute. Image processing uses local screening, and model accuracy varies.

The npm package and an external oMLX server are updated independently. Updating the package or restarting an MCP client does not upgrade an external oMLX installation. A paid subscription adds cloud sync, higher model tiers, and team features through the Synalux portal; the local server itself does not require that subscription.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Prism MCP

dcostenco/prism-mcp is an MCP server that connects Claude, Cursor, Claude Code, Gemini CLI, Codex, and other clients to persistent local memory and agent utilities. Its main capabilities include SQLite-backed session memory, memory search, local model routing, cross-client sharing, session replay, and token savings reporting without requiring an account or API key.

Install the `prism-mcp-server` npm package, then use `prism connect` to configure supported clients. The connection workflow supports Claude Code, Claude Desktop, Cursor, Gemini CLI, and Codex while preserving unrelated client settings.

Yes, dcostenco/prism-mcp supports Cursor. Use `prism connect` to configure the client, after which Cursor can use the server's persistent memory and other exposed MCP capabilities.

Yes, the local server runs without an account or API keys. It stores memory locally and can route eligible work to installed Ollama models or a compatible oMLX server; paid services add optional cloud sync, model tiers, and team features.

Related MCP servers

All in Knowledge & Memory All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewPrism MCP AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/dcostenco-prism-mcp?style=directory)](https://allmcps.com/mcp/dcostenco-prism-mcp)
HTML Embed
<a href="https://allmcps.com/mcp/dcostenco-prism-mcp"><img src="https://allmcps.com/api/badge/dcostenco-prism-mcp?style=directory" alt="Prism MCP on AllMCPs" /></a>