io.github.dcostenco/prism-coder
Session memory for coding agents: local-first recall, drift detection, on-device inference.
MCP server · by dcostenco
About
io.github.dcostenco/prism-coder is an MCP server published by dcostenco. Marketplaces we read that list it: 2 (Official MCP Registry, Community GitHub marketplaces). The last change we recorded was on 2026-10-12. As of our marketplace pass on 2026-10-13.
What it asks for
- Runs on your machine
- Secrets: 3
- Settings: 8
Requires: BRAVE_API_KEY (secret), GEMINI_API_KEY (secret), SUPABASE_KEY (secret)
What it declares, asks for and runs, in full
Only install plugins from developers you trust. We list what marketplaces publish and do not test plugins.
Package
npm prism-mcp-server (prism-mcp-server on npm)
- npm downloads/week: 1 370 (2026-10-13)
- npm downloads/month: 7 975 (2026-10-13)
- Latest version on npm: 20.21.25, published 2026-10-12
No known vulnerabilities in OSV for 20.21.25 (checked 2026-10-13)
npm facts come from the public npm registry (registry.npmjs.org, api.npmjs.org). Each figure is the registry's own and is never added to another. A registry that publishes no figure shows none: no number is not zero. Vulnerability records come from OSV.dev (CC BY 4.0) and concern the declared version only; a listing that declares no version gets no answer. We do not scan code.
Works with
- Claude Code
- Codex
- Cursor
- VS Code
- Copilot CLI
From the marketplaces that list it and the MCP transport it declares, as each client documents them. We do not test plugins.
Connect
Commands and configs built only from what its marketplaces declare. We do not run them for you and do not test plugins.
As a local MCP server: npm package
Built from what Official MCP Registry declares.
claude mcp add --env "BRAVE_API_KEY=<YOUR_BRAVE_API_KEY>" --env "GEMINI_API_KEY=<YOUR_GEMINI_API_KEY>" --env "SUPABASE_KEY=<YOUR_SUPABASE_KEY>" --transport stdio prism-coder -- npx -y prism-mcp-server[mcp_servers.prism-coder]
command = "npx"
args = ["-y", "prism-mcp-server"]
[mcp_servers.prism-coder.env]
BRAVE_API_KEY = "<YOUR_BRAVE_API_KEY>"
GEMINI_API_KEY = "<YOUR_GEMINI_API_KEY>"
SUPABASE_KEY = "<YOUR_SUPABASE_KEY>"{
"mcpServers": {
"prism-coder": {
"command": "npx",
"args": [
"-y",
"prism-mcp-server"
],
"env": {
"BRAVE_API_KEY": "<YOUR_BRAVE_API_KEY>",
"GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>",
"SUPABASE_KEY": "<YOUR_SUPABASE_KEY>"
}
}
}
}Replace the values in angle brackets with your own. We show the names of the settings, never values.
Optional settings it also lists: GCP_PROJECT_ID, PRISM_USER_ID, SUPABASE_URL, VERTEX_DATA_STORE_ID, VERTEX_LOCATION.
As a Claude Code plugin
Built from what Community GitHub marketplaces declares.
/plugin marketplace add dcostenco/prism-coder
/plugin install prism-coder@prismWhere it is published
| Marketplace | Status | Version | Figures | Verified | First seen |
|---|---|---|---|---|---|
| Official MCP Registry (Open the registry record) | Listed | 20.21.25 | Downloads/month (npm): 7 975 Downloads/week (npm): 1 370 Forks (GitHub): 26 Stars (GitHub): 158 |
Not marked |
Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.
Also listed in one community marketplace
| Marketplace | Repository | Stars (GitHub) |
|---|---|---|
| prism | dcostenco/prism-coder | 158 |
What the bundle contains
As published on Community GitHub marketplaces.
MCP servers: 1
prism-mcp
Skills: 1
prism-startup
What changed
- Appeared on a new marketplace: Community GitHub marketplaces
- Community GitHub marketplaces: appeared
- Official MCP Registry: released version 20.21.25 (was 20.21.24)
- Official MCP Registry: released version 20.21.24 (was 20.21.23)
Possibly the same plugin
Listings that share a signal with this one but not enough for us to treat them as the same product.
Similar plugins
Products whose own names, descriptions, tools and skills are closest in meaning to this one, on every marketplace we read. Closeness is ranked within this list only.
-
Local code graph and solution memory for coding agents via CLI and MCP.
-
Hosted MCP memory for coding agents: persistent across sessions, editable markdown, team sharing.
-
Local-first memory for coding agents; stores decisions, bugs, and context across sessions.
-
ainative-opencode-memory-mcp io.github.AINative-Studio/ainative-opencode-memory-mcp
Persistent cross-session memory for OpenCode and MCP coding agents, powered by ZeroDB.
-
Persistent project memory for AI coding agents: one compact digest instead of re-reading the repo.
-
Shared memory for coding agents: projects, reusable code, sessions and commits across machines
-
todox io.github.beydemirfurkan/todox
Memory for coding agents: the decisions, the dead ends, and where the last session stopped.
-
Session memory for AI coding agents: records decisions and dead ends, flags what went stale.
-
peon-mem io.github.VineetV2/peon-mem
Local-first memory brain for AI coding agents: hooks capture sessions, beliefs injected per prompt.
-
Local-first, governable long-term memory for AI coding agents
Similar plugins by marketplace
The same question asked of one marketplace at a time: is there an analog of this plugin there?
Has a listing on Claude Code: claude-plugins-community (5)
-
engram io.github.tstockham96/engram
Intelligent agent memory with automatic extraction, consolidation, and bi-temporal recall.
-
memex io.github.STiFLeR7/memex
Temporal engineering context for agents via MCP.
-
Cross-session memory for Claude Code projects via two in-repo docs: SESSION_PRIMER.md (current state) and LEARNINGS.md (hard-won bugs).
-
Local-first persistent session memory for Claude Code and other agents. SQLite + FTS5, no cloud.
-
Eliminate context rot in Claude Code with intelligent memory hierarchy, auto-learning hooks, and specialized subagents. Uses an 8-layer memory architecture with SessionStart/End…
Has a listing on Claude Code: claude-plugins-official (5)
-
Continuous memory for Claude Code. Extracts, summarizes, and compresses conversations into tiered daily logs. Claude remembers what you did yesterday.
-
mcp-server io.github.cap-js/mcp-server
Model Context Protocol (MCP) server for AI-assisted development of CAP applications.
-
MCP server for AI coding agents to create, manage, and interact with Quarkus applications. Provides tools for project scaffolding, dev mode lifecycle, extension skills, Dev MCP…
-
mdk-mcp-server io.github.SAP/mdk-mcp-server
Model Context Protocol (MCP) server for AI-assisted development of MDK applications.
-
Detect an MCP server's language (Python, TypeScript or Go) and instrument it with the matching Pendo SDK so MCP tool calls flow into Pendo Agent Analytics.
Has a listing on Claude: knowledge-work-plugins (5)
-
MCP server for terminal commands, file operations, and process management
-
gk-cli com.gitkraken/gk-cli
The GitKraken MCP Server for managing repos, PRs, issues across GitHub, GitLab, Bitbucket and more.
-
Bring Qodo's codebase intelligence, coding standards, and code review into your coding agent.
-
Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF…
-
Official Buildkite skills for Claude Code, Cursor, and other AI coding agents — pipelines, migration, preflight, agent runtime, CLI, and API
Has a listing on Codex: openai-curated (openai/plugins) (5)
-
Skills for NVIDIAs ecosystem spans GPU acceleration, CUDA, AI agents, inference, robotics, Physical AI, Omniverse, and simulation. This plugin helps you understand the pieces…
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
AI-powered code review in Codex, powered by CodeRabbit.
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
-
An agentic skills framework & software development methodology that works: planning, TDD, debugging, and collaboration workflows.
Has a listing on Community GitHub marketplaces (5)
-
Local-first, governable long-term memory for AI coding agents
-
bettermemory io.github.0Mattias/bettermemory
Memory for coding agents, checked against the filesystem and git before it is believed.
-
Markdown memory for coding agents that audits itself: drift reports and session digests.
-
Persistent memory for Claude Code, Cursor and Codex. Facts retire when they change.
-
PAPI: Persistent Adaptive Project Intelligence
Adaptive plan/build/review cycles for AI coding assistants, persisted across sessions.
Has a listing on Copilot CLI: github/awesome-copilot (5)
-
Complete toolkit for building Model Context Protocol (MCP) servers in TypeScript/Node.js using the official SDK. Includes instructions for best practices, a prompt for generating…
-
Shows live prompt-cache reuse, expiry, token composition, and AIU cost for the current GitHub Copilot session without making model calls.
-
Complete toolkit for building Model Context Protocol (MCP) servers in Go using the official github.com/modelcontextprotocol/go-sdk. Includes instructions for best practices, a…
-
Build applications with the GitHub Copilot SDK across multiple programming languages. Includes comprehensive instructions for C#, Go, Node.js/TypeScript, and Python to help you…
-
Complete toolkit for building Model Context Protocol (MCP) servers in Kotlin using the official io.modelcontextprotocol:kotlin-sdk library. Includes instructions for best…
Has a listing on Copilot CLI: github/copilot-plugins (5)
-
Navigate and interact with your C++ code using the Microsoft C++ Language Server.
-
Advanced Security plugin for GitHub Copilot.
-
Bring Azure DevOps work-item, repository, and pull-request workflows into GitHub Copilot.
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
mcp-apps
Generate MCP App widgets for MCP tools. Produces self-contained HTML widgets using the MCP Apps protocol.
Has a listing on Cursor: cursor/plugins (5)
-
Incremental transcript-driven memory updates for AGENTS.md using high-signal bullet points only.
-
Patterns for designing CLIs that coding agents can run reliably: flags, help with examples, pipelines, errors, idempotency, dry-run.
-
Build apps, scripts, and automations with the TypeScript SDK.
-
if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize with confidence.
-
Fan large tasks out across parallel cloud agents with planners, workers, verifiers, and structured handoffs.
Has a listing on Docker MCP Catalog (5)
-
Giving Claude ability to run code with E2B via MCP (Model Context Protocol).
-
Bridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.
-
A Python-based execution tool that mimics a Jupyter notebook environment. It accepts code snippets, executes them, and maintains state across sessions — preserving variables…
-
Official Arm MCP server for code migration, optimization, and Arm architecture guidance
-
Stop stitching context for Copilot and Cursor. With Sequa MCP, your AI tools know your entire codebase and docs out of the box.
Has a listing on Official MCP Registry (5)
-
Local code graph and solution memory for coding agents via CLI and MCP.
-
Hosted MCP memory for coding agents: persistent across sessions, editable markdown, team sharing.
-
Local-first memory for coding agents; stores decisions, bugs, and context across sessions.
-
ainative-opencode-memory-mcp io.github.AINative-Studio/ainative-opencode-memory-mcp
Persistent cross-session memory for OpenCode and MCP coding agents, powered by ZeroDB.
-
Persistent project memory for AI coding agents: one compact digest instead of re-reading the repo.
Found by meaning, not by shared code or a shared repository: similar plugins stay separate products, and this is not a review or a recommendation.
Is this your plugin?
Add it to your projects and prove you maintain it with a file in its repository, a file on your domain or a DNS record. You get alerts when a marketplace lists it, drops it, changes its verified mark or what it asks for, and its remote endpoint goes on monitoring as a web service.
Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Data comes from public marketplace files in GitHub repositories of their authors. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.