agentmods.dev

prism-mcp

prism-mcp is an MCP server for Claude Code from dcostenco/prism-coder. Its token cost is not measured, scanned A, original, Apache-2.0.

A local memory service for AI coding agents that keeps past decisions, open TODOs, and changed files between sessions.

In plain words
What is it for?
It helps resume coding tasks, track unfinished work, and retrieve earlier project context. The memory and its on-device reasoning model run on your machine.
Why use it?
It removes the need to repeat project context or reconstruct earlier decisions after a session ends. Related past work can also be recalled from the stored information.

MCP server for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: listed in a Claude config.

Part of the prism-coder plugin — 1 skill, 1 MCP server shipped together

not rated 156repo +1 changed today A scan Socket: warn tokens not measured original Apache-2.0

Good fit It helps resume coding tasks, track unfinished work, and retrieve earlier project context. The memory and its on-device reasoning model run on your machine.

Compare 6 mcp servers from other repositories ↓
Install with agentmods
npx agentmods add mcp/dcostenco/prism-coder/prism-prism-mcp
View source ↗ dcostenco/prism-coder synalux.ai
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/dcostenco/prism-coder

Made for: Claude Code.

Or install prism-coder, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for prism-mcp

README.md
[![agentmods](https://agentmods.dev/badge/mcp/dcostenco/prism-coder/prism-prism-mcp/github.svg)](https://agentmods.dev/mcp/dcostenco/prism-coder/prism-prism-mcp)
Your own site
<a href="https://agentmods.dev/mcp/dcostenco/prism-coder/prism-prism-mcp"><img src="https://agentmods.dev/badge/mcp/dcostenco/prism-coder/prism-prism-mcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for prism-mcp

Your own site · 80×15
<a href="https://agentmods.dev/mcp/dcostenco/prism-coder/prism-prism-mcp"><img src="https://agentmods.dev/badge/mcp/dcostenco/prism-coder/prism-prism-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits How audits are shown
Origin original No closer match found in the catalogue.
Security

Grade A, and why

prism-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/prism/.mcp.json · 12 lines

What it actually says

{
  "prism-mcp": {
    "command": "npx",
    "args": [
      "-y",
      "[email protected]"
    ],
    "env": {
      "npm_config_ignore_scripts": "true"
    }
  }
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. today Changed 9355d666ba67
  2. 2d ago Changed d0bd98eb4b74
  3. 4d ago Changed 0e48e80059dd
  4. 5d ago Changed 9140c543c9a0
  5. 7d ago Changed 21fa96b32b8a
  6. 10d ago Changed 2da587bd0d98
  7. 11d ago Changed dc4f24681112
  8. 12d ago Changed 31a16391f400
  9. 13d ago Changed b48ed1e81070
  10. 14d ago First seen · 12 lines scan A c93e8e52f03e

Subscribe to this mod's changes

prism-mcp is an MCP server published in the GitHub repository dcostenco/prism-coder (156 stars, last pushed today), licensed Apache-2.0. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Data and AIMemory and contextTypeScriptagent-memoryai-agentmcpmcp-servermodel-context-protocol
Related

Other mcp servers, from other repositories

inspeximus

MCP server "inspeximus", hosted remotely at pypi.org, as configured in DanceNitra/inspeximus. Needs 1 environment variable to run.

DanceNitra/inspeximus · not measured

xmemo

Shared, governed long-term memory for AI agents across tools and sessions via MCP and REST. Runs locally from the @xmemo/client npm package. Needs 2 environment variables to run.

yonro/memory-os-cli · not measured

session-collab

Provider-agnostic Model Context Protocol (MCP) collaboration server: claim files, persist working memory, and prevent multi-agent session conflicts. Runs locally from the session-collab-mcp npm package.

leaf76/session-collab-mcp · not measured

saihm

MCP standards client for your own custodial SAIHM operator (endpoint URL + operator token). Free hosted start: @saihm/mcp-server-pro. Runs locally from the @saihm/mcp-server npm package. Needs 2 environment variables to run.

SAIHM-Admin/saihm-mcp · not measured

saihm-mcp

Sovereign encrypted memory for AI agents. 8 MCP tools. GDPR erasure. Runnable offline demos. Runs locally from the @saihm/mcp-server npm package. Needs 2 environment variables to run.

SAIHM-Admin/saihm-mcp · not measured

ideahub_mcp

Agent-first MCP server for capturing and recalling ideas — the agent's and their human's. Runs locally from the ideahub_mcp Python package.

CobraChickenAI/ideahub_mcp · not measured