Is io.github.nfemmanuel/iranti safe to use?

io.github.nfemmanuel/iranti has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments.

How do I install io.github.nfemmanuel/iranti?

io.github.nfemmanuel/iranti can be installed by cloning its GitHub repository and following the setup instructions in the README.

Is io.github.nfemmanuel/iranti actively maintained?

io.github.nfemmanuel/iranti is actively maintained — last commit was 0 days ago. It has 3 GitHub stars.

io.github.nfemmanuel/iranti

Persistent, shared memory for AI agents — facts, checkpoints, semantic search.

ActiveNot tested

Search AI / ML

★ 3GitHub

28DNo CVEsactive

Quick Install

{
  "mcpServers": {
    "io-github-nfemmanuel-iranti": {
      "command": "<see-readme>",
      "args": []
    }
  }
}

Setup guide

No install config available. Check the server's README for setup instructions.

Are you the author?

Add this badge to your README to show your security score and help users find safe servers.

Embed in your READMEAbout badges →

[![MCPpedia Score](https://mcppedia.org/api/badge/io-github-nfemmanuel-iranti)](https://mcppedia.org/s/io-github-nfemmanuel-iranti)

Should you use this server?

Persistent, shared memory for AI agents — facts, checkpoints, semantic search.

✓

Is it safe?

No package registry to scan.

No authentication — any process on your machine can connect.

License not specified.

✓

Is it maintained?

Last commit 0 days ago. 3 stars.

Will it work with my client?

Transport: stdio. Works with Claude Desktop, Cursor, Claude Code, and most MCP clients.

README

Iranti

Shared memory for AI coding tools — Claude Code, Codex CLI, and GitHub Copilot.

Iranti is a self-hosted MCP server that gives your AI tools persistent, identity-based memory. Facts written in one session are retrievable in any other — across tools, projects, and context resets.

Quick Start

# Install globally
npm install -g iranti

# Run the guided setup (configures database, API key, project binding)
iranti setup

# Start the instance
iranti run --instance local

Then wire it into your AI tool:

iranti claude-setup    # Claude Code
iranti codex-setup     # Codex CLI
iranti copilot-setup   # GitHub Copilot

That's it. Your AI tool now has persistent memory across sessions.

Supported Tools

Tool	Command	What it does
Claude Code	`iranti claude-setup`	Adds `.mcp.json`, `CLAUDE.md`, and session hooks
Codex CLI	`iranti codex-setup`	Registers Iranti in the global MCP registry
GitHub Copilot	`iranti copilot-setup`	Writes MCP config to `.mcp.json` + `.vscode/mcp.json`, protocol instructions to `.github/copilot-instructions.md`
Any MCP client	`iranti mcp`	Runs the stdio MCP server directly

What It Does

Iranti stores facts as entityType/entityId → key → value triples in PostgreSQL. Any agent that knows the entity and key can retrieve the fact exactly — no semantic guessing, no hallucinated state.

Agent A writes:  project/my-app → deployment_status → "deployed to staging"
Agent B reads:   project/my-app → deployment_status → "deployed to staging" ✓

Facts persist across sessions, context resets, and tool switches. When you restart Claude Code tomorrow, it can pick up exactly where you left off.

Key capabilities

Exact lookup — retrieve by entityType/entityId + key, deterministic and fast
Hybrid search — lexical + vector similarity when exact keys are unknown
Cross-tool sharing — Claude Code, Codex, and Copilot share the same memory
Conflict resolution — concurrent writes from multiple agents are detected and resolved
Per-fact confidence — every fact carries a confidence score; low-confidence facts age out
Session recovery — checkpoint/resume for interrupted work
User operating rules — define trigger-based rules that surface only when relevant
File-change recall — agents remember which files changed and why

Staff agents

Iranti is built around four internal Staff components that run alongside the host AI tool. Each Staff member has a specific job, and together they turn the memory layer into an active participant in the session — not just a dictionary the agent reads from.

Staff	Role	What it does
Librarian	Writes and conflict resolution	Normalizes facts before storage, runs multi-step conflict resolution with cited evidence, enforces schema and confidence rules
Attendant	Turn-time context	Pre-response memory injection, mid-turn tool-call guidance, post-response autowrite nudges, drift detection, session objective tracking
Archivist	Background maintenance	Decays stale facts, archives expired entries, processes escalations, runs a bounded reasoning pass that proposes compressions and demotions
Resolutionist	Human-in-the-loop	Consumes escalation files for conflicts the Librarian could not auto-resolve

Attendant a

... View full README on GitHub

Test This Server

No automated test available for this server. Check the GitHub README for setup instructions.

Help improve this page

This server is missing a description. Tools and install config are also missing.If you've used it, help the community.

Add information

Score Breakdown

MCPpedia Score

Click each category to see evidence

28D

Last scored 6h ago

How we score →

Security

3/30

No known vulnerabilities.

○

Known CVEs — No package registry to scan

○

Tool safety — No tools to analyze

○

Tool poisoning — No tools to analyze

○

Injection vectors — No tools to analyze

✓

Tool stability — Tool definitions stable

○

Dependency health — No package to analyze

✗

License — No license specified

○

Authentication — No authentication required

○

Repository — active repo

CVEs checked daily via OSV.dev. Score algorithm is open source.

Reviews

Have you used this server?

Share your experience — it helps other developers decide.

How easy was setup?Did it work reliably?How was the documentation?

Frequently Asked Questions

Is io.github.nfemmanuel/iranti safe to use?: io.github.nfemmanuel/iranti has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments.
How do I install io.github.nfemmanuel/iranti?: io.github.nfemmanuel/iranti can be installed by cloning its GitHub repository and following the setup instructions in the README.
What AI clients work with io.github.nfemmanuel/iranti?: io.github.nfemmanuel/iranti is compatible with Claude Desktop, Cursor, Claude Code, and most MCP clients that support stdio transport. It uses stdio transport.
Is io.github.nfemmanuel/iranti actively maintained?: io.github.nfemmanuel/iranti is actively maintained — last commit was 0 days ago. It has 3 GitHub stars.

Similar servers

View all →

Brave Search MCP Server

Official

No CVEs98A

Web and local search using Brave Search API

2 toolsstdio83.8k24.8k/wk1d ago

Sequential Thinking MCP Server

Official

No CVEs98A

Dynamic problem-solving through sequential thought chains

1 toolsstdio83.8k111.0k/wk1d ago

XcodeBuildMCP

Official

No CVEs97A

A Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS and macOS projects.

2 toolsremote5.2k46.6k/wk1d ago

Tavily Mcp

Official

No CVEs96A

Production ready MCP server with real-time search, extract, map & crawl.

4 toolsremote1.8k62.7k/wk2d ago

MCP Security Weekly

Get CVE alerts and security updates for io.github.nfemmanuel/iranti and similar servers.

Discussion

Start a conversation

Ask a question, share a tip, or report an issue.

Has anyone used this with Cursor?How do you handle auth?Any alternatives?

Iranti

Shared memory for AI coding tools — Claude Code, Codex CLI, and GitHub Copilot.

Quick Start

# Install globally
npm install -g iranti

# Run the guided setup (configures database, API key, project binding)
iranti setup

# Start the instance
iranti run --instance local

Then wire it into your AI tool:

iranti claude-setup    # Claude Code
iranti codex-setup     # Codex CLI
iranti copilot-setup   # GitHub Copilot

That's it. Your AI tool now has persistent memory across sessions.

Supported Tools

Tool	Command	What it does
Claude Code	`iranti claude-setup`	Adds `.mcp.json`, `CLAUDE.md`, and session hooks
Codex CLI	`iranti codex-setup`	Registers Iranti in the global MCP registry
GitHub Copilot	`iranti copilot-setup`	Writes MCP config to `.mcp.json` + `.vscode/mcp.json`, protocol instructions to `.github/copilot-instructions.md`
Any MCP client	`iranti mcp`	Runs the stdio MCP server directly

What It Does

Agent A writes:  project/my-app → deployment_status → "deployed to staging"
Agent B reads:   project/my-app → deployment_status → "deployed to staging" ✓

Facts persist across sessions, context resets, and tool switches. When you restart Claude Code tomorrow, it can pick up exactly where you left off.

Key capabilities

Exact lookup — retrieve by entityType/entityId + key, deterministic and fast
Hybrid search — lexical + vector similarity when exact keys are unknown
Cross-tool sharing — Claude Code, Codex, and Copilot share the same memory
Conflict resolution — concurrent writes from multiple agents are detected and resolved
Per-fact confidence — every fact carries a confidence score; low-confidence facts age out
Session recovery — checkpoint/resume for interrupted work
User operating rules — define trigger-based rules that surface only when relevant
File-change recall — agents remember which files changed and why

Staff agents

Staff	Role	What it does
Librarian	Writes and conflict resolution	Normalizes facts before storage, runs multi-step conflict resolution with cited evidence, enforces schema and confidence rules
Attendant	Turn-time context	Pre-response memory injection, mid-turn tool-call guidance, post-response autowrite nudges, drift detection, session objective tracking
Archivist	Background maintenance	Decays stale facts, archives expired entries, processes escalations, runs a bounded reasoning pass that proposes compressions and demotions
Resolutionist	Human-in-the-loop	Consumes escalation files for conflicts the Librarian could not auto-resolve

Attendant a

... View full README on GitHub