Developer · Local MCP server

Agent Recall

Correction-first agent memory. Precision KPI tracks if agents heed warnings. 5 layers, local-only.

What the MCP Registry states

The entry as published to the official MCP Registry (read 2026-10-04), latest version.

Registry name
io.github.Goldentrii/agent-recall
Version
3.4.31
Status
Active
Category
developer
Transport
stdio (local process)
Package
npm
Published
2026-06-20
Updated
2026-06-20
Publisher
Goldentrii (GitHub) · 2 servers with pages here
Namespace
Namespace verified by the MCP Registry via GitHub (github.com/Goldentrii) · how
Repository
github.com/Goldentrii/AgentRecall-MCP (folder packages/mcp-server)
Source
Registry API entry

Packages

RegistryPackageVersionTransportEnvironment variables
npmagent-recall-mcp3.4.31stdioNone declared

How to connect Agent Recall

Agent Recall runs locally from a Node.js package published to the npm registry: agent-recall-mcp version 3.4.31. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Node.js; clients usually start it with npx - the usual command is npx -y agent-recall-mcp@3.4.31.

In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):

{
  "mcpServers": {
    "agent-recall": {
      "command": "npx",
      "args": [
        "-y",
        "agent-recall-mcp@3.4.31"
      ]
    }
  }
}

Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect

More from Goldentrii (GitHub)

All 2 →
ServerRunsEndpoint or package
Proxy VeilResidential proxy MCP server for AI agents - geo-targeting, sticky sessions, anti-bot bypass.Local · stdionpm: proxy-veil

More developer servers

All 5,152 →
ServerRunsEndpoint or package
Agent PlanetsA galaxy where every AI agent owns a planet: claim free, terraform, build, visit, trade.Remote · HTTPLive check: ✓ handshakeplanets.agentexchange.work
Agent Readiness AuditorAudits any website for AI agent readiness and safety, scoring prompt injection risk and llms.txt.Local · stdionpm: agent-readiness-auditor
Agent Ready KitAgent-readiness scanner (0-5 score), robots.txt + llms.txt generators, managed agent enablement.Remote · HTTPLive check: ✓ handshakemudko.com
Agent Ready Website CheckCheck whether a website is readable by AI agents: robots, llms.txt, sitemap, HTML. Bounded.Remote · HTTPLive check: ✓ handshakeagent-observatory-sensor.nolimit-observatory.workers.dev
Agent Recall TrailPrivate Agent memory and governed shared knowledge.Local · stdioMCP Bundle (.mcpb): fantasyce/agent-recall-trail/releases/download/v
Agent Release AuditorDeterministic release gate for AI-written code and coding agents.Local · stdionpm: agent-release-auditor
Agent ReliabilityTesting, benchmarking and auditing autonomous AI agents - methods, harnesses, evidence.Remote · HTTPLive check: ✓ handshakeagentreliability.dev
Agent Rescue Desk Production TriageRead-only triage for n8n, MCP, webhook, and AI agent workflow production failures.Remote · HTTPLive check: ✓ handshakeagent-rescue-desk.netlify.app