Log inSubmit server
AgentRecall logo

AgentRecall

by Goldentrii

Persistent agent memory that records corrections, retrieves relevant context, and measures whether mistakes recur.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install AgentRecall

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": {
    "goldentrii-agentrecall": {
      "command": "npx",
      "args": [
        "-y",
        "agent-recall-mcp"
      ]
    }
  }
}

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

We couldn’t confirm it starts correctly

The install command started, but didn't respond the way we expected when we tried to talk to it.

npx -y agent-recall-mcp

initialize succeeded but no response to tools/list.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 1mo ago.

Overview

Goldentrii/AgentRecall MCP server gives agents persistent memory across sessions, projects, and restarts. It records corrections as structured entries, retrieves relevant past context, and tracks whether later encounters are heeded or repeated. The MCP interface exposes five tools for starting sessions, saving memories, recalling context, checking records, and ending sessions. Reach for it when an agent needs a local-first correction history and a way to evaluate behavioral change rather than retrieval alone.

Use cases

  • Persist corrections across agent sessions
  • Load project context when a session starts
  • Search memories relevant to a current task
  • Track whether agents heed or repeat corrections

Key features

  • Persistent cross-session memory
  • Structured corrections ledger
  • Contextual memory retrieval
  • Session lifecycle tools
  • Heeded-versus-recurred outcome tracking
  • Local-first operation

Tools5

What AgentRecall lets your agent do. Expand a tool for its parameters.

Self-reported~119 tokens of context

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.

6/6 checks healthy over the last 30d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 8d ago via OSV.dev · agent-recall-mcp (npm)

Adoption & maintenance

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

GitHub stars372Stargazers on the source repository.
npm downloads976Package downloads in the last 30 days.
Last commit11d agoMost recent push to the default branch.
Install checkInconclusiveStarted but did not complete the MCP handshake in our test.
Tools exposed5Callable tools this server registers over MCP.
Directory activity6 viewsConfig copies, upvotes, and views on AllMCPs.

How AgentRecall works

What Goldentrii/AgentRecall MCP server does

Goldentrii/AgentRecall MCP server provides persistent memory for AI-agent sessions, with a specific focus on corrections. When a human tells an agent that an assumption, version, ordering, or behavior is wrong, the correction can be saved as a structured record instead of remaining only in the current conversation.

Saved records persist across sessions, projects, and agent restarts. The system also treats memory as an observable learning loop: corrections include information such as severity, evidence, and outcome tracking. Each correction can accumulate a retrieval count, while later encounters can be marked as either heeded or recurred.

This makes the project suitable for agents that need continuity between sessions and for developers who want to inspect whether captured corrections affect future behavior. It does not promise that every correction will be captured or transferred successfully; the project publishes evaluation results showing that its own measured capture and transfer performance is incomplete.

How it works

The MCP workflow follows a session lifecycle. At the beginning of a session, the agent calls the session-start operation to load relevant context. When the user provides a correction, the agent calls the remember operation, typically recording it with a correction type. At the end, the session-end operation compounds information from the session.

Retrieval is intended to surface contextually relevant memories. The project describes its retrieval as using the Intelligent Distance Protocol and also identifies keyword-plus-RRF retrieval. The available memory model is organized into five layers mapped to the agent’s filesystem, while cloud use is zero by default according to the repository metadata.

The measurement model separates retrieval from behavioral outcome. A retrieved correction can be counted, and a later encounter can record whether the agent heeded the correction or repeated the behavior. The repository includes reproducible evaluation artifacts and a benchmark command for its measurement material, but the supplied MCP setup does not require a hosted measurement service.

Setup and configuration

Install the Goldentrii/AgentRecall MCP server through npm with:

Terminal
npx -y agent-recall-mcp

For Claude Code, the documented command is:

Terminal
claude mcp add --scope user agent-recall -- npx -y agent-recall-mcp

Other documented MCP configurations use the same npx command and package name. Examples are provided for Cursor and Windsurf, using their respective MCP JSON configuration files. The repository also documents a Claude Code skill, an SDK for JavaScript and TypeScript applications, and a separate command-line package; those are additional interfaces rather than required parts of the MCP server.

Tools and capabilities

Goldentrii/AgentRecall MCP server exposes five default tools:

  • sessionstart for loading context at the start of a session.
  • remember for saving a memory or correction.
  • recall for searching relevant memories.
  • check for inspecting memory or correction state.
  • sessionend for closing a session and compounding what was learned.

The README examples use the names session_start and session_end in prompts, so client integrations should follow the tool names exposed by the installed server version.

Limitations and notes

The project’s published measurements are explicitly qualified. Its reported correction-capture recall was 35.3% on the cited live corpus, and its post-reset evidence-grounded heed result was 0/3 events. The offline correction-transfer result was also 0/4. These figures indicate that the system should not be treated as a guarantee that agents will remember every correction or stop repeating every mistake.

Goldentrii/AgentRecall MCP server is local-first and does not require a paid API key in the documented installation. Its usefulness depends on the agent following the session lifecycle and recording corrections when they occur. The repository’s license badge identifies the project as MIT-licensed.

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 AgentRecall

Run `npx -y agent-recall-mcp`, or add it to Claude Code with `claude mcp add --scope user agent-recall -- npx -y agent-recall-mcp`.

The listing identifies five tools: `sessionstart`, `remember`, `recall`, `check`, and `sessionend`.

Yes. The README provides MCP JSON configurations for both Cursor and Windsurf.

The documented local npm installation does not specify an API key or paid service requirement.

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 PreviewAgentRecall AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/goldentrii-agentrecall?style=directory)](https://allmcps.com/mcp/goldentrii-agentrecall)
HTML Embed
<a href="https://allmcps.com/mcp/goldentrii-agentrecall"><img src="https://allmcps.com/api/badge/goldentrii-agentrecall?style=directory" alt="AgentRecall on AllMCPs" /></a>