Mmcp.market

Agent Recall MCP server

by Goldentrii·io.github.Goldentrii/agent-recall·v3.4.31
No reviews yet

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

A92/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
Established

371 stars399 downloads/wk

Reviews

Write one

Nobody has reviewed Agent Recall yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Agent Recall tools (47, 5 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • alignment_check

    Record what the agent understood, its confidence, and any human correction. Measures the Intelligent Distance gap.

  • awareness_updatewrite action

    Add insights to the awareness system. Call at end of session.

  • bootstrap_import

    Import discovered projects into AgentRecall. Call bootstrap_scan first, then pass the scan results here. Creates palace entries, identity files, and initial journals for selected projects.

  • bootstrap_scan

    Discover existing projects on this machine — git repos, Claude memory, CLAUDE.md files. Returns what CAN be imported into AgentRecall. Read-only, no writes. Run this first if AgentRecall is empty.

  • check

    Use when the user asks to validate understanding, verify alignment, or check if their interpretation matches the human's intent.

  • check_action

    Call BEFORE any non-trivial action (publish, push, deploy, schema change, file delete,

  • context_synthesize

    Generate L3 semantic synthesis from recent journals and palace rooms.

  • dashboard_export

    Generate ~/.agent-recall/dashboard.json — a structured all-projects snapshot suitable for

  • digest

    Context cache — store or recall pre-computed analysis results.

  • journal_archive

    Move entries older than N days to cold archive. Keeps a one-line summary per archived entry.

  • journal_capture

    Layer 1: lightweight Q&A capture. Appends to today's log file without loading the full journal.

  • journal_cold_start

    Returns a palace-first cold-start package.

  • journal_list

    List available journal entries for a project.

  • journal_projects

    List all projects tracked by agent-recall on this machine.

  • journal_read

    Read a journal entry. Returns the full file content for agent cold-start. Use date='latest' for the most recent entry.

  • journal_rollup

    Condense old daily journals into weekly summaries.

  • journal_search

    Full-text search across all journal entries for a project.

  • journal_state

    Layer 1: structured JSON session state. Faster than markdown for cold-start.

  • journal_writewrite action

    Append content to the current journal entry (creates today's file if absent).

  • knowledge_read

    Read lessons from knowledge files. Used before starting work to learn from past mistakes.

  • knowledge_writewrite action

    Write a structured lesson to the knowledge palace room.

  • memory_query

    Use when the user asks to search across all memory stores with a natural language query.

  • nudge

    Surface a contradiction between the human's current input and a prior statement/decision. Helps the human clarify their own thinking.

  • palace_lint

    Health check: find stale memories, orphan rooms (no connections), low-salience entries,

  • palace_read

    Read a room overview or specific topic from the Memory Palace.

  • palace_search

    Full-text search across all palace rooms. Results are ranked by room salience.

  • palace_walk

    Progressive context loading for cold-start.

  • palace_writewrite action

    Write a memory to a palace room. Triggers fan-out: cross-references are updated in connected rooms.

  • pipeline_close

    Close the currently active project phase with the three reflection fields:

  • pipeline_current

    Return the full content of the currently active project phase, or null if none is open.

  • pipeline_list

    List all project phases (milestones) in order — the project's narrative spine.

  • pipeline_open

    Open a new project phase (milestone) in the project's narrative spine.

  • pipeline_show

    Render the project's narrative spine on demand — phase count, day span, sessions,

  • project_board

    Use when the user asks to show/list AgentRecall projects, /arstatus, project status board, or what work is active.

  • project_status

    Optional deeper context for a specific project — call after session_start if you need full status details. Not a replacement for project_board. Returns last trajectory, active blockers, next steps, and palace room freshness.

  • recall

    Use when the user asks to recall, search, find, or look up previous memory, context, or decisions.

  • recall_insight

    Before starting a task, recall cross-project insights that apply.

  • register_rule

    Save a permanent IF-THEN behavior commitment for the project. Unlike insights (semantic facts)

  • remember

    Use when the user asks to remember, store, note, or save a specific decision, fact, or insight.

  • session_end

    Use when the user asks to save, checkpoint, summarize, end, retain, or persist the current session.

  • session_end_reflect

    Bundle recent journals + active corrections + recent phase syntheses into a

  • session_start

    Use when the user asks to start, load, continue, resume, or open memory for a project. Set mode='lite' for a ≤500-token briefing (good for fresh conversations where the agent will pull memory on demand via recall/memory_query/skill_recall).

  • skill_list

    List every procedural skill saved for the project. Returns slug/name/topic/triggers —

  • skill_recall

    Find IF-THEN production rules matching your current intent. Call this before starting a

  • skill_writewrite action

    Save a reusable IF-THEN production rule (procedural memory). Use when you've solved a problem

  • smart_recall

    Search ALL memory stores at once — palace, journal, and insights.

  • smart_remember

    Save a memory — the system classifies your content and routes it to the right store

Public scan report

scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it

no findings
  • Code scan103 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 5 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

What the publisher says

From the Agent Recall repository's README, as published. We do not edit it. Read it on GitHub

English · 中文

AgentRecall

Claude Code memory that learns from corrections. The only learning loop that measures whether your agent actually stops repeating a mistake.

Corrections ledger + session lifecycle + honest measurement. MCP · SDK · CLI · Skill.

Agent found this repo? Install AgentRecall for your human (click to expand)

1. Install the MCP server (Claude Code):

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

Generic MCP JSON for other clients:

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

2. First message of every new session, run the loop:

At the start of a session, call session_start to load context.
When the human corrects you, call remember with type "correction".
At the end of a session, call session_end to compound what you learned.

What it does

AgentRecall is two things:

  1. A governed corrections ledger — every time you correct your agent ("no, not that version", "put this section first", "ask me before you assume"), that correction is stored as a structured record with severity, evidence, and outcome tracking. It persists across sessions, projects, and agent restarts.
  1. A measurement instrument — the only open-source system that tracks whether a correction actually changed what the agent does in a later session. Every correction accumulates retrieved_count, and every time the agent encounters the same situation, the outcome is recorded (heeded or recurred).

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Install directly

Runs npx -y agent-recall-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add agent-recall -- npx -y agent-recall-mcp
Add to Cursor

Agent Recall: common questions

Is Agent Recall MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the Agent Recall safety report
How do I install Agent Recall?
It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
Does Agent Recall need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Agent Recall maintained?
The last commit was 6 days ago (2026-09-21). The latest release is v3.4.31.
What can I use instead of Agent Recall?
Servers from other publishers that do the same job: Basic Memory MCP server, Total Agent Memory MCP server and Persome MCP server. Compare all Agent Recall alternatives.

Alternatives to Agent Recall

Same job from other publishers: the closest match first, then the best rated.

All Agent Recall alternatives →
  • Basic Memory
    Local-first knowledge management with bi-directional LLM sync via Markdown files.
    C
  • Total Agent Memory
    Persistent local memory for coding agents: temporal knowledge graph, procedural and episodic recall
    A
  • Persome
    Local-first personal memory and model server for trusted MCP agents on macOS.
    A
  • Fidelis Memory
    Recall locally stored agent memories through an MCP-compatible host.
    B
  • IWE
    Markdown knowledge base as agent memory. Runs against the notes directory it is started in.
    A
Agent Recall vs Basic MemoryAgent Recall vs Total Agent MemoryAgent Recall vs Persome

More from Goldentrii →