{"name":"io.github.Goldentrii/agent-recall","slug":"goldentrii-agent-recall","title":null,"description":"Correction-first agent memory. Precision KPI tracks if agents heed warnings. 5 layers, local-only.","url":"https://mcp.market/server/goldentrii-agent-recall","rating":null,"grade":"A","score":92,"certified":false,"status":"active","category":"ai","tags":["ai"],"presence":{"score":53,"stars":371,"forks":60,"downloads_week":399,"last_push_at":"2026-09-21T14:25:02.000Z","license":"MIT"},"uptime":null,"claimed":false,"transport":"npm","callable_via_gateway":false,"default_price_micros":0,"repository":"https://github.com/Goldentrii/AgentRecall-MCP","website":null,"version":"3.4.31","remotes":[],"packages":[{"registryType":"npm","identifier":"agent-recall-mcp","version":"3.4.31","transport":{"type":"stdio"}}],"tools":[{"name":"alignment_check","description":"Record what the agent understood, its confidence, and any human correction. Measures the Intelligent Distance gap.","write_action":false,"price_micros":0,"input_schema":null},{"name":"awareness_update","description":"Add insights to the awareness system. Call at end of session.","write_action":true,"price_micros":0,"input_schema":null},{"name":"bootstrap_import","description":"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.","write_action":false,"price_micros":0,"input_schema":null},{"name":"bootstrap_scan","description":"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.","write_action":false,"price_micros":0,"input_schema":null},{"name":"check","description":"Use when the user asks to validate understanding, verify alignment, or check if their interpretation matches the human's intent.","write_action":false,"price_micros":0,"input_schema":null},{"name":"check_action","description":"Call BEFORE any non-trivial action (publish, push, deploy, schema change, file delete,","write_action":false,"price_micros":0,"input_schema":null},{"name":"context_synthesize","description":"Generate L3 semantic synthesis from recent journals and palace rooms.","write_action":false,"price_micros":0,"input_schema":null},{"name":"dashboard_export","description":"Generate ~/.agent-recall/dashboard.json — a structured all-projects snapshot suitable for","write_action":false,"price_micros":0,"input_schema":null},{"name":"digest","description":"Context cache — store or recall pre-computed analysis results.","write_action":false,"price_micros":0,"input_schema":null},{"name":"journal_archive","description":"Move entries older than N days to cold archive. Keeps a one-line summary per archived entry.","write_action":false,"price_micros":0,"input_schema":null},{"name":"journal_capture","description":"Layer 1: lightweight Q&A capture. Appends to today's log file without loading the full journal.","write_action":false,"price_micros":0,"input_schema":null},{"name":"journal_cold_start","description":"Returns a palace-first cold-start package.","write_action":false,"price_micros":0,"input_schema":null},{"name":"journal_list","description":"List available journal entries for a project.","write_action":false,"price_micros":0,"input_schema":null},{"name":"journal_projects","description":"List all projects tracked by agent-recall on this machine.","write_action":false,"price_micros":0,"input_schema":null},{"name":"journal_read","description":"Read a journal entry. Returns the full file content for agent cold-start. Use date='latest' for the most recent entry.","write_action":false,"price_micros":0,"input_schema":null},{"name":"journal_rollup","description":"Condense old daily journals into weekly summaries.","write_action":false,"price_micros":0,"input_schema":null},{"name":"journal_search","description":"Full-text search across all journal entries for a project.","write_action":false,"price_micros":0,"input_schema":null},{"name":"journal_state","description":"Layer 1: structured JSON session state. Faster than markdown for cold-start.","write_action":false,"price_micros":0,"input_schema":null},{"name":"journal_write","description":"Append content to the current journal entry (creates today's file if absent).","write_action":true,"price_micros":0,"input_schema":null},{"name":"knowledge_read","description":"Read lessons from knowledge files. Used before starting work to learn from past mistakes.","write_action":false,"price_micros":0,"input_schema":null},{"name":"knowledge_write","description":"Write a structured lesson to the knowledge palace room.","write_action":true,"price_micros":0,"input_schema":null},{"name":"memory_query","description":"Use when the user asks to search across all memory stores with a natural language query.","write_action":false,"price_micros":0,"input_schema":null},{"name":"nudge","description":"Surface a contradiction between the human's current input and a prior statement/decision. Helps the human clarify their own thinking.","write_action":false,"price_micros":0,"input_schema":null},{"name":"palace_lint","description":"Health check: find stale memories, orphan rooms (no connections), low-salience entries,","write_action":false,"price_micros":0,"input_schema":null},{"name":"palace_read","description":"Read a room overview or specific topic from the Memory Palace.","write_action":false,"price_micros":0,"input_schema":null},{"name":"palace_search","description":"Full-text search across all palace rooms. Results are ranked by room salience.","write_action":false,"price_micros":0,"input_schema":null},{"name":"palace_walk","description":"Progressive context loading for cold-start.","write_action":false,"price_micros":0,"input_schema":null},{"name":"palace_write","description":"Write a memory to a palace room. Triggers fan-out: cross-references are updated in connected rooms.","write_action":true,"price_micros":0,"input_schema":null},{"name":"pipeline_close","description":"Close the currently active project phase with the three reflection fields:","write_action":false,"price_micros":0,"input_schema":null},{"name":"pipeline_current","description":"Return the full content of the currently active project phase, or null if none is open.","write_action":false,"price_micros":0,"input_schema":null},{"name":"pipeline_list","description":"List all project phases (milestones) in order — the project's narrative spine.","write_action":false,"price_micros":0,"input_schema":null},{"name":"pipeline_open","description":"Open a new project phase (milestone) in the project's narrative spine.","write_action":false,"price_micros":0,"input_schema":null},{"name":"pipeline_show","description":"Render the project's narrative spine on demand — phase count, day span, sessions,","write_action":false,"price_micros":0,"input_schema":null},{"name":"project_board","description":"Use when the user asks to show/list AgentRecall projects, /arstatus, project status board, or what work is active.","write_action":false,"price_micros":0,"input_schema":null},{"name":"project_status","description":"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.","write_action":false,"price_micros":0,"input_schema":null},{"name":"recall","description":"Use when the user asks to recall, search, find, or look up previous memory, context, or decisions.","write_action":false,"price_micros":0,"input_schema":null},{"name":"recall_insight","description":"Before starting a task, recall cross-project insights that apply.","write_action":false,"price_micros":0,"input_schema":null},{"name":"register_rule","description":"Save a permanent IF-THEN behavior commitment for the project. Unlike insights (semantic facts)","write_action":false,"price_micros":0,"input_schema":null},{"name":"remember","description":"Use when the user asks to remember, store, note, or save a specific decision, fact, or insight.","write_action":false,"price_micros":0,"input_schema":null},{"name":"session_end","description":"Use when the user asks to save, checkpoint, summarize, end, retain, or persist the current session.","write_action":false,"price_micros":0,"input_schema":null},{"name":"session_end_reflect","description":"Bundle recent journals + active corrections + recent phase syntheses into a","write_action":false,"price_micros":0,"input_schema":null},{"name":"session_start","description":"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).","write_action":false,"price_micros":0,"input_schema":null},{"name":"skill_list","description":"List every procedural skill saved for the project. Returns slug/name/topic/triggers —","write_action":false,"price_micros":0,"input_schema":null},{"name":"skill_recall","description":"Find IF-THEN production rules matching your current intent. Call this before starting a","write_action":false,"price_micros":0,"input_schema":null},{"name":"skill_write","description":"Save a reusable IF-THEN production rule (procedural memory). Use when you've solved a problem","write_action":true,"price_micros":0,"input_schema":null},{"name":"smart_recall","description":"Search ALL memory stores at once — palace, journal, and insights.","write_action":false,"price_micros":0,"input_schema":null},{"name":"smart_remember","description":"Save a memory — the system classifies your content and routes it to the right store","write_action":false,"price_micros":0,"input_schema":null}],"scan":{"score":92,"grade":"A","scanned_at":"2026-09-26T21:20:51.205Z","report":{"scannerVersion":"0.1.9","scannedAt":"2026-09-26T21:20:51.161Z","components":{"code":{"score":25,"max":25,"notes":["103 source files scanned"]},"reliability":{"score":-1,"max":20,"notes":["no gateway calls yet and no remote to probe"]},"poisoning":{"score":-1,"max":15,"notes":["tools not inspected (local package is not executed); not counted"]},"auth":{"score":12,"max":15,"notes":["local package, no credentials required"]},"maintenance":{"score":15,"max":15,"notes":["last push 5 days ago"]},"identity":{"score":8,"max":10,"notes":["registry namespace matches repository owner","GitHub account older than a year"]}},"findings":[],"inputs":{"packages":[{"registryType":"npm","identifier":"agent-recall-mcp","version":"3.4.31","found":true,"license":"MIT","hasInstallScripts":false,"dependencyCount":3,"publishedAt":"2026-06-20T10:08:35.285Z","repositoryUrl":"git+https://github.com/Goldentrii/AgentRecall.git","weeklyDownloads":399}],"repo":{"found":true,"owner":"Goldentrii","repo":"AgentRecall-MCP","archived":false,"pushedAt":"2026-09-21T14:25:02Z","stars":371,"forks":60,"openIssues":24,"ownerType":"User","ownerAvatarUrl":"https://avatars.githubusercontent.com/u/232191022?v=4","ownerCreatedAt":"2025-09-14T11:50:51Z","license":"MIT"},"icon":{"url":null,"source":"none"},"presence":{"stars":371,"forks":60,"downloadsWeek":399,"license":"MIT","lastPushAt":"2026-09-21T14:25:02.000Z","score":53}}}},"grade_history":[],"reviews":[]}