Claude Amplifier MCP server
Persistent memory + decision tracking for Claude across sessions. Local SQLite, no cloud.
Usage numbers are collected on the next scan
Reviews
Write oneNobody has reviewed Claude Amplifier yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Claude Amplifier tools (13)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
amplify_audit_freshnessv1.5.0 — List memory/<YYYY-MM-DD>.md files that are newer than the latest Amplifier write for a project. Use this when amplify_context_load surfaces a stale-memory warning, or when you suspect a previous session did real work without recording lessons/decisions. Surfaces unrecorded sessions so they can be triaged retroactively.
amplify_context_loadLoad saved context (decisions, lessons, patterns) for the current project at the start of a session.
amplify_decisionsTrack and query architectural / design decisions for a project.
amplify_evidence_chainv1.4.0 — Show the evidence chain that supports a stored lesson or decision. Useful for auditing why Amplifier 'knows' something — surfaces commits, test runs, and user confirmations that promoted a claim to confirmed.
amplify_global_patternsManage cross-project patterns (best practices, conventions) that apply to all or multiple projects.
amplify_learnRecord a lesson — a mistake, success, or insight — so Claude remembers it in future sessions.
amplify_link_decisionsv1.2.0 — Add a knowledge-graph link between two existing decisions. Lightweight: one call = one link. Idempotent.
amplify_preflightv1.4.0 — Before starting a task, check stored lessons + decisions for matching failure patterns. Returns risk_level (low/medium/high/critical), matched patterns and lessons, and suggested approach. Call this BEFORE diving in when working on something that touches a familiar area.
amplify_promote_from_memory_mdv1.5.0 — Read a memory/<YYYY-MM-DD>.md file and surface DRAFT suggestions for amplify_learn / amplify_decisions follow-up calls. Heuristics: architectural Wrote: lines (plan/decision/architecture/blueprint/manifesto), >50 events per hour, ≥8× repeated tool/terminal calls. Returns drafts only — never writes to SQLite. Use when amplify_audit_freshness flagged a stale day worth triaging.
amplify_promote_patternv1.4.0 — Promote a pattern_key from per-project to global scope. Requires the key to exist in ≥2 projects with ≥1 confirmed lesson. After promotion the pattern weighs more in cross-project Pattern Oracle scoring.
amplify_record_claimv1.4.0 — Record a lesson as an UNVERIFIED claim (default confidence 0.5). Use this for any 'I just learned X' moment that has not been confirmed by tests, commits, or user confirmation. Promote later with amplify_verify_claim. (amplify_learn remains for confirmed/legacy records.)
amplify_suggest_pattern_keyv1.5.0 — Suggest an existing pattern_key (or propose a new one) for a lesson before recording it. Use this before amplify_learn when you suspect the lesson is a recurring pattern. Prevents the failure where two sessions invent two different keys for the same lesson and the frequency counter never aggregates. Returns up to 3 existing keys ranked by trigram similarity, or a new key suggestion if non
amplify_verify_claimv1.4.0 — Attach evidence to a lesson to promote it. Promotion rules: (claim + 1 evidence) → 'evidence' (conf 0.7); (evidence + user_confirmation OR ≥2 distinct evidence types) → 'confirmed' (conf 1.0). Use this when tests pass, a commit lands, or the user explicitly confirms.
Public scan report
scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it
- Code scan32 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
- Maintenancerepository not readable: repo not found3/15
- Maintainer identityno repository or website to verify2/10
Install directly
Runs npx -y claude-amplifier on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add claude-amplifier -- npx -y claude-amplifier
Claude Amplifier: common questions
- Is Claude Amplifier MCP server safe?
- With care: it is graded C, so read the findings first (65/100). Read the Claude Amplifier safety report
- How do I install Claude Amplifier?
- It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
- Does Claude Amplifier need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Claude Amplifier maintained?
- The latest release is v1.5.3.
- What can I use instead of Claude Amplifier?
- Servers from other publishers that do the same job: Myc MCP server, memo MCP server and KEPTA — Agent Memory MCP server. Compare all Claude Amplifier alternatives.
Alternatives to Claude Amplifier
Same job from other publishers: the closest match first, then the best rated.
- MycTask queue, decisions and memory for coding agents. Local SQLite, no network. Requires Bun.not reviewedGrowingC
- memoMemory for AI agents — MLX (Apple Silicon) or CPU (Linux), sqlite-vec + BM25, zero cloud.not reviewedGrowingA
- KEPTA — Agent MemoryLocal memory for AI agents. One SQLite file on your machine — no cloud, no account.not reviewedGrowingA
- LoreConvoLocal-first persistent session memory for Claude Code and other agents. SQLite + FTS5, no cloud.not reviewedGrowingB
- Local MemoryPersistent local AI memory. SQLite + FTS5 + vector search, knowledge graph. No cloud, no API keys.not reviewedGrowingA