# Claude Engram MCP server

Agent View of the PolicyLayer registry record for Claude Engram: identity, probed posture, risk grade, and all 16 tools classified. HTML page: https://policylayer.com/tools/20alexl-claude-engram

## Facts

- Server id: `20alexl/claude-engram`
- Homepage: https://github.com/20alexl/claude-engram
- Registry record: grade D, identity unverified
- Lifecycle: active
- Rate-limited: no
- Tools: 16
- Tool categories present: Execute, Read, Write
- Tags: 20alexl claude engram, automation
- Record last modified: 2026-10-04T11:48:45.118Z

## Tools (16)

| Tool | Category | Risk | Record |
| --- | --- | --- | --- |
| `audit_batch` | Read | Low | https://policylayer.com/tools/20alexl-claude-engram/audit-batch.md |
| `claude_engram_status` | Read | Low | https://policylayer.com/tools/20alexl-claude-engram/claude-engram-status.md |
| `context` | Read | Low | https://policylayer.com/tools/20alexl-claude-engram/context.md |
| `convention` | Read | Low | https://policylayer.com/tools/20alexl-claude-engram/convention.md |
| `deps_map` | Read | Low | https://policylayer.com/tools/20alexl-claude-engram/deps-map.md |
| `file_summarize` | Read | Low | https://policylayer.com/tools/20alexl-claude-engram/file-summarize.md |
| `find_similar_issues` | Read | Low | https://policylayer.com/tools/20alexl-claude-engram/find-similar-issues.md |
| `impact_analyze` | Read | Low | https://policylayer.com/tools/20alexl-claude-engram/impact-analyze.md |
| `memory` | Read | Low | https://policylayer.com/tools/20alexl-claude-engram/memory.md |
| `pre_edit_check` | Read | Low | https://policylayer.com/tools/20alexl-claude-engram/pre-edit-check.md |
| `scope` | Read | Low | https://policylayer.com/tools/20alexl-claude-engram/scope.md |
| `scout_search` | Read | Low | https://policylayer.com/tools/20alexl-claude-engram/scout-search.md |
| `session_end` | Read | Low | https://policylayer.com/tools/20alexl-claude-engram/session-end.md |
| `session_mine` | Read | Low | https://policylayer.com/tools/20alexl-claude-engram/session-mine.md |
| `session_start` | Read | Low | https://policylayer.com/tools/20alexl-claude-engram/session-start.md |
| `work` | Read | Low | https://policylayer.com/tools/20alexl-claude-engram/work.md |

## Tool descriptions

- `audit_batch` — Audit code for quality issues. Two modes: pass file_paths (paths or globs like
- `claude_engram_status` — Check Claude Engram health. Returns: status, model, memory stats.
- `deps_map` — Map a file
- `file_summarize` — Summarize a file
- `find_similar_issues` — Search an entire codebase for a regex bug pattern. Finds all occurrences of anti-patterns like bare excepts, hardcoded secrets, or missing null checks. Returns: matching files with line numbers, context snippets, and match count.
- `impact_analyze` — Analyze the impact of changing a file before making edits. Scans dependents, exported symbols, and usage patterns to estimate risk level (low/medium/high/critical). Returns: affected files, exported symbols at risk, suggested test target…
- `pre_edit_check` — RARELY NEEDED — the PreToolUse hook auto-runs this before every edit. Call manually only for an explicit impact check (past mistakes, loop risk, scope violations).
- `scout_search` — Search codebase semantically. Returns findings with files, lines, connections.
- `session_end` — RARELY NEEDED — Stop/SessionEnd hooks handle teardown automatically. Just a summary recap; memories save without it.
- `session_start` — RARELY NEEDED — the SessionStart hook auto-loads context every session. Call only for an explicit deep re-load (full memories + checkpoints + decisions + health).

## Related servers

- UnClick (1662 tools) — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server.md
- Apibase (1384 tools) — https://policylayer.com/tools/io-github-whiteknightonhorse-apibase.md
- Delx Mcp A2a (1068 tools) — https://policylayer.com/tools/io-github-davidmosiah-delx-mcp-a2a.md
- MCP Framework Personal (912 tools) — https://policylayer.com/tools/inggerman-mcps.md
- Hermoso (896 tools) — https://policylayer.com/tools/hermoso.md
- Nodebench (824 tools) — https://policylayer.com/tools/io-github-homenshum-nodebench.md
- Altium-MCP-Suite (817 tools) — https://policylayer.com/tools/altium-mcp-suite.md
- Eda Agent (777 tools) — https://policylayer.com/tools/eda-agent.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=20alexl-claude-engram · API: https://policylayer.com/registry/api · Recommended policies for every tool: https://policylayer.com/policies/20alexl-claude-engram