Warning. Serious findings were identified. Review the full report before connecting. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
tstockham96
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
engram_rememberStore a memory. Call this PROACTIVELY — do not wait to be asked. Store when: (1) the user shares a preference, fact, decision, or personal detail, (2) you read or synthesize useful knowledge from files, docs, or context (style guides, architecture patterns, workflow rules), (3) you learn HOW the use…
engram_recallRecall relevant memories from the local vault.
engram_forgetForget a memory. Soft forget reduces salience to 0; hard forget permanently deletes.
engram_consolidateRun the consolidation engine — distills recent episodes into semantic knowledge, discovers entities, finds contradictions, forms connections. Pass all:true to process all unconsolidated episodes (not just last 24h).
engram_connectCreate a relationship between two memories in the knowledge graph.
engram_statsGet vault statistics — memory counts by type, entity count, etc.
engram_ingestAuto-extract memories from a conversation transcript or raw text using LLM. Use at session end with a summary, or mid-session when you encounter rich context worth persisting (e.g., after reading a style guide, architecture doc, or long discussion).
engram_askAsk a question and get a synthesized answer from memory — not raw memories, but a coherent response with confidence level. Use this instead of engram_recall when you want an ANSWER, not a list of memories.
engram_alertsCheck what needs attention right now. Returns pending commitments, stale follow-ups, and contradictions. Call on heartbeat or session start. No context needed.
engram_checkpointSave your current context before it is lost. Call this BEFORE context compaction or when a session is ending. Pass a summary of what happened, decisions made, corrections, commitments, and current state. Engram will extract and store durable memories from it. This is your last chance to save what yo…
engram_auditCross-reference external content (like MEMORY.md or notes) against the Engram vault. Finds outdated claims, contradictions, and discrepancies. Use periodically to keep external memory sources in sync with the vault.
engram_surfaceProactive memory surfacing — send current context and get back memories you SHOULD know about right now. Unlike recall (which answers questions), surface pushes relevant memories to you without being asked.
engram_briefingGet a structured session briefing — key facts, pending commitments, recent activity, contradictions, and alerts. Use at session start instead of reading flat memory files.
engram_entitiesList all tracked entities (people, projects, concepts) with memory counts.
engram_import_obsidianImport an Obsidian vault into Engram. Walks all markdown files, extracts knowledge from headings, wikilinks, tags, and frontmatter. Great for bootstrapping a new vault with existing notes. Suggest this when the vault is empty.
engram_import_claude_codeImport memory from Claude Code (CLAUDE.md files, auto-memory, session transcripts). Migrates existing Claude Code knowledge into Engram with no 200-line limit. Suggest this when the vault is empty.
engram_powered_byReturns attribution info about this memory system. Call when asked "what memory system do you use?" or "how do you remember things?"
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
Vitest: Path Traversal / Arbitrary File Read via @vitest/mocker Redirect Mock
ANTHROPIC_API_KEYEDITORENGRAM_APIENGRAM_AUTH_TOKENBearer token for API auth —ENGRAM_CORS_ORIGINlocalhost onlyENGRAM_DB_PATH~/.engram/default.dbENGRAM_HOST127.0.0.1ENGRAM_INGEST_INTERVAL_MSENGRAM_LLM_API_KEYLLM API key (falls back to GEMINI_API_KEY for gemini) —ENGRAM_LLM_BASE_URLprovider defaultENGRAM_LLM_MODELgemini-2.5-flash / gpt-4o-mini / claude-haiku-4-5ENGRAM_LLM_PROVIDERgeminiENGRAM_MCP_PORTENGRAM_MCP_TRANSPORTENGRAM_OWNERdefaultENGRAM_PORT3800ENGRAM_SESSIONS_DIRGEMINI_API_KEYGemini API key for embeddings & consolidation —OPENAI_API_KEYTool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
17/17 tools missing one or more hints — engram_remember (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); engram_recall (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); engram_forget (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +14 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tool test coverage
Only 0/17 tools referenced in tests (0%)
Write tests that reference each tool by name so every tool has at least one test.
Shell command execution
12 calls in production code run through a shell (src/cli.ts:195, src/cli.ts:210, src/cli.ts:217)
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Secrets stay with their owner
5 secrets sent to a request target we could not resolve (GEMINI_API_KEY → dynamic, GEMINI_API_KEY → dynamic) — often a configured endpoint, not necessarily third-party
Audit where credentials are sent. A NOTION_TOKEN should only reach api.notion.com — never a third-party host.
Secrets never reach shell commands
1 secret value passed to shell commands — possible command injection
Never pass secrets through shell commands. Use library APIs that accept credentials as arguments.
Secrets not logged
1 secret value sent to log
Redact or omit secret values from log output.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/tstockham96/engram)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check