Engram (tinydarkforge) MCP Server
@tinydarkforge/engram
npm
v4.0.3
Published by @tinydarkforge — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
Local-first memory and assertion ledger for AI coding agents. Confidence-weighted, contradiction-aware, token-budgeted context over MCP.
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 1 = 99. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 6
low Hardcoded egress to an external endpoint in packaging/dev tooling (scripts/summarizer.js)MTC-SRC-003
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/summarizer.js:90`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const res = await this._fetch('https://api.anthropic.com/v1/messages', { method: 'POST', headers: {
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server scripts/summarizer.js
low Shell/command execution in packaging/dev tooling (scripts/engram-loader.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/engram-loader.js:12`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { execSync } = require('child_process'); const { gunzipSync } = require('zlib'); const { decode: msgpackDecode } = requi
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server scripts/engram-loader.js
low Shell/command execution in packaging/dev tooling (scripts/index-git.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/index-git.js:25`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: spawnSync } = require('child_process'); const { encode: msgpackEncode, decode: msgpackDecode } = require('@msgpack/msgp
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server scripts/index-git.js
low Shell/command execution in packaging/dev tooling (scripts/mcp-tools.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/mcp-tools.js:13`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ecFileSync } = require('child_process'); const { resolveEngramPath, resolveProjectDirName } = require('./paths'); const
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server scripts/mcp-tools.js
low Shell/command execution in packaging/dev tooling (scripts/save-session.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/save-session.js:16`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ecFileSync } = require('child_process'); const readline = require('readline'); const { resolveEngramPath, resolveProject
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server scripts/save-session.js
low Shell/command execution in packaging/dev tooling (scripts/setup.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/setup.js:11`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ecFileSync } = require('child_process'); const { resolveEngramPath } = require('./paths'); const { runMigrations } = req
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server scripts/setup.js
Tools 18
Each tool and what it can reach — statically extracted from the published source.
Concept Graphno sensitive capabilitycross_project_searchno sensitive capabilityEngram Statsno sensitive capabilityfind_duplicatesno sensitive capabilityget_bundleno sensitive capabilityget_sessionno sensitive capabilityget_topicsno sensitive capabilityledger_ingestno sensitive capabilityledger_queryno sensitive capabilityledger_select_contextno sensitive capability
Show 8 more tools ↓
ledger_statsno sensitive capabilitylist_projectsno sensitive capabilityneural_searchno sensitive capabilityquery_conceptno sensitive capabilityrebuild_indexno sensitive capabilityrecent_sessionsno sensitive capabilityrememberno sensitive capabilitysearch_sessionsno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (18 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 1
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v4.0.3 latest |
A 99/100 | 6 | 1.13.0 | 2026-09-07 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan @tinydarkforge/engram --onlineOther implementations of Engram 11
Independent packages implementing the same tool, scanned with the same engine. Compare all 12 side by side →
MCP server for cognitive knowledge graphs — models thought, emotion, reasoning, and episodic memory
MCP server for Engram: persistent memory for AI
The permanent and semantic memory layer for AI agents
Persistent memory for Claude Code — survives context compaction
Give Claude a perfect memory. Local-first MCP server with hybrid search.
MCP server for Engram — structured agent memory as relational intelligence
More in AI, Memory & Reasoning
FDA device & vehicle recall risk for AI agents: recall history, MAUDE trend, risk score.
Open-source MCP server exposing Agent402.Tools' catalog — 500+ strong: 400+ self-hostable tools + 100 multi-tool skill packs (security-audit, trend-analysis, structured-scrape, decode-blob, forecasting-bake-off) for AI agents — browser, web search & answe
Zero-dependency MCP server that gives AI agents a self-updating project memory in AGENTS.md. Returns merge instructions instead of mutating state, so every change is a reviewable diff.
MCP Apps UI resources and server helpers for n8n
MCP server providing comprehensive access to BookStack knowledge management system
MCP server for tracking achievements with STAR methodology