Engram (kpachhai) MCP Server
engram-mcp-server
PyPI
v0.6.0
Published by kpachhai — 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.
Personal AI memory backend - portable, sovereign, protocol-compatible (MCP server with markdown source-of-truth and local vector search).
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 − 7 = 93. 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 |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
| −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 10
high Shell/command execution in server code (src/engram/cli/daemon.py)MTC-SRC-002
In the server's implementation (`src/engram/cli/daemon.py:151`): 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: try: result = subprocess.run( # noqa: S603 - fixed argv with int-coerced pid [ps_bin, "-p", str(p
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 src/engram/cli/daemon.py
high Shell/command execution in server code (src/engram/cli/team_vault.py)MTC-SRC-002
In the server's implementation (`src/engram/cli/team_vault.py:466`): 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: =True) result = subprocess.run( # noqa: S603 ["git", "clone", remote_url, str(target_path)], # noq
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 src/engram/cli/team_vault.py
high Shell/command execution in server code (src/engram/daemon/spawn.py)MTC-SRC-002
In the server's implementation (`src/engram/daemon/spawn.py:72`): 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: ntinel for a successful spawn (used in equality checks).""" return cls(kind=_ReadinessKind.READY) @classmet
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 src/engram/daemon/spawn.py
high Shell/command execution in server code (src/engram/storage/facade.py)MTC-SRC-002
In the server's implementation (`src/engram/storage/facade.py:196`): 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: s result = subprocess.run( # noqa: S603 ["git", "-C", str(self.thoughts_dir), "symbolic-re
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 src/engram/storage/facade.py
high Shell/command execution in server code (src/engram/sync/startup_probes.py)MTC-SRC-002
In the server's implementation (`src/engram/sync/startup_probes.py:317`): 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: cp_agent = subprocess.run( # noqa: S603 - resolved absolute path; static args [gpg_connect
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 src/engram/sync/startup_probes.py
high Shell/command execution in server code (src/engram/team/server_hooks/pre_receive.py)MTC-SRC-002
In the server's implementation (`src/engram/team/server_hooks/pre_receive.py:205`): 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: onzero.""" result = subprocess.run( # noqa: S603 - git is the canonical tool here ["git", *args], # noqa:
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 src/engram/team/server_hooks/pre_receive.py
high Shell/command execution in server code (src/engram/utils/run_command.py)MTC-SRC-002
In the server's implementation (`src/engram/utils/run_command.py:72`): 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: eError(msg) return subprocess.run( # noqa: S603 - shell=False (default); args validated above list(args),
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 src/engram/utils/run_command.py
low Shell/command execution in packaging/dev tooling (tests/consolidate/test_apply.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/consolidate/test_apply.py:249`): 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: r) -> str: result = subprocess.run( # noqa: S603 - test-only helper; args are static literals ["git", *args
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 tests/consolidate/test_apply.py
low Shell/command execution in packaging/dev tooling (tests/storage/test_branch_drift.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/storage/test_branch_drift.py:21`): 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: cwd: Path) -> None: subprocess.run( # noqa: S603 ["git", *args], # noqa: S607 cwd=str(cwd),
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 tests/storage/test_branch_drift.py
low Shell/command execution in packaging/dev tooling (tests/sync/conftest.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/sync/conftest.py:32`): 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: e_output.""" return subprocess.run( # noqa: S603 - test-only helper; args are static literals ["git", *args
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 tests/sync/conftest.py
Tools 8
Each tool and what it can reach — statically extracted from the published source.
fetchingests untrusted inputcapture_thoughtno sensitive capabilitydelete_thoughtno sensitive capabilitylist_thoughtsno sensitive capabilitysearch_thoughtsno sensitive capabilitysummarize_thoughtno sensitive capabilitysynthesize_thoughtsno sensitive capabilitythought_statsno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (8 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 |
|---|---|---|---|---|
v0.6.0 latest |
A 93/100 | 10 | 1.13.0 | 2026-08-25 |
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 engram-mcp-server --online --registry pypiOther 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
Local-first memory and assertion ledger for AI coding agents. Confidence-weighted, contradiction-aware, token-budgeted context over MCP.
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.
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