Lore Sdk MCP Server
lore-sdk
PyPI
v1.4.2
Published by agentkitai — 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.
Cross-agent semantic memory with knowledge graphs, fact extraction, and MCP integration
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 12
high Shell/command execution in server code (src/lore/bootstrap.py)MTC-SRC-002
In the server's implementation (`src/lore/bootstrap.py:132`): 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: y: result = subprocess.run( ["docker", "info"], capture_output=True,
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/lore/bootstrap.py
high Shell/command execution in server code (src/lore/cli/commands/_project.py)MTC-SRC-002
In the server's implementation (`src/lore/cli/commands/_project.py:98`): 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( ["git", "-C", str(cwd), *args], check=True,
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/lore/cli/commands/_project.py
high Shell/command execution in server code (src/lore/cli/commands/capture.py)MTC-SRC-002
In the server's implementation (`src/lore/cli/commands/capture.py:587`): 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: proc = subprocess.Popen( # noqa: S603 — input is internal, not user-supplied # Claude Code
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/lore/cli/commands/capture.py
high Shell/command execution in server code (src/lore/cli/commands/dream.py)MTC-SRC-002
In the server's implementation (`src/lore/cli/commands/dream.py:420`): 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: return subprocess.Popen( # noqa: S603 — internal prompt # See cli/commands/capture.py for
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/lore/cli/commands/dream.py
high Shell/command execution in server code (src/lore/cli/commands/server.py)MTC-SRC-002
In the server's implementation (`src/lore/cli/commands/server.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: log", "ab") subprocess.Popen( [ "lore", "serve",
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/lore/cli/commands/server.py
high Shell/command execution in server code (src/lore/freshness/git_ops.py)MTC-SRC-002
In the server's implementation (`src/lore/freshness/git_ops.py: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: try: result = subprocess.run( cmd, capture_output=True, text=True,
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/lore/freshness/git_ops.py
high Shell/command execution in server code (src/lore/github/syncer.py)MTC-SRC-002
In the server's implementation (`src/lore/github/syncer.py:66`): 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( cmd, capture_output=True, text=True,
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/lore/github/syncer.py
high Shell/command execution in server code (src/lore/services/graph_extraction.py)MTC-SRC-002
In the server's implementation (`src/lore/services/graph_extraction.py:252`): 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_mcp=False) return subprocess.Popen( # noqa: S603 — internal prompt [ "claude", "-p", prompt,
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/lore/services/graph_extraction.py
high Shell/command execution in server code (src/lore/setup.py)MTC-SRC-002
In the server's implementation (`src/lore/setup.py:127`): 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: subprocess.run( ["bash", "-c", _ENSURE_SERVER_BASH], stdout=subprocess.D
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/lore/setup.py
medium Dynamic module load from a non-literal (src/lore/server/models.py)MTC-SRC-005
In the server's implementation (`src/lore/server/models.py:133`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: """Single lesson for import (upsert).""" id: Optional[str] = None problem: str = Field(..., min_length=1)
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/lore/server/models.py
medium Dynamic module load from a non-literal (src/lore/server/routes/lessons.py)MTC-SRC-005
In the server's implementation (`src/lore/server/routes/lessons.py:337`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: rtResponse: """Bulk import (upsert) lessons.""" count = await lessons_service.import_lessons( store,
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/lore/server/routes/lessons.py
low Shell/command execution in packaging/dev tooling (tests/cli/test_resolve_project.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/cli/test_resolve_project.py:75`): 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: args: str) -> None: subprocess.run( ["git", *args], cwd=str(cwd), check=True, captur
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/cli/test_resolve_project.py
Tools 3
Each tool and what it can reach — statically extracted from the published source.
save_snapshotno sensitive capabilitytopic_detailno sensitive capabilitytopicsno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (3 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 |
|---|---|---|---|---|
v1.4.2 latest |
A 93/100 | 12 | 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 lore-sdk --online --registry pypiMore 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