People Context MCP Server
people-context
PyPI
v1.3.0
Published by jinyangwang27 — 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 MCP server giving AI agents contextual knowledge about the people in your life
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 (obsidian-plugin/src/bridge.ts)MTC-SRC-002
In the server's implementation (`obsidian-plugin/src/bridge.ts:15`): 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: nodeSpawn } from "node:child_process"; import { DB_KEY_ENV } from "./settings.js"; /** Why a run failed. Callers bran
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 obsidian-plugin/src/bridge.ts
high Shell/command execution in server code (src/people_context/cli/imports.py)MTC-SRC-002
In the server's implementation (`src/people_context/cli/imports.py:547`): 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: completed = subprocess.run([*editor, str(path)], check=False) except OSError as exc: _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/people_context/cli/imports.py
high Shell/command execution in server code (src/people_context/cli/setup.py)MTC-SRC-002
In the server's implementation (`src/people_context/cli/setup.py:375`): 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: ] completed = subprocess.run(command, check=False, capture_output=True, text=True) # noqa: S603 if comple
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/people_context/cli/setup.py
low Shell/command execution in packaging/dev tooling (obsidian-plugin/esbuild.config.mjs)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`obsidian-plugin/esbuild.config.mjs:27`): 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: , "electron", "node:child_process", "node:crypto", "node:fs", "node:os", "node:path", "node:process", "n
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 obsidian-plugin/esbuild.config.mjs
low Shell/command execution in packaging/dev tooling (tests/adapters/mcp/test_http_e2e.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/adapters/mcp/test_http_e2e.py:45`): 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: ck_port() process = subprocess.Popen( [ uv, "run", "people-context-mcp",
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/adapters/mcp/test_http_e2e.py
low Shell/command execution in packaging/dev tooling (tests/adapters/mcp/test_stdio_e2e.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/adapters/mcp/test_stdio_e2e.py:74`): 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: n updates" shown = subprocess.run( [uv, "run", "pctx", "--db", str(db_path), "show", person_id], cw
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/adapters/mcp/test_stdio_e2e.py
low Shell/command execution in packaging/dev tooling (tests/adapters/mcp/test_sync_multi_device_e2e.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/adapters/mcp/test_sync_multi_device_e2e.py:324`): 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: ot None completed = subprocess.run( [uv, "run", "pctx", "--db", str(db_path), *args], cwd=_PROJECT_R
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/adapters/mcp/test_sync_multi_device_e2e.py
low Shell/command execution in packaging/dev tooling (tests/adapters/web/test_browse_app.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/adapters/web/test_browse_app.py:1022`): 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: ot None completed = subprocess.run([node, str(program)], capture_output=True, text=True, timeout=60, 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 tests/adapters/web/test_browse_app.py
low Shell/command execution in packaging/dev tooling (tests/test_demo_packaging.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_demo_packaging.py:17`): 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: h / "wheel" built = subprocess.run( [uv, "build", "--wheel", "--out-dir", str(wheel_dir)], cwd=proje
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/test_demo_packaging.py
low Shell/command execution in packaging/dev tooling (tests/test_obsidian_plugin.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_obsidian_plugin.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: None: tracked = subprocess.run( ["git", "ls-files", "obsidian-plugin"], capture_output=T
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/test_obsidian_plugin.py
What this scan could not see
- No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Versions 8
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 |
|---|---|---|---|---|
v1.3.0 latest |
A 93/100 | 10 | 1.14.0 | 2026-09-24 |
v1.2.1 |
A 93/100 | 9 | 1.14.0 | 2026-09-20 |
v1.2.0 |
A 93/100 | 9 | 1.13.0 | 2026-09-14 |
v1.1.1 |
A 93/100 | 9 | 1.13.0 | 2026-09-04 |
v1.0.0 |
A 93/100 | 7 | 1.13.0 | 2026-08-27 |
Show 3 more versions ↓
v0.4.0 |
A 93/100 | 7 | 1.13.0 | 2026-08-25 |
v0.2.0 |
A 96/100 | 3 | 1.12.1 | 2026-07-27 |
v0.1.1 |
A 98/100 | 3 | 1.5.0 | 2026-07-23 |
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 people-context --online --registry pypiMore in Developer Tools
Hotel booking MCP server — 300K+ properties, real confirmation numbers, loyalty programs. Builders monetize every booking via Stripe Connect. The first MCP server that completes real hotel reservations inside AI conversations.
Generates production-ready UI components from natural language, inspired by v0.
Model Context Protocol server that serves the A11y Context accessibility-pattern corpus (WCAG 2.2 AA patterns, Foundations rules) to AI coding agents.
Manage AdGuard Home through AI assistants
Read-only Azure DevOps for MCP clients using only your existing browser session — no PAT, no Azure CLI. Browse work items, pull requests, comments, attachments and Artifacts feeds across every project, repo and feed you can access.
MCP server for Adobe Experience Manager Assets integration development