Sofagent MCP Server
@sofagent/mcp
npm
v1.4.5
Published by @sofagent — 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.
sofagent MCP Server — 暴露审计能力给 MCP Client（JSON-RPC 2.0 over stdio）
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 3
high Shell/command execution in server code (dist/tools/audit-tools.js)MTC-SRC-002
In the server's implementation (`dist/tools/audit-tools.js:8`): 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: Audit = runAudit; const child_process_1 = require("child_process"); const audit_1 = require("@sofagent/audit"); const th
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 dist/tools/audit-tools.js
high Shell/command execution in server code (dist/tools/orchestrator-tools.js)MTC-SRC-002
In the server's implementation (`dist/tools/orchestrator-tools.js:8`): 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: ompose = compose; const child_process_1 = require("child_process"); // =================================================
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 dist/tools/orchestrator-tools.js
medium Dynamic module load from a non-literal (dist/tools/knowledge-tools.js)MTC-SRC-005
In the server's implementation (`dist/tools/knowledge-tools.js:156`): 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: .then(s => __importStar(require(s)))); if (typeof fed.withOfflineFallback !== 'function' || typeof fed.listPeers
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 dist/tools/knowledge-tools.js
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 10
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 |
|---|---|---|---|---|
v1.4.5 latest |
A 93/100 | 3 | 1.13.0 | 2026-09-07 |
v1.4.4 |
A 93/100 | 3 | 1.13.0 | 2026-09-06 |
v1.4.2 |
A 93/100 | 3 | 1.13.0 | 2026-09-01 |
v1.4.1 |
A 93/100 | 3 | 1.13.0 | 2026-08-28 |
v1.4.0 |
A 93/100 | 3 | 1.13.0 | 2026-08-27 |
Show 5 more versions ↓
v1.3.9 |
A 93/100 | 3 | 1.12.1 | 2026-08-24 |
v1.3.8 |
A 93/100 | 3 | 1.12.1 | 2026-08-21 |
v1.3.7 |
A 93/100 | 3 | 1.12.1 | 2026-08-20 |
v1.3.6 |
A 93/100 | 3 | 1.12.1 | 2026-08-19 |
v1.3.5 |
A 93/100 | 3 | 1.12.1 | 2026-08-17 |
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 @sofagent/mcp --onlineMore in Business & CRM
Free public tax reference data — GST/VAT, income, company and capital-gains tax rules for 50+ countries.
The approval gate for unattended UCP buying agents — a policy/approval MCP proxy in front of a merchant's UCP checkout endpoint.
Autotask PSA MCP server. Generic entity query/get/create/update across the full REST API plus convenience tools for tickets, companies, contacts, projects, tasks and time entries. AI-safe with readonly mode and destructive-action confirmation. stdio + opt
MCP server for B2C Commerce developer experience tools
Search, compare and contact real-world companies through a public MCP business directory.
Norwegian business register (Brønnøysundregistrene) as an MCP server — companies, roles, subunits and annual accounts, with the register's silent traps encoded as guards.