Lab Agent MCP Server
mcp-lab-agent
npm
v2.3.1
Published by wesley-gomes93 — 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.
Sistema de Inteligência em Qualidade de Software: executa, analisa, prevê, recomenda e aprende. Memória local + Learning Hub.
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 − 11 = 89. 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 |
|---|---|
| −10 | capability blast radius (critical) — 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 7
critical Completed toxic-flow trifecta across toolsMTC-FLOW-002
This server (without client built-ins) exposes a complete data-exfiltration chain: read_project → generate_tests ⇒ web_eval_browser. Untrusted input is ingested, private data is read, and it can be sent to an external sink — and at least one leg is a direct schema wire (⇒), where a producer's output drops straight into a free-text parameter of the next tool, so the chain needs little agent cooperation. Static analysis proves the primitive exists, not that a specific run will occur.
Fix: Remove one leg of the trifecta: isolate untrusted-input tools from secret-reading tools and from egress tools, or require human approval between them.
Location: flow read_project → generate_tests → web_eval_browser
high Tool "web_eval_browser" exposes command/code executionMTC-CAP-001
Tool "web_eval_browser" appears to run shell commands or evaluate code (keyword "eval" in tool name). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.
Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.
Location: tool web_eval_browser
high Shell/command execution in server code (dist/index.js)MTC-SRC-002
In the server's implementation (`dist/index.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: spawn as spawn2 } from "child_process"; import path6 from "path"; import fs6 from "fs"; import { fileURLToPath, pathToFi
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/index.js
high Shell/command execution in server code (slack-bot/src/workers/qa-job.js)MTC-SRC-002
In the server's implementation (`slack-bot/src/workers/qa-job.js:1`): 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: rt { spawn } from "node:child_process"; import fs from "node:fs"; import path from "node:path"; import { getRepoForChann
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 slack-bot/src/workers/qa-job.js
medium Dynamic module load from a non-literal (dist/index.js)MTC-SRC-005
In the server's implementation (`dist/index.js:4768`): 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: ubPath).href; await import(hubUrl2); return; } if (cmd === "slack-bot") { const __dirname2 = path6.dirna
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/index.js
low Mutating tool "web_eval_browser" declares no destructiveHintMTC-CAP-005
Tool "web_eval_browser" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool web_eval_browser
low Unconstrained path parameter "path" on "read_file"MTC-CAP-008
Tool "read_file" takes a path parameter "path" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.
Fix: Resolve and verify the path stays within an allowed root; reject traversal sequences.
Location: tool read_file · inputSchema.properties.path
Tools 31
Each tool and what it can reach — statically extracted from the published source.
generate_testsreads sensitive dataread_filereads sensitive dataread_projectingests untrusted inputweb_eval_browserruns code / shellanalyze_failuresno sensitive capabilityanalyze_file_methodsno sensitive capabilitycreate_bug_reportno sensitive capabilitycreate_test_templateno sensitive capabilitydetect_projectno sensitive capabilityget_business_metricsno sensitive capability
Show 21 more tools ↓
get_learning_reportno sensitive capabilityget_test_coverageno sensitive capabilityinstall_dependenciesno sensitive capabilitylist_test_filesno sensitive capabilitymap_mobile_elementsno sensitive capabilitypor_que_falhouno sensitive capabilityqa_autono sensitive capabilityqa_compare_with_industryno sensitive capabilityqa_full_analysisno sensitive capabilityqa_health_checkno sensitive capabilityqa_learning_statsno sensitive capabilityqa_predict_flakyno sensitive capabilityqa_route_taskno sensitive capabilityqa_suggest_next_testno sensitive capabilityqa_time_travelno sensitive capabilityrun_linterno sensitive capabilityrun_testsno sensitive capabilitysuggest_fixno sensitive capabilitysuggest_selector_fixno sensitive capabilitywatch_testsno sensitive capabilitywrite_testno sensitive capability
Toxic flows 1
Cross-tool combinations that form a data-exfiltration primitive (untrusted input → sensitive source → external sink).
What this scan could not see
- Tools were statically extracted from the published source (31 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 |
|---|---|---|---|---|
v2.3.1 latest |
B 89/100 | 7 | 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 mcp-lab-agent --onlineMore in Security & Testing
The Stripe Agent Toolkit enables popular agent frameworks including LangChain and Vercel's AI SDK to integrate with Stripe APIs through function calling.
MCP (Model Context Protocol) server for AgentGate. Enables Claude and other MCP-compatible AI assistants to request approvals.
Scan any website for AI agent readiness, payment protocols, and discovery endpoints
MCP server for aigently security guardrails — reads static catalog-data JSON, zero API dependency
Governed threat modeling, code threat verification, traceability & compliance, as MCP tools.
Governed threat modeling, code threat verification, traceability & compliance, as MCP tools.