Sumo Qa MCP Server
sumo-qa
PyPI
v0.61.0
Published by sumithr — 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.
Sumo QA — a senior-QA-shaped MCP server for pre-coding QA planning, TDD scaffolding, mutation-testing follow-up, code review, and test-data discovery.
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 − 1.2 = 99. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −1.2 | Hardcoded GitHub token in test/example/packaging MTC-SRC-008 | exfiltration |
2. Client adoption risk — 99 − 7 = 92. 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 14
high Shell/command execution in server code (.claude/hooks/validate-on-content-edit.py)MTC-SRC-002
In the server's implementation (`.claude/hooks/validate-on-content-edit.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: return 0 result = subprocess.run( ["sumo-qa-validate"], cwd=repo_root, 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 .claude/hooks/validate-on-content-edit.py
high Shell/command execution in server code (src/sumo_qa/doctor.py)MTC-SRC-002
In the server's implementation (`src/sumo_qa/doctor.py:238`): 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: rams": {}}) proc = subprocess.Popen( # noqa: S603 -- argv comes from a trusted McpCommand mcp_cmd.as_subpr
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/sumo_qa/doctor.py
high Shell/command execution in server code (src/sumo_qa/external_skills.py)MTC-SRC-002
In the server's implementation (`src/sumo_qa/external_skills.py:188`): 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: ry: completed = subprocess.run( command, capture_output=True, check=False,
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/sumo_qa/external_skills.py
medium Dynamic module load from a non-literal (src/sumo_qa/repo_map_resolvers/typescript.py)MTC-SRC-005
In the server's implementation (`src/sumo_qa/repo_map_resolvers/typescript.py:551`): 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: g literal (a computed ``require(name)`` / ``import(expr)`` cannot be resolved statically). """ c
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/sumo_qa/repo_map_resolvers/typescript.py
low Hardcoded GitHub token in test/example/packaging (tests/test_feedback_memory.py)MTC-SRC-008
A hardcoded GitHub token (a live-looking credential hardcoded in shipped code) appears in `tests/test_feedback_memory.py:347`. Verify whether this is a real credential; if so, remove and rotate it.
Evidence: GitHub token: ghp_…(redacted)
Fix: Remove the secret, rotate it, and load credentials from the environment or a secret store.
Location: server tests/test_feedback_memory.py
low Dynamic code execution in packaging/dev tooling (tests/test_route_qa_runners.py)MTC-SRC-001
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_route_qa_runners.py:406`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: positives; a first-line eval (the common case) still routes. This pins the accepted trailing-line miss.
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_route_qa_runners.py
low Shell/command execution in packaging/dev tooling (.claude/skills/regen-eval-baseline/scripts/run_baseline.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`.claude/skills/regen-eval-baseline/scripts/run_baseline.py:448`): 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: in(cmd)}") result = subprocess.run(cmd, cwd=repo_root) if result.returncode != 0: print( f"\
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 .claude/skills/regen-eval-baseline/scripts/run_baseline.py
low Shell/command execution in packaging/dev tooling (scripts/check_codeblock_file_refs.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/check_codeblock_file_refs.py:71`): 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: > list[Path]: out = subprocess.check_output( ["git", "ls-files", "*.md"], cwd=repo_root, tex
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 scripts/check_codeblock_file_refs.py
low Shell/command execution in packaging/dev tooling (scripts/check_mutation_gate.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/check_mutation_gate.py:186`): 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: list[str]: result = subprocess.run( ["git", "diff", "--name-only", "--no-renames", spec], capture_ou
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 scripts/check_mutation_gate.py
low Shell/command execution in packaging/dev tooling (scripts/dev_install.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/dev_install.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: lush=True) result = subprocess.run(argv, check=False) if check and result.returncode != 0: print(f"\n[de
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 scripts/dev_install.py
low Shell/command execution in packaging/dev tooling (scripts/generate_marketplace_assets.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/generate_marketplace_assets.py:220`): 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: ). """ result = subprocess.run( [sys.executable, "-m", "sumo_qa.doctor"], 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 scripts/generate_marketplace_assets.py
low Shell/command execution in packaging/dev tooling (scripts/regen_tools_list_snapshot.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/regen_tools_list_snapshot.py:29`): 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: lse src_path return subprocess.Popen( [sys.executable, "-m", "sumo_qa"], stdin=subprocess.PIPE,
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 scripts/regen_tools_list_snapshot.py
low Shell/command execution in packaging/dev tooling (scripts/uvx_smoke_handshake.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/uvx_smoke_handshake.py:96`): 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: RED"] = "1" proc = subprocess.Popen( # noqa: S603 -- cmd is caller-controlled cmd, stdin=subproces
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 scripts/uvx_smoke_handshake.py
low Dynamic module load from a non-literal in packaging/dev tooling (tests/test_repo_map_resolvers_typescript.py)MTC-SRC-005
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_repo_map_resolvers_typescript.py:163`): 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: js.extract(b"const x = require(dynamicName);\n") == [] @_needs_ts def test_extract_empty_specifier_literal(): # `
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_repo_map_resolvers_typescript.py
Tools 30
Each tool and what it can reach — statically extracted from the published source.
sumo_qa_list_skill_manifestsingests untrusted inputsumo_qa_analyze_diff_impactno sensitive capabilitysumo_qa_capabilitiesno sensitive capabilitysumo_qa_capture_review_feedbackno sensitive capabilitysumo_qa_check_external_skill_installedno sensitive capabilitysumo_qa_execute_external_skillno sensitive capabilitysumo_qa_explain_test_data_requirementsno sensitive capabilitysumo_qa_export_test_casesno sensitive capabilitysumo_qa_find_test_datano sensitive capabilitysumo_qa_format_context_bundleno sensitive capability
Show 20 more tools ↓
sumo_qa_format_qa_scorecardno sensitive capabilitysumo_qa_format_risk_ledgerno sensitive capabilitysumo_qa_generate_qa_reportno sensitive capabilitysumo_qa_ingest_knowledge_packno sensitive capabilitysumo_qa_install_external_skillno sensitive capabilitysumo_qa_load_approachesno sensitive capabilitysumo_qa_load_catalogue_entryno sensitive capabilitysumo_qa_load_classificationsno sensitive capabilitysumo_qa_load_principlesno sensitive capabilitysumo_qa_load_rulesno sensitive capabilitysumo_qa_load_skill_contextno sensitive capabilitysumo_qa_load_standardsno sensitive capabilitysumo_qa_load_techniquesno sensitive capabilitysumo_qa_query_repo_mapno sensitive capabilitysumo_qa_record_coverageno sensitive capabilitysumo_qa_record_mutationno sensitive capabilitysumo_qa_register_known_good_test_datano sensitive capabilitysumo_qa_scan_repono sensitive capabilitysumo_qa_search_external_skillsno sensitive capabilitysumo_qa_validate_test_datano sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (30 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 5
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 |
|---|---|---|---|---|
v0.61.0 latest |
A 92/100 | 14 | 1.13.0 | 2026-09-05 |
v0.60.9 |
A 92/100 | 14 | 1.13.0 | 2026-09-04 |
v0.60.6 |
A 92/100 | 14 | 1.13.0 | 2026-08-25 |
v0.60.2 |
A 92/100 | 14 | 1.12.1 | 2026-08-02 |
v0.60.1 |
A 92/100 | 14 | 1.12.1 | 2026-07-27 |
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 sumo-qa --online --registry pypiMore 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.