Elite Reasoning MCP Server
elite-reasoning-mcp
PyPI
v1.2.1
Published by snehgabani — 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.
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 8
high Tool "run_elite_eval_suite" exposes command/code executionMTC-CAP-001
Tool "run_elite_eval_suite" 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 run_elite_eval_suite
high Tool "export_eval_harness" exposes command/code executionMTC-CAP-001
Tool "export_eval_harness" 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 export_eval_harness
high Shell/command execution in server code (test_quality_gate.py)MTC-SRC-002
In the server's implementation (`test_quality_gate.py:22`): 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: ubprocess process = subprocess.Popen( [sys.executable, "-m", "uvicorn", "core.integration.sync_server:app",
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 test_quality_gate.py
high Shell/command execution in server code (test_team_sync.py)MTC-SRC-002
In the server's implementation (`test_team_sync.py:23`): 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: nd server_process = subprocess.Popen( [sys.executable, "core/integration/sync_server.py"], stdout=su
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 test_team_sync.py
medium Untrusted input can drive an external actionMTC-FLOW-005
Untrusted-input tools ([validate_predictions, browse_tool_usage, introspect]) co-exist with external-action tools ([run_elite_eval_suite, export_eval_harness]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.
Evidence: untrusted [validate_predictions, browse_tool_usage, introspect] → sinks [run_elite_eval_suite, export_eval_harness]
Fix: Require confirmation for state-changing/egress actions triggered after processing untrusted content.
Location: flow validate_predictions → run_elite_eval_suite
low Mutating tool "run_elite_eval_suite" declares no destructiveHintMTC-CAP-005
Tool "run_elite_eval_suite" 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 run_elite_eval_suite
low Mutating tool "export_eval_harness" declares no destructiveHintMTC-CAP-005
Tool "export_eval_harness" 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 export_eval_harness
low Shell/command execution in packaging/dev tooling (scripts/release_check.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/release_check.py: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: > {name}") result = subprocess.run(command, cwd=ROOT) if result.returncode != 0: raise SystemExit(result
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/release_check.py
Tools 92
Each tool and what it can reach — statically extracted from the published source.
browse_tool_usageingests untrusted inputexport_eval_harnessruns code / shellintrospectingests untrusted inputrun_elite_eval_suiteruns code / shellvalidate_predictionsingests untrusted inputadopt_vs_buildno sensitive capabilityafter_action_reviewno sensitive capabilityanalyzeno sensitive capabilityanalyze_prompt_sequenceno sensitive capabilityarchive_goalno sensitive capability
Show 82 more tools ↓
assess_confidenceno sensitive capabilityauditno sensitive capabilityautonomous_scanno sensitive capabilitybayesian_updateno sensitive capabilitybenchmark_trackno sensitive capabilitybias_scanno sensitive capabilitybuild_experiment_treeno sensitive capabilitycalculate_expected_valueno sensitive capabilitycalibration_predictno sensitive capabilitycalibration_resolveno sensitive capabilitycalibration_scoreno sensitive capabilitycheck_anti_patternsno sensitive capabilitycheck_goalsno sensitive capabilitycompound_growthno sensitive capabilitydecision_council_reviewno sensitive capabilitydelete_goalno sensitive capabilitydelete_prevention_ruleno sensitive capabilityelite_doctorno sensitive capabilityelite_doctor_jsonno sensitive capabilityelite_outcome_scorecardno sensitive capabilityfive_whysno sensitive capabilityfmea_analysisno sensitive capabilityfmea_risk_gateno sensitive capabilitygenerate_autonomous_goalsno sensitive capabilityget_autonomous_statusno sensitive capabilityget_elite_workflowno sensitive capabilityget_prompt_quality_trendno sensitive capabilityget_quality_trendno sensitive capabilityget_tool_usage_statsno sensitive capabilityget_user_profileno sensitive capabilityget_user_thinking_modelno sensitive capabilityingest_contextno sensitive capabilitylearnno sensitive capabilitylist_prevention_rulesno sensitive capabilitylist_team_usersno sensitive capabilitymemory_context_packno sensitive capabilitymemory_search_contextno sensitive capabilitymemory_sync_decisionsno sensitive capabilitymemory_sync_mistakesno sensitive capabilitymemory_sync_rulesno sensitive capabilitynuclear_prompt_breakdownno sensitive capabilityorchestrate_request_toolno sensitive capabilityplanno sensitive capabilitypolish_promptno sensitive capabilitypre_commit_auditno sensitive capabilitypredictno sensitive capabilitypredictive_preventionno sensitive capabilityquery_temporal_graphno sensitive capabilityreasoning_preflightno sensitive capabilityrecommend_open_source_integrationsno sensitive capabilityrecord_decisionno sensitive capabilityrecord_hypothesisno sensitive capabilityrecord_missed_detectionno sensitive capabilityrecord_mistakeno sensitive capabilityrecord_prompt_intentno sensitive capabilityrecord_prospective_failureno sensitive capabilityrecord_quality_scoreno sensitive capabilityregister_prevention_ruleno sensitive capabilityrememberno sensitive capabilityremember_contextno sensitive capabilityresearch_benchmark_catalogno sensitive capabilityresolve_hypothesisno sensitive capabilityresolve_prospective_failureno sensitive capabilityroi_tool_budgetno sensitive capabilitysearch_decisionsno sensitive capabilitysearch_thinking_patternsno sensitive capabilityselect_reasoning_protocolno sensitive capabilityself_diagnoseno sensitive capabilityset_goalno sensitive capabilityshare_skillno sensitive capabilitysimulate_future_regretsno sensitive capabilitysmoke_test_gateno sensitive capabilitysocratic_challengeno sensitive capabilityswiss_cheese_auditno sensitive capabilitysync_team_memoryno sensitive capabilityupdate_goalno sensitive capabilityupdate_thinking_patternno sensitive capabilityupdate_user_configno sensitive capabilityverify_capabilities_toolno sensitive capabilityworkflow_runno sensitive capabilityworkflow_statusno sensitive capabilityworkflow_update_stepno 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 (92 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 |
|---|---|---|---|---|
v1.2.1 latest |
A 93/100 | 8 | 1.9.0 | 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 elite-reasoning-mcp --online --registry pypiMore in Developer Tools
Security scan results for the 1stay MCP server.
Security scan results for the Adguard Home MCP server.
Security scan results for the Ado Browser MCP server.
Security scan results for the Adobe Experience Dev MCP server.
Security scan results for the Aemet MCP server.
Security scan results for the Affinity Mcp Bridge MCP server.