Turingmind MCP Server
turingmind-mcp
PyPI
v0.3.0
Published by turingmindai — 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 |
| ✓ | inspection depth (source) — how much of the target the scan could see |
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 19
high Sensitive-source and external-sink co-existMTC-FLOW-004
Tools that read sensitive data ([turingmind_get_edit_reasoning, turingmind_request_code_edit, turingmind_analyze_diff, turingmind_store_auto_plan, turingmind_get_auto_plans, turingmind_apply_edit, turingmind_bootstrap_codebase]) and tools that can send data out ([turingmind_enable_auto_review, turingmind_create_issue, turingmind_create_comment]) are exposed together. An agent can move private data to the sink.
Evidence: sources [turingmind_get_edit_reasoning, turingmind_request_code_edit, turingmind_analyze_diff, turingmind_store_auto_plan, turingmind_get_auto_plans, turingmind
Fix: Keep secret-reading and egress capabilities on separate, separately-approved servers.
Location: flow turingmind_get_edit_reasoning → turingmind_enable_auto_review
high Shell/command execution in server code (src/turingmind_mcp/auto_review_service.py)MTC-SRC-002
In the server's implementation (`src/turingmind_mcp/auto_review_service.py:119`): 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: subprocess.run(
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/turingmind_mcp/auto_review_service.py
high Shell/command execution in server code (src/turingmind_mcp/chat_capture.py)MTC-SRC-002
In the server's implementation (`src/turingmind_mcp/chat_capture.py:413`): 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: subprocess.run(
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/turingmind_mcp/chat_capture.py
high Shell/command execution in server code (src/turingmind_mcp/chat_observation_poller.py)MTC-SRC-002
In the server's implementation (`src/turingmind_mcp/chat_observation_poller.py:65`): 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: subprocess.check_output(
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/turingmind_mcp/chat_observation_poller.py
high Shell/command execution in server code (src/turingmind_mcp/client/client.py)MTC-SRC-002
In the server's implementation (`src/turingmind_mcp/client/client.py:59`): 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: subprocess.Popen(
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/turingmind_mcp/client/client.py
high Shell/command execution in server code (src/turingmind_mcp/cursor_database_reader.py)MTC-SRC-002
In the server's implementation (`src/turingmind_mcp/cursor_database_reader.py:109`): 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: subprocess.run(
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/turingmind_mcp/cursor_database_reader.py
high Shell/command execution in server code (src/turingmind_mcp/entity_indexer.py)MTC-SRC-002
In the server's implementation (`src/turingmind_mcp/entity_indexer.py:455`): 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: subprocess.run(
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/turingmind_mcp/entity_indexer.py
high Shell/command execution in server code (src/turingmind_mcp/git_churn.py)MTC-SRC-002
In the server's implementation (`src/turingmind_mcp/git_churn.py:37`): 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: subprocess.run(
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/turingmind_mcp/git_churn.py
high Shell/command execution in server code (src/turingmind_mcp/unified_cli.py)MTC-SRC-002
In the server's implementation (`src/turingmind_mcp/unified_cli.py:61`): 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: subprocess.run(
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/turingmind_mcp/unified_cli.py
high Shell/command execution in server code (src/turingmind_mcp/v2_engine/handlers.py)MTC-SRC-002
In the server's implementation (`src/turingmind_mcp/v2_engine/handlers.py:618`): 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: subprocess.run(
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/turingmind_mcp/v2_engine/handlers.py
high Shell/command execution in server code (src/turingmind_mcp/v2_engine/security_scanner.py)MTC-SRC-002
In the server's implementation (`src/turingmind_mcp/v2_engine/security_scanner.py:94`): 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: subprocess.run(
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/turingmind_mcp/v2_engine/security_scanner.py
medium Unconstrained URL/host parameter "webhook_url" on "turingmind_enable_auto_review"MTC-CAP-007
Tool "turingmind_enable_auto_review" takes a URL/host parameter "webhook_url" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).
Fix: Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.
Location: tool turingmind_enable_auto_review · inputSchema.properties.webhook_url
low Unconstrained path parameter "file_path" on "turingmind_get_edit_reasoning"MTC-CAP-008
Tool "turingmind_get_edit_reasoning" takes a path parameter "file_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 turingmind_get_edit_reasoning · inputSchema.properties.file_path
low Unconstrained path parameter "file_path" on "turingmind_request_code_edit"MTC-CAP-008
Tool "turingmind_request_code_edit" takes a path parameter "file_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 turingmind_request_code_edit · inputSchema.properties.file_path
low Unconstrained path parameter "file_path" on "turingmind_analyze_diff"MTC-CAP-008
Tool "turingmind_analyze_diff" takes a path parameter "file_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 turingmind_analyze_diff · inputSchema.properties.file_path
low Unconstrained path parameter "file_path" on "turingmind_store_auto_plan"MTC-CAP-008
Tool "turingmind_store_auto_plan" takes a path parameter "file_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 turingmind_store_auto_plan · inputSchema.properties.file_path
low Unconstrained path parameter "file_path" on "turingmind_get_auto_plans"MTC-CAP-008
Tool "turingmind_get_auto_plans" takes a path parameter "file_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 turingmind_get_auto_plans · inputSchema.properties.file_path
low Unconstrained path parameter "file_path" on "turingmind_apply_edit"MTC-CAP-008
Tool "turingmind_apply_edit" takes a path parameter "file_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 turingmind_apply_edit · inputSchema.properties.file_path
low Unconstrained path parameter "project_path" on "turingmind_bootstrap_codebase"MTC-CAP-008
Tool "turingmind_bootstrap_codebase" takes a path parameter "project_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 turingmind_bootstrap_codebase · inputSchema.properties.project_path
Tools 99
Show each tool and what it can reach · statically extracted from the published source
turingmind_analyze_diffreads sensitive dataturingmind_apply_editreads sensitive dataturingmind_bootstrap_codebasereads sensitive dataturingmind_create_commentnetwork egressturingmind_create_issuenetwork egressturingmind_enable_auto_reviewnetwork egressturingmind_get_auto_plansreads sensitive dataturingmind_get_edit_reasoningreads sensitive dataturingmind_request_code_editreads sensitive dataturingmind_store_auto_planreads sensitive dataturingmind_apply_fixno sensitive capabilityturingmind_apply_spec_deltano sensitive capabilityturingmind_break_down_featureno sensitive capabilityturingmind_bundle_plans_for_commitno sensitive capabilityturingmind_classify_failureno sensitive capabilityturingmind_complete_tdd_cycleno sensitive capabilityturingmind_create_decisionno sensitive capabilityturingmind_create_edit_planno sensitive capabilityturingmind_create_featureno sensitive capabilityturingmind_create_goalno sensitive capabilityturingmind_create_initiativeno sensitive capabilityturingmind_create_spec_nodeno sensitive capabilityturingmind_create_strategic_riskno sensitive capabilityturingmind_create_strategic_specno sensitive capabilityturingmind_define_required_testsno sensitive capabilityturingmind_delete_memoryno sensitive capabilityturingmind_detect_conflictsno sensitive capabilityturingmind_explain_decisionno sensitive capabilityturingmind_generate_specno sensitive capabilityturingmind_generate_verificationno sensitive capabilityturingmind_get_audit_trailno sensitive capabilityturingmind_get_chat_analysis_plansno sensitive capabilityturingmind_get_contextno sensitive capabilityturingmind_get_decision_queueno sensitive capabilityturingmind_get_decision_statsno sensitive capabilityturingmind_get_execution_stateno sensitive capabilityturingmind_get_featureno sensitive capabilityturingmind_get_feature_issuesno sensitive capabilityturingmind_get_goalno sensitive capabilityturingmind_get_impacted_nodesno sensitive capabilityturingmind_get_initiativeno sensitive capabilityturingmind_get_issueno sensitive capabilityturingmind_get_kanban_datano sensitive capabilityturingmind_get_memoryno sensitive capabilityturingmind_get_memory_statsno sensitive capabilityturingmind_get_next_unblocked_issueno sensitive capabilityturingmind_get_pending_decisionsno sensitive capabilityturingmind_get_project_structureno sensitive capabilityturingmind_get_ready_nodesno sensitive capabilityturingmind_get_related_codeno sensitive capabilityturingmind_get_spec_statusno sensitive capabilityturingmind_get_strategic_riskno sensitive capabilityturingmind_get_strategic_specno sensitive capabilityturingmind_get_tdd_statusno sensitive capabilityturingmind_index_codebaseno sensitive capabilityturingmind_ingest_runtime_signalno sensitive capabilityturingmind_initiate_loginno sensitive capabilityturingmind_is_issue_blockedno sensitive capabilityturingmind_link_intentno sensitive capabilityturingmind_list_commentsno sensitive capabilityturingmind_list_featuresno sensitive capabilityturingmind_list_goalsno sensitive capabilityturingmind_list_initiativesno sensitive capabilityturingmind_list_issuesno sensitive capabilityturingmind_list_memoryno sensitive capabilityturingmind_list_spec_nodesno sensitive capabilityturingmind_list_strategic_risksno sensitive capabilityturingmind_list_strategic_specsno sensitive capabilityturingmind_log_reasoningno sensitive capabilityturingmind_mark_test_writtenno sensitive capabilityturingmind_poll_loginno sensitive capabilityturingmind_promote_nodeno sensitive capabilityturingmind_quarantine_ruleno sensitive capabilityturingmind_record_execution_stageno sensitive capabilityturingmind_register_ruleno sensitive capabilityturingmind_request_approvalno sensitive capabilityturingmind_resolve_conflictno sensitive capabilityturingmind_resolve_decisionno sensitive capabilityturingmind_run_verificationno sensitive capabilityturingmind_save_architecture_diagramno sensitive capabilityturingmind_save_memoryno sensitive capabilityturingmind_simulate_impactno sensitive capabilityturingmind_store_chat_analysis_planno sensitive capabilityturingmind_submit_feedbackno sensitive capabilityturingmind_sync_cloudno sensitive capabilityturingmind_sync_codebaseno sensitive capabilityturingmind_test_opengrep_ruleno sensitive capabilityturingmind_update_featureno sensitive capabilityturingmind_update_feature_progressno sensitive capabilityturingmind_update_goalno sensitive capabilityturingmind_update_initiativeno sensitive capabilityturingmind_update_issueno sensitive capabilityturingmind_update_spec_nodeno sensitive capabilityturingmind_update_strategic_riskno sensitive capabilityturingmind_update_strategic_specno sensitive capabilityturingmind_upload_reviewno sensitive capabilityturingmind_validate_authno sensitive capabilityturingmind_validate_tests_passingno sensitive capabilityturingmind_validate_tests_writtenno 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 (99 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
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 |
|---|---|---|---|---|
v0.3.0 latest |
A 93/100 | 19 | 1.8.0 | 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 turingmind-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 Agent MCP server.