Total Agent Memory MCP Server
total-agent-memory
PyPI
v12.4.0
Published by vbcherepanov — 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 − 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 23
critical Completed toxic-flow trifecta across toolsMTC-FLOW-002
This server (without client built-ins) exposes a complete data-exfiltration chain: memory_get → memory_perf_report → memory_eval_contradictions. Untrusted input is ingested, private data is read, and it can be sent to an external sink via the agent composing the tools (→). 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 memory_get → memory_perf_report → memory_eval_contradictions
high Tool "memory_eval_locomo" exposes command/code executionMTC-CAP-001
Tool "memory_eval_locomo" 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 memory_eval_locomo
high Tool "memory_eval_recall" exposes command/code executionMTC-CAP-001
Tool "memory_eval_recall" 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 memory_eval_recall
high Tool "memory_eval_temporal" exposes command/code executionMTC-CAP-001
Tool "memory_eval_temporal" 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 memory_eval_temporal
high Tool "memory_eval_entity_consistency" exposes command/code executionMTC-CAP-001
Tool "memory_eval_entity_consistency" 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 memory_eval_entity_consistency
high Tool "memory_eval_contradictions" exposes command/code executionMTC-CAP-001
Tool "memory_eval_contradictions" 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 memory_eval_contradictions
high Tool "memory_eval_long_context" exposes command/code executionMTC-CAP-001
Tool "memory_eval_long_context" 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 memory_eval_long_context
high Shell/command execution in server code (src/dashboard.py)MTC-SRC-002
In the server's implementation (`src/dashboard.py:811`): 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: try: result = subprocess.run( ["launchctl", "list"], capture_output=True, text=True, t
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/dashboard.py
high Shell/command execution in server code (src/reflection/scheduler.py)MTC-SRC-002
In the server's implementation (`src/reflection/scheduler.py:218`): 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: = "1" result = subprocess.run( [OLLAMA_BIN, "run", model, prompt], 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 src/reflection/scheduler.py
high Shell/command execution in server code (src/server.py)MTC-SRC-002
In the server's implementation (`src/server.py:6828`): 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: try: return subprocess.check_output( ["git", "rev-parse", "--abbrev-ref", "HEAD"], s
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/server.py
high Shell/command execution in server code (src/tools/brain_autonomy.py)MTC-SRC-002
In the server's implementation (`src/tools/brain_autonomy.py:57`): 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: = "1" result = subprocess.run( [OLLAMA_BIN, "run", model, prompt], 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 src/tools/brain_autonomy.py
high Shell/command execution in server code (src/tools/brain_health.py)MTC-SRC-002
In the server's implementation (`src/tools/brain_health.py:57`): 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: try: proc = subprocess.run( ["launchctl", "list"], 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 src/tools/brain_health.py
high Shell/command execution in server code (src/tools/check_updates.py)MTC-SRC-002
In the server's implementation (`src/tools/check_updates.py:63`): 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: n None try: subprocess.run( ["git", "fetch", "--tags", "--quiet"], cwd=ROOT, check=True, timeout
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/tools/check_updates.py
high Shell/command execution in server code (src/tools/cross_project.py)MTC-SRC-002
In the server's implementation (`src/tools/cross_project.py:132`): 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: = "1" result = subprocess.run( [OLLAMA_BIN, "run", model, prompt], 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 src/tools/cross_project.py
high Shell/command execution in server code (src/tools/git_observer.py)MTC-SRC-002
In the server's implementation (`src/tools/git_observer.py:136`): 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: = "1" result = subprocess.run( [OLLAMA_BIN, "run", model, prompt], 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 src/tools/git_observer.py
high Shell/command execution in server code (src/tools/idea_engine.py)MTC-SRC-002
In the server's implementation (`src/tools/idea_engine.py:78`): 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: = "1" result = subprocess.run( [OLLAMA_BIN, "run", model, prompt], 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 src/tools/idea_engine.py
high Shell/command execution in server code (src/tools/improve_search.py)MTC-SRC-002
In the server's implementation (`src/tools/improve_search.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: try: result = subprocess.run( ["/usr/local/bin/ollama", "list"], 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 src/tools/improve_search.py
low Mutating tool "memory_eval_locomo" declares no destructiveHintMTC-CAP-005
Tool "memory_eval_locomo" 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 memory_eval_locomo
low Mutating tool "memory_eval_recall" declares no destructiveHintMTC-CAP-005
Tool "memory_eval_recall" 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 memory_eval_recall
low Mutating tool "memory_eval_temporal" declares no destructiveHintMTC-CAP-005
Tool "memory_eval_temporal" 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 memory_eval_temporal
low Mutating tool "memory_eval_entity_consistency" declares no destructiveHintMTC-CAP-005
Tool "memory_eval_entity_consistency" 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 memory_eval_entity_consistency
low Mutating tool "memory_eval_contradictions" declares no destructiveHintMTC-CAP-005
Tool "memory_eval_contradictions" 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 memory_eval_contradictions
low Mutating tool "memory_eval_long_context" declares no destructiveHintMTC-CAP-005
Tool "memory_eval_long_context" 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 memory_eval_long_context
Tools 74
Each tool and what it can reach — statically extracted from the published source.
memory_eval_contradictionsruns code / shellmemory_eval_entity_consistencyruns code / shellmemory_eval_locomoruns code / shellmemory_eval_long_contextruns code / shellmemory_eval_recallruns code / shellmemory_eval_temporalruns code / shellmemory_getingests untrusted inputmemory_perf_reportreads sensitive datamemory_timelineingests untrusted inputanalogizeno sensitive capability
Show 64 more tools ↓
benchmarkno sensitive capabilityclassify_taskno sensitive capabilityfile_contextno sensitive capabilityingest_codebaseno sensitive capabilitykg_add_factno sensitive capabilitykg_atno sensitive capabilitykg_invalidate_factno sensitive capabilitykg_timelineno sensitive capabilitylearn_errorno sensitive capabilitylist_intentsno sensitive capabilitymemory_associateno sensitive capabilitymemory_conceptsno sensitive capabilitymemory_consolidateno sensitive capabilitymemory_consolidate_statusno sensitive capabilitymemory_context_buildno sensitive capabilitymemory_deleteno sensitive capabilitymemory_entity_resolveno sensitive capabilitymemory_episode_recallno sensitive capabilitymemory_episode_saveno sensitive capabilitymemory_explain_searchno sensitive capabilitymemory_exportno sensitive capabilitymemory_extract_sessionno sensitive capabilitymemory_forgetno sensitive capabilitymemory_graphno sensitive capabilitymemory_graph_indexno sensitive capabilitymemory_graph_statsno sensitive capabilitymemory_historyno sensitive capabilitymemory_observeno sensitive capabilitymemory_rebuild_embeddingsno sensitive capabilitymemory_rebuild_ftsno sensitive capabilitymemory_recallno sensitive capabilitymemory_recall_iterativeno sensitive capabilitymemory_reflect_nowno sensitive capabilitymemory_relateno sensitive capabilitymemory_saveno sensitive capabilitymemory_save_fastno sensitive capabilitymemory_search_by_tagno sensitive capabilitymemory_search_fastno sensitive capabilitymemory_self_assessno sensitive capabilitymemory_skill_getno sensitive capabilitymemory_skill_updateno sensitive capabilitymemory_statsno sensitive capabilitymemory_temporal_queryno sensitive capabilitymemory_updateno sensitive capabilitymemory_warmupno sensitive capabilitymemory_wiki_generateno sensitive capabilityphase_transitionno sensitive capabilityrule_set_phaseno sensitive capabilitysave_decisionno sensitive capabilitysave_intentno sensitive capabilitysearch_intentsno sensitive capabilityself_error_logno sensitive capabilityself_insightno sensitive capabilityself_patternsno sensitive capabilityself_reflectno sensitive capabilityself_rulesno sensitive capabilityself_rules_contextno sensitive capabilitysession_endno sensitive capabilitysession_initno sensitive capabilitytask_createno sensitive capabilitytask_phases_listno sensitive capabilityworkflow_learnno sensitive capabilityworkflow_predictno sensitive capabilityworkflow_trackno 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 (74 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 |
|---|---|---|---|---|
v12.4.0 latest |
B 89/100 | 23 | 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 total-agent-memory --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.