Semahash MCP Server
semahash
PyPI
v0.5.5
Published by emergent-wisdom — 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.
Content-addressed semantics for multi-agent coordination. When the hash is the word.
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 6
high Dynamic evaluation of a non-literal value (src/sema/server/static/assets/GraphPage-2VgYBBGA.js)MTC-SRC-010
In the server's implementation (`src/sema/server/static/assets/GraphPage-2VgYBBGA.js:4056`): Evaluating a runtime value as code (rather than a fixed literal) executes whatever reaches it — a direct RCE primitive, and almost never necessary in legitimate 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: ){let o=t(s,a),{Body:l}=new Function(o)();return l}function t(s,a){return` ${r(s,a)} ${n(s)} return {Body: Body, Vector:
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/sema/server/static/assets/GraphPage-2VgYBBGA.js
high Dynamic code execution in server code (src/sema/server/static/assets/GraphPage-2VgYBBGA.js)MTC-SRC-001
In the server's implementation (`src/sema/server/static/assets/GraphPage-2VgYBBGA.js:4056`): 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: ){let o=t(s,a),{Body:l}=new Function(o)();return l}function t(s,a){return` ${r(s,a)} ${n(s)} return {Body: Body, Vector:
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/sema/server/static/assets/GraphPage-2VgYBBGA.js
high Shell/command execution in server code (src/sema/audit/runner.py)MTC-SRC-002
In the server's implementation (`src/sema/audit/runner.py:33`): 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: axonomy.db") proc = subprocess.run( [sys.executable, "-m", module], capture_output=True, 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 src/sema/audit/runner.py
medium Dynamic module load from a non-literal (src/sema/server/static/assets/chunk-QFMPRPBF-DgVX359w.js)MTC-SRC-005
In the server's implementation (`src/sema/server/static/assets/chunk-QFMPRPBF-DgVX359w.js:5`): 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: t[e.id];try{let r=await import(e.module);return t[e.id]=r,r}catch(r){return console.error(`Error loading route module \`
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/sema/server/static/assets/chunk-QFMPRPBF-DgVX359w.js
low Shell/command execution in packaging/dev tooling (src/sema/core/tests/test_libraries.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`src/sema/core/tests/test_libraries.py:280`): 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: r, second_dir): subprocess.run( [ sys.executable, str(script),
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/sema/core/tests/test_libraries.py
low Shell/command execution in packaging/dev tooling (src/sema/mcp/tests/test_mcp_pull.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`src/sema/mcp/tests/test_mcp_pull.py:40`): 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: ols)))" ) out = subprocess.check_output([sys.executable, "-c", code], env=env, text=True) return set(out.str
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/sema/mcp/tests/test_mcp_pull.py
Tools 13
Each tool and what it can reach — statically extracted from the published source.
sema_searchingests untrusted inputsema_graph_skeletonno sensitive capabilitysema_handshakeno sensitive capabilitysema_lookupno sensitive capabilitysema_propose_contextno sensitive capabilitysema_reset_sessionno sensitive capabilitysema_resolveno sensitive capabilitysema_rootno sensitive capabilitysema_statsno sensitive capabilitysema_treeno sensitive capability
Show 3 more tools ↓
sema_useno sensitive capabilitysema_validateno sensitive capabilitysema_verify_contextno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (13 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 6
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 |
|---|---|---|---|---|
v0.5.5 latest |
A 93/100 | 6 | 1.13.0 | 2026-09-07 |
v0.5.3 |
A 93/100 | 6 | 1.13.0 | 2026-08-25 |
v0.5.1 |
A 93/100 | 6 | 1.12.1 | 2026-08-21 |
v0.5.0 |
A 93/100 | 6 | 1.12.1 | 2026-08-13 |
v0.4.0 |
A 93/100 | 5 | 1.12.1 | 2026-08-05 |
Show 1 more version ↓
v0.3.0 |
A 93/100 | 4 | 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 semahash --online --registry pypiMore in AI, Memory & Reasoning
FDA device & vehicle recall risk for AI agents: recall history, MAUDE trend, risk score.
Open-source MCP server exposing Agent402.Tools' catalog — 500+ strong: 400+ self-hostable tools + 100 multi-tool skill packs (security-audit, trend-analysis, structured-scrape, decode-blob, forecasting-bake-off) for AI agents — browser, web search & answe
Zero-dependency MCP server that gives AI agents a self-updating project memory in AGENTS.md. Returns merge instructions instead of mutating state, so every change is a reviewable diff.
MCP Apps UI resources and server helpers for n8n
MCP server providing comprehensive access to BookStack knowledge management system
MCP server for tracking achievements with STAR methodology