Meridian (KNambiarDJsc) MCP Server
meridian-mcp
PyPI
v0.6.22
Published by knambiardjsc — 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.
Meridian — Local-first AI compliance scanner. DPDPA 2023 · RBI FREE-AI · SEBI AI/ML · EU AI Act. Works with any LLM provider. AST-level code analysis across Python, TypeScript, Go, Java.
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 12
high Shell/command execution in server code (src/meridian/context/builder.py)MTC-SRC-002
In the server's implementation (`src/meridian/context/builder.py:154`): 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( ["git", "rev-parse", "HEAD"], cwd=repository_path, captu
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/meridian/context/builder.py
high Shell/command execution in server code (src/meridian/ledger.py)MTC-SRC-002
In the server's implementation (`src/meridian/ledger.py:567`): 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: olve() result = subprocess.run( ["git", "-C", str(p), "rev-parse", "--show-toplevel"], 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/meridian/ledger.py
high Shell/command execution in server code (src/meridian/remote_clone.py)MTC-SRC-002
In the server's implementation (`src/meridian/remote_clone.py:173`): 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(cmd, capture_output=True, text=True, timeout=timeout_seconds, env=env) except
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/meridian/remote_clone.py
high Shell/command execution in server code (src/meridian/report/pdf_exporter.py)MTC-SRC-002
In the server's implementation (`src/meridian/report/pdf_exporter.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: setup)...") subprocess.run([sys.executable, "-m", "playwright", "install", "chromium"], check=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/meridian/report/pdf_exporter.py
high Shell/command execution in server code (src/meridian/scan_ledger/scan_history.py)MTC-SRC-002
In the server's implementation (`src/meridian/scan_ledger/scan_history.py:83`): 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( ["git", "-C", str(resolved), "rev-parse", "--show-toplevel"],
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/meridian/scan_ledger/scan_history.py
low Hardcoded egress to an external endpoint in packaging/dev tooling (tests/test_assessment_e2e.py)MTC-SRC-003
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_assessment_e2e.py:109`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. 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" " requests.get('https://api.example.com/data')\n" " return {'email': '[email protected]'}\n"
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_assessment_e2e.py
low Hardcoded egress to an external endpoint in packaging/dev tooling (tests/test_context_builder_e2e.py)MTC-SRC-003
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_context_builder_e2e.py:33`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: file():\n" " requests.get('https://api.example.com/data')\n" " return {'email': '[email protected]'}\n"
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_context_builder_e2e.py
low Hardcoded egress to an external endpoint in packaging/dev tooling (tests/test_engine_e2e.py)MTC-SRC-003
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_engine_e2e.py:33`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: file():\n" " requests.get('https://api.example.com/data')\n" " return {'email': '[email protected]'}\n"
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_engine_e2e.py
low Hardcoded egress to an external endpoint in packaging/dev tooling (tests/test_interpreter_prompt_builder.py)MTC-SRC-003
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_interpreter_prompt_builder.py:29`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. 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" " requests.get('https://api.example.com/data')\n" " return {'email': '[email protected]'}\n"
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_interpreter_prompt_builder.py
low Hardcoded egress to an external endpoint in packaging/dev tooling (tests/test_report_builder_and_exporters.py)MTC-SRC-003
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_report_builder_and_exporters.py:236`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. 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" " requests.get('https://api.example.com/data')\n" " return {'email': '[email protected]'}\n"
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_report_builder_and_exporters.py
low Shell/command execution in packaging/dev tooling (tests/test_assessment_boundary.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_assessment_boundary.py:107`): 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: args: str) -> None: subprocess.run( ["git", "-C", str(repo), *args], check=True, 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 tests/test_assessment_boundary.py
low Shell/command execution in packaging/dev tooling (tests/test_cli.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_cli.py:656`): 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: ONPATH", "") proc = subprocess.run( [sys.executable, "-c", code], capture_output=True, env=env, timeout=120
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_cli.py
Tools 14
Each tool and what it can reach — statically extracted from the published source.
ai_governance_summaryno sensitive capabilitycompare_scansno sensitive capabilitycontinue_scanno sensitive capabilityexplain_controlno sensitive capabilitygenerate_reportno sensitive capabilityget_findingno sensitive capabilityrepository_profileno sensitive capabilityrepository_summaryno sensitive capabilityrisk_summaryno sensitive capabilityscan_repositoryno sensitive capability
Show 4 more tools ↓
scan_repository_from_urlno sensitive capabilitystart_scanno sensitive capabilitystart_scan_from_urlno sensitive capabilitytechnology_inventoryno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (14 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 10
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 |
|---|---|---|---|---|
v0.6.22 latest |
A 93/100 | 12 | 1.13.0 | 2026-08-25 |
v0.6.21 |
A 93/100 | 11 | 1.12.1 | 2026-08-19 |
v0.6.20 |
A 93/100 | 10 | 1.12.1 | 2026-08-18 |
v0.6.19 |
A 93/100 | 10 | 1.12.1 | 2026-08-16 |
v0.6.16 |
A 93/100 | 10 | 1.12.1 | 2026-08-10 |
Show 5 more versions ↓
v0.6.15 |
A 93/100 | 8 | 1.12.1 | 2026-08-09 |
v0.6.14 |
A 93/100 | 8 | 1.12.1 | 2026-08-07 |
v0.6.13 |
A 93/100 | 8 | 1.12.1 | 2026-08-04 |
v0.6.12 |
A 93/100 | 9 | 1.12.1 | 2026-07-27 |
v0.6.11 |
A 93/100 | 10 | 1.10.0 | 2026-07-25 |
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 meridian-mcp --online --registry pypiOther implementations of Meridian 1
Independent packages implementing the same tool, scanned with the same engine. Compare all 2 side by side →
More in Business & CRM
Free public tax reference data — GST/VAT, income, company and capital-gains tax rules for 50+ countries.
The approval gate for unattended UCP buying agents — a policy/approval MCP proxy in front of a merchant's UCP checkout endpoint.
Autotask PSA MCP server. Generic entity query/get/create/update across the full REST API plus convenience tools for tickets, companies, contacts, projects, tasks and time entries. AI-safe with readonly mode and destructive-action confirmation. stdio + opt
MCP server for B2C Commerce developer experience tools
Search, compare and contact real-world companies through a public MCP business directory.
Norwegian business register (Brønnøysundregistrene) as an MCP server — companies, roles, subunits and annual accounts, with the register's silent traps encoded as guards.