Duckdb Mcp Native MCP Server
@seed-ship/duckdb-mcp-native
npm
v1.6.0
Published by @seed-ship — 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.
Native Node.js/TypeScript implementation of DuckDB MCP extension
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 − 11 = 89. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −11 | Untrusted input concatenated into a command sink ×3 MTC-SRC-009 | injection |
2. Client adoption risk — 89 − 7 = 82. 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 Shell/command execution in server code (dist/compute-session.js)MTC-SRC-002
In the server's implementation (`dist/compute-session.js:100`): 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: on: true, async exec(sql, params) { const start = Date.now(); try { retu
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 dist/compute-session.js
high Shell/command execution in server code (dist/federation/QueryRouter.js)MTC-SRC-002
In the server's implementation (`dist/federation/QueryRouter.js:238`): 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: ; await exec(sql); } finally { try { await f
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 dist/federation/QueryRouter.js
high Shell/command execution in server code (dist/utils/connection-reset.js)MTC-SRC-002
In the server's implementation (`dist/utils/connection-reset.js:1`): 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: port { execSync } from 'child_process'; import { logger } from './logger.js'; export class ConnectionReset { activeC
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 dist/utils/connection-reset.js
medium Untrusted input concatenated into a command sink (dist/tools/ducklake-tools.js)MTC-SRC-009
In the server's implementation (`dist/tools/ducklake-tools.js:319`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: result = await session.exec(`${queryWithTempTable} LIMIT ${input.limit}`); // Clean up
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 dist/tools/ducklake-tools.js
medium Untrusted input concatenated into a command sink (dist/tools/graph-export.js)MTC-SRC-009
In the server's implementation (`dist/tools/graph-export.js:46`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ; await session.exec(`COPY (SELECT * FROM ${nodeTable}) TO ${escapeString(nodesPath)} (FORMAT JSON)`); a
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/tools/graph-export.js
medium Untrusted input concatenated into a command sink (dist/utils/connection-reset.js)MTC-SRC-009
In the server's implementation (`dist/utils/connection-reset.js:104`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const pid = execSync(`lsof -ti :${port} 2>/dev/null || true`, { encoding: 'utf-8',
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 dist/utils/connection-reset.js
medium Dynamic module load from a non-literal (dist/federation/ResourceRegistry.js)MTC-SRC-005
In the server's implementation (`dist/federation/ResourceRegistry.js:218`): 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: persistence */ import(data) { this.clearAll(); // Restore resources for (const [key, re
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 dist/federation/ResourceRegistry.js
low Shell/command execution in packaging/dev tooling (scripts/port-manager.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/port-manager.js:3`): 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: execSync, spawn } from 'child_process' import net from 'net' /** * Port Management Utility * Handles port cleanup, pr
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/port-manager.js
Tools 30
Each tool and what it can reach — statically extracted from the published source.
federate_queryreads sensitive dataqueryreads sensitive dataquery_duckdbreads sensitive dataquery_hybridreads sensitive dataanalyze_datano sensitive capabilityattach_mcpno sensitive capabilitycatalog_nameno sensitive capabilitychecksno sensitive capabilitycolumnsno sensitive capabilitycreate_virtual_tableno sensitive capability
Show 20 more tools ↓
data_quality_checkno sensitive capabilitydescribe_tableno sensitive capabilitydetach_mcpno sensitive capabilitydrop_virtual_tableno sensitive capabilityducklake_time_travelno sensitive capabilityducklake.attachno sensitive capabilityducklake.snapshotsno sensitive capabilityducklake.time_travelno sensitive capabilitylist_attached_serversno sensitive capabilitylist_mcp_resourcesno sensitive capabilitylist_tablesno sensitive capabilitylist_virtual_tablesno sensitive capabilityload_csvno sensitive capabilityload_parquetno sensitive capabilitymigrate_to_ducklakeno sensitive capabilityoptimize_queryno sensitive capabilityrefresh_virtual_tableno sensitive capabilitysource_pathno sensitive capabilitytable_nameno sensitive capabilitytimestampno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (30 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 |
|---|---|---|---|---|
v1.6.0 latest |
B 82/100 | 8 | 1.13.0 | 2026-09-07 |
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 @seed-ship/duckdb-mcp-native --onlineMore in Analytics & Monitoring
Public-safe MCP admin discovery contract descriptors and response builders.
Pokemon Champions battle advisor MCP server
Airflow MCP server — DAG list, runs, task instances, log tails, trigger and clear over the Airflow REST API
MCP analytics wrapper SDK that instruments MCP tool declarations with telemetry.
AI-ready GIS, geofencing, DataSynch, CRM, inventory, routing, APIs, telemetry and workflows.
AI-native social listening. Monitor buying signals and run GTM workflows via natural language.