Midnight MCP Server
midnight-mcp
npm
v0.3.0
Published by olanetsoft — 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.
[DEPRECATED — migrate to Kapa + Midnight Expert: https://docs.midnight.network/blog/migrating-to-kapa-and-midnight-expert] Model Context Protocol Server for Midnight Blockchain Development
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 − 15.4 = 85. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −15.4 | Shell command embedded in tool metadata MTC-INJ-CMD-1 | injection |
2. Client adoption risk — 85 − 4 = 81. 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 |
|---|---|
| −3 | capability blast radius (moderate) — 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 2
high Shell command embedded in tool metadataMTC-INJ-CMD-1
Shell command embedded in tool metadata detected in the description of tool "midnight-auto-update-config". Instruction-like content in tool metadata is executed by the model, not the human, and is the primary tool-poisoning vector.
Evidence: rm -rf
Fix: Tool descriptions should describe behavior, not instruct the assistant. Treat imperative / secrecy / sequencing language in metadata as hostile.
Location: tool midnight-auto-update-config · description
medium Hardcoded egress to an external endpoint (dist/chunk-VBZPDFKP.js)MTC-SRC-003
In the server's implementation (`dist/chunk-VBZPDFKP.js:9462`): 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: const response = await fetch( "https://registry.npmjs.org/midnight-mcp/latest" ); if (!response.ok) {
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/chunk-VBZPDFKP.js
Tools 89
Each tool and what it can reach — statically extracted from the published source.
midnight-fetch-docsingests untrusted inputAccess Control Patternno sensitive capabilityapproachesno sensitive capabilityassertno sensitive capabilityBasic Contract Templateno sensitive capabilityBulletin Boardno sensitive capabilityBulletin Board Exampleno sensitive capabilityCompact AST Schemano sensitive capabilityCompact Language Referenceno sensitive capabilitycomplexityno sensitive capability
Show 79 more tools ↓
conceptno sensitive capabilitycontractCodeno sensitive capabilitycontractTypeno sensitive capabilityCounterno sensitive capabilityCounter Exampleno sensitive capabilitydefaultno sensitive capabilitydiscloseno sensitive capabilityDocumentationno sensitive capabilityerrorMessageno sensitive capabilityExample Contractsno sensitive capabilityfocusAreasno sensitive capabilityHash Functionsno sensitive capabilitylevelno sensitive capabilityMidnight Bankno sensitive capabilitymidnight-analyze-contractno sensitive capabilitymidnight-auto-update-configno sensitive capabilitymidnight-check-breaking-changesno sensitive capabilitymidnight-check-versionno sensitive capabilitymidnight-compare-syntaxno sensitive capabilitymidnight-compile-contractno sensitive capabilitymidnight-document-contractno sensitive capabilitymidnight-explain-circuitno sensitive capabilitymidnight-extract-contract-structureno sensitive capabilitymidnight-generate-contractno sensitive capabilitymidnight-get-fileno sensitive capabilitymidnight-get-file-at-versionno sensitive capabilitymidnight-get-latest-syntaxno sensitive capabilitymidnight-get-latest-updatesno sensitive capabilitymidnight-get-migration-guideno sensitive capabilitymidnight-get-repo-contextno sensitive capabilitymidnight-get-statusno sensitive capabilitymidnight-get-update-instructionsno sensitive capabilitymidnight-get-version-infono sensitive capabilitymidnight-health-checkno sensitive capabilitymidnight-list-category-toolsno sensitive capabilitymidnight-list-examplesno sensitive capabilitymidnight-list-tool-categoriesno sensitive capabilitymidnight-mcpno sensitive capabilitymidnight-new-mcpno sensitive capabilitymidnight-review-contractno sensitive capabilitymidnight-search-compactno sensitive capabilitymidnight-search-docsno sensitive capabilitymidnight-search-typescriptno sensitive capabilitymidnight-suggest-toolno sensitive capabilitymidnight-upgrade-checkno sensitive capabilitymidnight:compare-approachesno sensitive capabilitymidnight:create-contractno sensitive capabilitymidnight:debug-contractno sensitive capabilitymidnight:explain-conceptno sensitive capabilitymidnight:review-contractno sensitive capabilityNullifier Patternno sensitive capabilityOpenZeppelin Access Controlno sensitive capabilityOpenZeppelin Contracts for Compactno sensitive capabilityOpenZeppelin FungibleTokenno sensitive capabilityOpenZeppelin Securityno sensitive capabilitypadno sensitive capabilitypersistentCommitno sensitive capabilitypersistentHashno sensitive capabilityPrivacy-Preserving Patternno sensitive capabilityprivacyLevelno sensitive capabilityproblemno sensitive capabilityProof Schemano sensitive capabilitypublic_keyno sensitive capabilityrandomno sensitive capabilityreentrancy-exampleno sensitive capabilityRepository Codeno sensitive capabilitySchema Definitionsno sensitive capabilitySimple Counterno sensitive capabilityState Management Patternno sensitive capabilitytemplate-contractno sensitive capabilityToken Templateno sensitive capabilityTokenomics Summaryno sensitive capabilitytokenomics-projectno sensitive capabilityTransaction Schemano sensitive capabilityTypeScript SDK APIno sensitive capabilityverify_signatureno sensitive capabilityVoting Templateno sensitive capabilityWallet Integration Guideno sensitive capabilityzswap-exampleno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (89 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 |
|---|---|---|---|---|
v0.3.0 latest |
B 81/100 | 2 | 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 midnight-mcp --onlineMore 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