MCP servers that fail: no install/post-install scripts
409 of the 14,628 Model Context Protocol servers where this control could be evaluated fail it — that is 3% of the evaluated corpus on the Canopii Trust Index.
- Servers failing
- 409
- Failure rate
- 3%
- Average score when failing
- 58/100
Why this matters
install hooks run arbitrary code on every consumer at install time.
How to pass it
Remove preinstall/install/postinstall scripts, or document and minimize them.
Control id supply.no_install_scripts — a guard control, so a confirmed failure caps the server's score at the medium ceiling no matter what else passes.
Affected servers
Each server's own page shows the evidence behind this result.
Your MAX account and bots for agents: read, search, send messages. Sign in with the max CLI first.
Your WhatsApp account for agents: read, search and send messages. Sign in with the wa CLI first.
Your Telegram account for agents: read, search and send messages. Sign in with the tg CLI first.
Give your AI agents trusted access to the full Postman platform.
People's context across messengers, notes and mail, from a local store. Set up the memo CLI first.
Provides AI assistants with direct access to Mapbox developer APIs and documentation.
minia2a.uk — x402 pay-per-call APIs for AI agents, USDC on Base, 5 free trials per wallet.
D2L Brightspace MCP server: grades, due dates, assignments, announcements and files. Any school.
Enforce brand writing guidelines in Claude Code — PostToolUse hook + MCP server
MCP server for terminal commands, file operations, and process management
BuildPulse CI test analytics for AI agents — flaky tests, CI failures, flakiness, and code coverage.
Pass the baton between coding agents: convert sessions across Claude Code, OpenCode, Codex & more.
Reasoning-based RAG system for chatting with long PDFs. Supports local and online files.
Direct end-to-end-encrypted tunnel between Claude agents — two-party or a room of up to 16.
Qatari legislation via MCP — full-text search across statutes and provisions
Serbian legislation via MCP — full-text search across statutes and provisions
AI design fidelity — compare Figma designs or screenshots against rendered UI. No API keys.
Italian legislation via MCP — full-text search across statutes and provisions
Let AI agents use secrets without seeing them: inject into a command, redact the output.
Chilean legislation via MCP — full-text search across statutes and provisions
UK legislation via MCP — full-text search across statutes and provisions
Play DOOM via MCP - works with Claude Code, Cursor, and any MCP client
Persistent code indexing for AI assistants. 50x less context than grep. 11 languages.
Agent orchestration platform - multi-agent spawning, tickets, boards, and workflows
Capture, replay, and debug failures with portable, executable bug artifacts
MCP server exposing Spinnaker CD platform via Gate API for pipeline and deployment management
French legislation via MCP — full-text search across statutes and provisions
Cryptographic identity, delegation, governance, and commerce for AI agents. 152 tools.
Free web search and long-term memory for AI assistants. No API keys; data stays local.
Japan legislation via MCP — full-text search across statutes and provisions
Cypriot legislation via MCP — full-text search across statutes and provisions
Egyptian legislation via MCP — full-text search across statutes and provisions
Clearotron — trademark clearance that shows its work
Easily find and fix security issues in your applications leveraging Snyk platform capabilities.
Rust code index MCP server, native 1C:Enterprise (BSL) support. 37 tools, AST for 14 languages.
Saudi legislation via MCP — full-text search across statutes and provisions
Brazil legislation via MCP — full-text search across statutes and provisions
Secure, self-hosted New Relic observability and administration tools for MCP clients
Control and verify a live Unity Editor through a local, low-token MCP server.
Secure, expiring artifact storage and handoff for AI agents.
MCP security scanner. CI-native testing, attack simulation, health scoring, and SARIF.
Multi-agent orchestration for Claude Code — consensus review, adaptive dispatch, skill learning
Native macOS markdown preview with MCP server for Claude Code. Swift/SwiftUI, no Electron.
Uruguayan legislation via MCP — full-text search across statutes and provisions
Local-first, LLM-agnostic memory layer for AI assistants.
AI Agent Astrology — natal charts, transits, cosmic weather, and forecasts for AI agents.
MCP server bridging GenieACS TR-069 ACS instances to LLMs for CPE device management
Georgian legislation via MCP — full-text search across statutes and provisions
Taiwanese legislation via MCP — full-text search across statutes and provisions
Peruvian legislation via MCP — full-text search across statutes and provisions
Mexican legislation via MCP — full-text search across statutes and provisions
Austrian federal legislation — statutes and EU cross-references via MCP
MCP server for CashPilot: track passive income and DePIN earnings, manage services
Context optimization for LLM agents: tool registry, result masking, budgeting, compaction.
Colombian legislation via MCP — full-text search across statutes and provisions
MCP bridge for autonomous x402 payments in HPP USDC.e — discover and pay for services per call.
Sends the same prompt to multiple LLM providers in parallel and returns a divergence score via MCP.
Costa Rican legislation via MCP — full-text search across statutes and provisions
Jamaican legislation via MCP — full-text search across statutes and provisions
Geospatial intelligence with Mapbox APIs like geocoding, POI search, directions, isochrones, etc.
Irish legislation via MCP — full-text search across statutes and provisions
Task management for AI coding agents — CQRS 2-gateway pattern, 200 ops across 10 domains
Luxembourg legislation via MCP — full-text search across statutes and provisions
Obsidian MCP server: semantic search, knowledge graph, and vault editing. No plugin required.
MCP server for Scrivener: read, write, analyze, and search your manuscripts with AI assistants.
Pakistani legislation via MCP — full-text search across statutes and provisions
Multi-cloud cost, inventory and waste analysis over MCP: AWS, GCP, Cloudflare and OVH.
Real eyes and hands on the web for AI agents. MCP-first. Local-first. Vendor-agnostic.
Hebbian memory for AI agents. Learns file patterns, predicts next tools, saves tokens.
Budna marketplace discovery and account access for AI assistants, with permissions you control.
Hermai MCP server — look up, submit, and classify website API schemas from any MCP client.
MemoryIndustry persistent memory MCP server: BM25+MMR retrieval and audit.
Auditable memory for coding agents: evidence chains, supersession history, keyless embedded SQLite
Query Slovenian statutes, court decisions, EU cross-references, and parliamentary materials
Playwright browser & Node.js MCP. ARIA refs, screenshots, ref-based interactions.
Indexes codebase into a local knowledge graph with 40+ AI tools and codebase-guard.
Persistent memory MCP server. 28 tools, BM25+MMR+OOD retrieval, tamper-evident audit, code graph.
Secure credential vault for AI agents. Store, manage, and audit API keys locally.
Record any browser page as GIF or video via MCP
Belgian legislation via MCP — full-text search across statutes and provisions
Track AI agent costs, detect waste, optimize models, and prove ROI. 23 MCP tools across 10 domains.
Control fleets of remote machines via AI agents: exec, files, git, fleet ops, map/reduce.
Pi agent teams on any provider: parallel delegates, forks, MCP tools; runs built to finish.
Cryptographic identity, delegation, governance, and commerce for AI agents. 154 tools.
A zero-LLM MCP server that replays recorded site maps instead of re-exploring browser routes.
Safe cross-OS desktop control for any AI agent - the fallback execution layer.
Trainable non-fiction writing voice, presets, and an anti-AI-tells audit for Claude, via MCP.
Drop-in fetch MCP: clean Markdown from any URL, with JS rendering and anti-bot.
Structural code intelligence over MCP: symbols, callers, imports and blast radius, 40+ languages.
Search CuddlyNest hotels and read rooms, prices, availability and cancellation policies
Constitutional-AI safety guardrails for any LLM — personas, constitutions, adjudication.
MCP server for iCloud (Apple) Calendar access via CalDAV
Catch bad animations before they ship. Deterministic motion audit + vision-LLM design review.
Search and query HackTricks pentesting documentation with quick lookup and section extraction
AI infrastructure cartographer & MCP server: fingerprints, graphs & watches live infra for agents
Task queue, decisions and memory for coding agents. Local SQLite, no network. Requires Bun.
Vet a package (CVEs, license, maintenance) before your AI agent uses it, plus capability discovery.
Norwegian legislation via MCP — full-text search across statutes and provisions
Icelandic legislation via MCP — full-text search across statutes and provisions
IBM Quantum OpenQASM 2.0 MCP — list backends, submit QASM, poll jobs, get histograms.
This control is one of 32 in the published rubric — see how scoring works or how the ecosystem fails every other control.