"Server Fault" matching MCP servers:

Agent-PLC MCP Server: auto-detect, probe, read, write and diagnose Modbus TCP / FINS / MELSEC / Siemens S7comm PLCs, with transparent proxy and fault-injection listener.

Fault injection and reliability scoring for MCP servers. Scans tool output schemas, injects corrupted payloads, and measures contract enforceability. Model-free, deterministic, no LLM required.

A chaos-engineering and resilience-testing toolkit for Model Context Protocol servers, enabling deterministic fault injection and testing of reliability scenarios.

Enables distributed multi-agent chaos latency injection and fault fuzzing, allowing MCP-compatible clients to inject network faults and retrieve structured execution telemetry.

A tiny MCP server that wraps Perseus Vault to provide persistent, encrypted, local-first memory for OpenAI Codex agents, enabling them to remember project conventions, decisions, and context across sessions.

Lets an AI agent request API keys and passwords from a human through an end-to-end encrypted one-time link and pass them to exactly one command or file, without the value ever entering the agent's context. Can also send secrets as self-destructing links.

Standalone MCP server for Obsidian vaults - hybrid search (FTS5 + vector + cross-encoder reranking), images and PDFs in agent-readable form, Kanban-aware tasks (Tasks-plugin + Dataview formats), structured memory with topic recall, fine-grained read/write tools for optimal token efficiency, and link graph support. Run locally, self-host, or one-click deploy for remote access. OAuth 2.1.

Tells your coding agent which tests to run after a change, and whether a failing test is its fault. Tools: select_tests (only the tests the change can affect, with reasons), triage_failure (new regression, pre-existing, flaky or unknown) and explain. Needs a self-hosted siftwise server; fails open to the full suite. Tested with Claude Code, Copilot, Cursor, Codex and Gemini.

Pull a Figma frame once, then let Claude Code, Codex or any MCP agent read it offline with no rate limits. Six read-only tools serve the normalized node tree, design tokens and locally built SVG icons from a vault you can commit, so teammates need no Figma token.

Mimir is Perseus's external persistent memory backend — a lightweight Rust MCP server that stores cross-session facts so agents remember what they learned last week. Zero network calls, no API keys, just SQLite + FTS5 running alongside your workspace.

A fault-tolerant, stealth-enabled Model Context Protocol (MCP) server for web searching and content fetching. Built for AI Agents (Cursor, Claude Code, OpenCode), it uses a stealth browser engine to fetch pages, dynamically handles SPAs/React, and converts bloat into token-optimized Markdown.

Zero-dependency in-memory PII airgap & reversible masking proxy for Cloud LLMs (GDPR Art. 32 compliant).

A universal MCP server enabling AI assistants to query and manage six database engines (Postgres, Redis, Elasticsearch, MySQL, MongoDB, LDAP) through 113+ tools with read-only safety and fault tolerance.

Provides read-only, stdio-based MCP tools for inspecting locally captured C/C++ fault artifacts, grouping processes and sessions, querying the evidence store, and resolving explicitly supported RPC/IPC relationships. Access is restricted to a configured artifact root, with observed, static-candidate, and unresolved evidence kept strictly separate.

MCP server for DeFi vault discovery, risk analysis and yield data. Query vaults across multiple protocols and chains, compare APY, TVL, risk scores and historical performance.

Enables agents to store and retrieve hierarchical memory in cryptographically partitioned namespaces, with HMAC-based isolation and Ebbinghaus time-decay so recall fades realistically over time. Runs as a zero-dependency Python STDIO MCP server that returns deterministic JSON results.

Enables MCP clients to validate a JSON report definition and render it into a PDF, Excel, Word, HTML, or CSV file written to disk, returning the output path and size rather than the file's bytes. Errors are reported as fixable problems naming the exact path at fault, and all host-level limits stay under the launching host's control.

Enables local zero-knowledge encryption of a personal vault and sanitization of PII such as credentials, credit cards, and addresses before dispatch to cloud LLMs, with client-side rehydration of masked data.

An encrypted, local-first memory server for AI agents that uses SQLite + FTS5 hybrid search, keeping memory off the GPU to maximize HBM for inference.

Enables AI agents to manage ephemeral payment tokens with cryptographic spend mandates, risk scoring, catalog resolution, and automated bargaining through native MCP tools.