AI & Agent Tools MCP Servers

Convert PDFs and other documents to structured formats via Docling, for AI applications.

Phone-first local dev MCP for Claude Code and Codex: install Yaver, pair mobile, run, build, deploy.

Zotero MCP server: preview-first, journaled writes and keyless local reads for AI agents.

Agent eXoskeleton Framework control plane for workspace-native agent capabilities over MCP.

Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.

Acquisition.gov FAR Overhaul model parts, agency deviations, PDFs, and guidance. 5 tools.

MCP server for mobile app automation: verify, control, and debug iOS, Android, TV, and desktop apps

React/React Native codebase analysis for AI agents — 34 free MCP tools, local-only.

Publish versioned agent skills to a team-scoped registry, track drift, and deprecate stale ones.

A sandboxed, agentic workspace providing secure filesystem, bash, and uv-powered Python execution.

Find and buy x402 agent readiness, vendor risk, transaction, and company intelligence APIs.

Gradus Notation + Harmonic Analyzer + Engraver: music tools for any AI agent. Free, no auth.

Access Pretorin compliance systems, controls, evidence, and narratives from your AI tools.

Bilibili MCP tool for video metadata, transcripts, subtitles, and comment summarization

AI-safe credential broker for MCP — run saved SSH/MySQL/psql aliases; passwords never reach AI.

Agent memory where every fact carries a receipt, and deletion is provable.

Scan prompts for injection attacks, redact PII, and audit LLM SDK usage from any MCP client

Let your assistant see your recording's spectrogram, box the noise, and heal only that.

A lightweight, Git-backed permanent memory for AI agents.

Local-first multilingual, auditable memory for Codex, Claude Code, and MCP clients.

Markdown knowledge base as agent memory. Runs against the notes directory it is started in.

Agent-safe structured edits: JSON/YAML/TOML/md/AST, dry-run, batch/tx. Not a filesystem MCP.

LLM evals as MCP tools: score outputs for faithfulness, relevancy, and hallucination.

Fused graph of your codebase — static code + runtime OTel — for AI agents, over MCP.