MCP server that gives a coding agent a Linux desktop it can see, click and type on
Runs locally- 5 tools
- Open source
- Developer tools
MCP server that gives a coding agent a Linux desktop it can see, click and type on
Runs locallySearch every AI coding chat in one place, with secret scanning and a shared task board
Hold risky agent actions for passkey approval and keep signed receipts you can verify
Runs locallyDesign, check, simulate and launch Solana game economies from a JSON spec

Draft, check and publish posts to X and Bluesky through PostSail, dry-run first
Runs locallyBlock stale writes when agents share files, plans or stores on one host
Runs locallyCreate Kubernetes clusters and deliver workloads with GitOps from one CLI and MCP server
Runs locallyHosted MCP server for CVE, CISA KEV and exploit data, SBOM scans and IOC checks
Search hotels, compare live room rates, book and cancel from an AI assistant
Index code, docs, PDFs and data in a local SQLite file and serve context to agents
Runs locallyA Markdown and Obsidian knowledge base that keeps what was true and why it changed
Runs locallyDraft and launch LinkedIn outreach campaigns from Claude Code, Cursor or a dashboard
Generate realistic connected test data, dbt projects and dashboards from a schema
Check API breaking changes in Cursor or Claude Code from captured OpenAPI evidence
Runs locallySeven read-only tools for adding EU AI Act controls to a TypeScript AI stack
Search AILANG's language reference, stdlib, examples and benchmarks from an agent

Fetch pages and search the web through a Singapore 4G/5G mobile IP from your agent
Show agents a file's structure, callers and impact in eight languages, unread
Runs locally
Reverse-osmosis membrane system design with a 742-element library, from AI clients
Not checked yetRun agent-written code under a capability policy and see what it can touch first
Runs locallyStores every fix your coding agent makes and brings it back when the problem returns
Runs locallyTake-home pay, employer cost and official tax tables for many countries via MCP
Runs locally
Infers a semantic layer from your data warehouse and serves it to agents
Runs locally
Records your voice and a browser session, then hands agents a causal evidence package
Runs locallyVerify single or bulk email addresses from an AI assistant, with no charge on unknowns
Run local simulators of Stripe, GitHub and Slack APIs from a coding agent
Runs locallyLive JSON from sites with no API, plus agent-built APIs for any website
Runs locallyWrite smooth, stylised 3D game models as text and build glTF and Godot scenes
Runs locallyAsk an agent what a website is: AI builder traces, tech stack, traffic rank and trust
Local-first shared memory for AI agents where only you confirm what is saved
Runs locally