See what each of your coding agents is working on, and read or advance your todos.
Servers that run on your own machine over stdio. They need Node or Python and a config edit — in exchange your data never reaches someone else's host.
Drop a short text fragment into a scratchpad slot, with newlines intact.
Start, stop, and inspect local dev servers in a desktop app instead of the agent's session.
Bridge a live Chrome browser to your agent: 150 tools for capture, extraction, and observation.
Create and read mind maps on CloudMindMaps from Claude and other AI assistants.
VIN decode, Canadian listings, market quotes, TC+NHTSA recalls.
221 MCP tools across 26 practices for independent professionals.
Drive ASMHunter attack-surface monitoring from an AI agent: recon, scans, findings, reports.
Self-hosted git-native knowledge base with an MCP endpoint your AI reads, writes and rewinds
Drive an open 3DStreet scene tab from Claude Desktop or Claude Code via MCP tool calls.
Albanian NIPT validation, TVSH (VAT) & invoice math, gross↔net payroll on verified 2026 rates.
Local-first, formally verified memory for AI agents: consult/learn/related/list over MCP.
Seven-layer agent memory: episodic, semantic, procedural and core.
Convert frontend folders to WordPress themes: quota, convert, status, download, preview, failures.
Advanced codebase indexing and semantic search MCP server
Give any MCP client the ability to browse and interact with the web via WebUplink.
Run any model on the live WaveSpeed catalog: image, video, audio, 3D.
Voris privacy-native web analytics for AI agents: query metrics & citations, scaffold tracking.
Inspect and manage Verlon AI gates, logs, recommendations, and experiments from any MCP client.
Generate your brand in-agent, then keep tokens, components, and copy on-brand over MCP.
Verify an AI agent's payment authority: signed mandates, allowlists, and tamper-proof receipts.
Slide decks locally: templates, checks, HTML to editable PowerPoint, .pptx rescue.
Credential broker that signs your AI agent up to SaaS dev tools, within a signed spending mandate.
Search TradeSearcher strategies and backtests from Claude Code, Cursor, Codex, and other agents.
Dynamically expose tools from proxied servers based on an Agent Persona
Multi-model consensus: 2-6 frontier LLMs answer, an independent judge synthesises one answer.
Local PDF accessibility audit: machine-checkable PDF/UA basics (ADA/EAA/508).
Permanent local PDF redaction: text is removed and verified gone, not covered.
Local-first visual regression for AI agents: verdicts, diff images, explainsnapshot.
Read-only Base mainnet reader.
Missing a connector?
Tell us which service you need, or add your own MCP server: we will check it and publish it in the catalog.
Suggest a connector