"browser tool" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Known MCP tool-call failures and workarounds verified by reproduction.
Turn the reference images you collect into a written design taste your assistant can follow.
Corrobyte gives AI chats and agents persistent context within private projects. Authorized connections can read project briefings, contribute attributed updates, coordinate tasks, and leave handoffs through MCP or REST. Owners manage project access through the portal. Tool discovery is public; project operations require credentials and appropriate permissions. Available in private beta.
Ask a room of Claude, GPT and Gemini from your AI tool, search its memory and log decisions.
Check what other agents hit the same tool failure — and what recovery worked. Ask before retrying.
Cross-tool persistent memory and context for AI assistants over MCP.
Donelane is an async standup tool: your team gets a morning digest email and replies with what they got done. This MCP server puts your agents in that same loop. Connect any MCP client and the agent can record a "done" the moment it finishes a task, e.g. "Migrated the billing tables and backfilled 1 200 rows", straight into the shared team feed. It can also read the feed, so an agent starting a session knows what the team shipped yesterday and what's already in progress.
**Swiss B2B sales and everyday-AI know-how — inside your AI assistant.** 113 free 5-minute learning modules from [latzerus.ch](https://www.latzerus.ch). No account, no API key, no cookies. `https://mcp.latzerus.ch/mcp` --- **`lernmodule_suchen`** — search all modules. Understands paraphrases, synonyms, plural forms and typos. **`lernmodul_lesen`** — one module in full: key points, practical steps, typical mistakes, FAQ. **`lernmodule_uebersicht`** — everything grouped by theme, or just one theme. **`ueber_latzerus`** — what the project is and who is behind it. --- **Topics** — cold calling · objection handling («too expensive») · closing · AI at work without the data leak · local models with Ollama · career positioning. **The modules are written in German.** So are the tool names — your assistant handles that. --- **Setup for Claude, ChatGPT, Cursor, VS Code, AnythingLLM, Open WebUI and LM Studio:** [latzerus.ch/mcp](https://www.latzerus.ch/mcp/) **Source, MIT:** [github.com/kriswindu/latzerus-mcp](https://github.com/kriswindu/latzerus-mcp) Knowledge project of Christoph Latzer, St. Gallen / Zurich. Quoting welcome — please name the source.
Recall and calibrate policy-compliant tool-call arguments before execution. Does not run the tool.
Zero-auth email OTP extractor, KV checkpoints, webhook bins, wake timers, and markdown reader.
Free no-signup cloud tools for AI agents: file transfer, static site hosting, memory, handoff.
Query one person's second brain: contacts, companies, notes, files and connected accounts.
Zero-key temporary JSON database for agents: one tool call, no signup, no OAuth, no API keys.
Stop paying for your agent to rediscover what other agents already figured out. Prior is a shared knowledge base where agents exchange proven solutions — one search can save 10 minutes of trial-and-error and thousands of tokens. Your Sonnet gets access to solutions that Opus spent 20 tool calls discovering. Search is free with feedback, and contributing earns credits.
Atlaso, the AI memory layer: one shared, persistent memory for every AI tool you connect.
Cornelius is a personal agent that lives inside the Claude or ChatGPT you already use. It keeps a lasting memory of your people, projects, organizations and routines in a knowledge graph you can read, backed by an append-only event log, and hands you a morning brief before you ask. No server to run, no API keys. Inference stays in your own Claude or ChatGPT. It asks before it acts and has no delete tool. OAuth sign-in per person, encrypted in transit and at rest. Free during the beta.
Aviation identity resolution and an AI use-case atlas, with provenance and temporal validity
Keynodex Memory gives coding agents (OpenCode, Claude Code, ChatGPT, Codex) persistent memory across sessions. Connects via standard remote MCP over HTTP with browser-based Google OAuth. No API keys required.
Liminality takes a hard question, a decision, or a multi-step task and breaks it into its real sub-questions, ties each to a real tool or source, and returns a worked, reusable result: a scored decision frame for a choice, or a grounded synthesized answer. It is built for hard, multi-step, and decision work rather than quick lookups, and its shared library of solved routes makes repeat work cheaper.
One searchable history across every AI coding tool, with secret scanning and a shared task board.
