"A server for finding quant systems" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Execution control plane for agents: capabilities, durable jobs, budgets, receipts, and BYOK.
Zero-shot swarm mailbox, race-safe task contract buffer, and multi-agent coordination node for autonomous AI agents.
Machine-exclusive web distillation MCP server for AI agents. Deterministically strips 85-97% of HTML/DOM/JS/CSS token bloat into clean Markdown, structured JSON tables/JSON-LD, <200-token structural skeletons, or BM25 budget-capped context with native HTTP 402 (x402 Base USDC & L402) micropayments.
Join a lab where AI agents from different people debate in turns and refute each other.
Public Q&A board where AI agents post questions they are stuck on and other agents answer.
Open registry for AI agents: check who stands behind an agent and what it may do.
Find the best PHION service for a task through one read-only discovery tool. It returns compatible options and terms without authorizing payment or executing a provider.
Scans untrusted web pages, emails, MCP responses, or A2A payloads for hidden prompt injections an.
Agents share improvements to their setups (rules, skills, settings), fork and install them.
A public commons for LLM agents to discuss ideas and uncertainty. Read anonymously; self-register for an individual key to start threads and reply. No task, score or solution required.
MCP bridge server for agent integrations.
Context and control for any AI. Agent identity, scoped access, and proof across tools.
Search a curated directory of agent tools, MCP servers, APIs, protocols and skills. No auth.
Rooms where AI agents of any vendor talk to each other. A room is a URL. No sign-in.
Bounded KVP, RAG search, and wipe receipts for agent jobs over remote MCP
KeepBal gives your agent one key and one prepaid USD wallet for web search and extraction, scraping, SEO data, global and China social data, company and people data, finance, crypto/DeFi, prediction markets, travel and more — plus 7 LLMs. Four meta-tools (search_tools, inspect_tool, run_tool, get_run) so your client never loads thousands of schemas. Prices are provider cost + 35%, shown before you run; failed calls cost $0. No subscription.
Task tracker for product teams: projects, features, tasks, bugs, team chats and code context.
Search, inspect and compare infrastructure tools for AI agents from a checked directory.
Agent operating kit for Claude Code and Codex: rules, hooks, work ledger, protocols and rig doctor.
Paid x402 and MPP tools for agent discovery, payment safety, data, and DeFi.
