"Manim - Python Library for Animations and Math Visualization" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Discovery registry for AI agents: 660+ APIs, MCP servers and CLIs, each health-checked every 6 hours with real requests — full initialize + tools/list handshakes for MCP, real calls for APIs — plus response-schema validation that catches responses which parse fine but are missing a required field.
Personal-finance workspace for AI agents: accounts, spending, budgets, goals, and investments.
The team's shared memory that reaches an AI before it starts work. Arroway holds what a team, or one person working across sessions and tools, has decided: rules, decisions, preferences and unfinished work. Any AI connected to it reads that before it acts and records what it did when it finishes. Each memory carries who decided it and the condition that retires it; the AI proposes what to record and a person approves it.
Collide is an MCP layer that keeps concurrent AI agents from stepping on each other in a shared codebase. It tracks code at the symbol level with a Merkle tree, so agents declare intent before writing, get warned about collisions, and pick up context on what changed and why. It also carries anchored team memory, merge simulation, and an audit ledger.
Bounded KVP, RAG search, and wipe receipts for agent jobs over remote MCP
Ephemeral context bridge: one link carries context to another agent, returns one answer; host-readable while live, anyone with the link, not for secrets, dissolves on TTL.
Check what other agents hit the same tool failure — and what recovery worked. Ask before retrying.
Evidence-first registry of real-world APIs for AI agents, with verified metadata and comparison.
Hosted AI agents and locked workflows on connected apps, with human approval gates and a run ledger. Docs: https://docs.flowra.dev/guides/mcp
Agent Observatory: checks A2A, MCP and OpenAPI declarations and logs published changes.
Multi-agent hub: MCP server and SSE stream
A second opinion before your agent acts on one model's unearned confidence. One question goes to 3-4 different AI models that answer independently, then a chair returns a single verdict with a confidence score, the consensus and the dissent that held. A grounded tier buys evidence first (honeypot simulation, OFAC sanctions screen, page content, SEC profile, web results) and itemises what it spent. Pay-per-call with x402 in USDC on Base: no account, no API key, one free call a day.
Delivery Assurance: checks which public agent candidates declare a fit for a bounded task.
Remote MCP server to run your Atako AI agents: chat, projects, files, integrations and channels.
Agent-native registry to discover APIs, MCP servers and CLIs, with live health checks.
Paid x402 and MPP tools for agent discovery, payment safety, data, and DeFi.
Zero-config agent-readiness auditor and Flight Simulator tools for AI coding agents
Selects between supported SEARCH providers for ECONOMY or CRITICAL mode.
Metered coordination for agent swarms: locks, sub-keys, storage, messaging. x402 billing (USDC).
Eight tools an agent uses; ten more for operating your tenant. Patent pending.
