"Code Execution" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Task tracker for product teams: projects, features, tasks, bugs, team chats and code context.
Execution control plane for agents: capabilities, durable jobs, budgets, receipts, and BYOK.
Your AI apps as one team: hand work to Codex or Claude Code on your Mac, with a shared logbook.
AI jobs, contracts, execution proof, translation and data quality over MCP + x402 USDC on Base.
Give AI agents private phone numbers so Claude Code, Codex, and MCP sessions can call each other, exchange up to 12 messages per call, and share files across computers or teammates.
Autonomous agent clearinghouse indexing 23,000+ MCP, A2A, x402 & MPP tools with instant execution.
1,400+ tool A2A, MCP & x402 clearinghouse with free semantic discovery and paid execution.
Your own AI agent on an always-on cloud computer: Claude Code, Codex and more, or managed OpenClaw.
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.
Paid x402 agent: API discovery,commerce availability/buyable,domain/package preflight,release asset
The Refusal Desk builds the *no* — a pre-execution tribunal that screens an incoming task brief
Intelligence for your AI agents: what they need to know, at the moment they decide. NEXUS connects Claude Code, Claude, ChatGPT, Cursor and OpenClaw to one shared record of your decisions, rules and past incidents, so an agent doesn't repeat a costly mistake or undo what was already decided. What one agent learns, the others already know. Every item is graded (measured, reported or inferred), outdated facts are marked as superseded, and contradictions are flagged. Before an important action, agents can call antes_de_actuar to get the rules that apply. Remote server with OAuth. Free plan, no credit card: https://nexus.eblas.link
Converra (converra.ai), not Convera, fixes the behavior, not the code. Diagnoses production agent failures, tests bounded prompt or configuration fixes head-to-head, ships what you approve, and reports a production verdict on every fix. Streamable HTTP; OAuth or API-key bearer auth. Docs: https://converra.ai/docs/mcp/coding-agents?utm_source=glama&utm_medium=referral&utm_campaign=mcp_registry_2026_10 . Full tool catalog and install commands: https://github.com/converra/converra-agent-kit/blob/main/SUBMISSION.md
Free AIOS discovery, preflight and bounded G05 authoritative-guidance execution for agents.
Paid deterministic data-quality and execution-verification tools for AI agents.
Supervised API-write gateway for AI agents with policy, human approval and execution receipts.
Recall and calibrate policy-compliant tool-call arguments before execution. Does not run the tool.
Cross-agent artifact workspace with provenance across Claude Code, Codex, Cursor, LangGraph.
Free API discovery for AI agents; API execution may require USDC payments via x402 on Arc Mainnet.
Free API discovery for AI agents; execution may require USDC/x402 payments on Arc Mainnet.
Temporary file relay for AI agents: upload a generated file, get an expiring download link.
Design AI agent teams for a business problem and generate ready-to-paste Claude Code prompts.
Human execution API for AI agents needing voluntary help with physical-world tasks.
AI agents discover human capabilities, request real-world human execution, and track status.
Set up the JEV model router for Claude Code, Codex and Cursor, and install MCP servers.
Discover agent services, compare sourced capabilities and inspect connection evidence. No execution.
Plan LLM fallback sequences from supplied cost, quality and latency assumptions; no live execution.
Put on anyone's AI rules by GitHub username: fetches their hat.md and its hat code.
Hosting for apps you build with AI. Tested with Claude Code and Codex. Private beta: ask for access.
Verification layer for the agentic web: a signed answer about any site before an agent acts.
