Building agents

ceedot-rock/Agent-Rider

MCP server Claude CodeCodexCursor +2

Signed agent identity, trust scoring, credit economy, and social layer for AI agents. Remote server at agentrider.vercel.app.

LIVELUCKY/fastcontext-integrations

Skill Claude Code

Fast, autonomous subagent that explores codebases through multi-step reasoning. Treat it as your default first step for any code comprehension task.

zach-source/claude-mailbox

Skill Claude CodeCodex

Coordinate with other concurrently-running Claude Code sessions via the mailbox MCP (register presence, broadcast your objective, discover who else is working and where, DM/ask them, and respect the single main-branch leader). Use at session start when the mailbox MCP tools are available, and whenever the user says…

khteh/mcpserver-local

MCP server Claude CodeCodexCursor +2

MCP server "mcpserver-local" as configured in khteh/mcpserver-local. Runs locally from the mcpserver-local Python package.

Pisama-AI/pisama-python

MCP server Claude CodeCodexCursor +2

Multi-agent failure detection for production AI systems. Runs locally from the pisama Python package.

Dheerax/opencode_mcp

MCP server Claude CodeCodexCursor +2

Local MCP server that hands coding tasks to a temporary OpenCode session and reports back when finished. Runs locally from the opencode-mcp-bridge npm package.

ch1kim0n1/claude-pm-mcp

Plugin Claude Code

Bundles 2 skills, 1 MCP server · 81 tokens together

Developer-ready, evidence-driven local orchestration of isolated AI coding workers.

allengox1994-creator/cursor-token-saver

MCP server Claude CodeCodexCursor +2

A local MCP server that adds an evidence store, semantic memory, a project model, and runbooks to Cursor's AI agent. Cursor is an AI-powered code editor.

xiaoran7/Agent-Android

MCP server Claude CodeCodexCursor +2

MCP server "droid-bridge-mcp" as configured in xiaoran7/Agent-Android. Runs locally from the droid-bridge-mcp Python package.

alexkirienko/bot2bot-chat

Skill Claude CodeCodex

Use this skill when a persistent agent needs to find other agents, publish its own capabilities, or start a private Bot2Bot conversation.

ZhenMoon/mcp-search-server

MCP server Claude CodeCodexCursor +2

MCP server "mcp-search-server" as configured in ZhenMoon/mcp-search-server. Runs locally from the mcp-search-server npm package.

VedSoni-dev/primer

MCP server Claude CodeCodexCursor +2

MCP server "primer-brain" as configured in VedSoni-dev/primer. Runs locally from the primer-brain npm package.

noktohq/nokto-agent-orchestrator

MCP server Claude CodeCodexCursor +2

MCP server "nokto-agent-orchestrator" as configured in noktohq/nokto-agent-orchestrator. Runs locally from the nokto-agent-orchestrator npm package.

lipey1/cursor-agent-mcp

Skill Claude Code

Manager mode that delegates implementation to Cursor Agent CLI (via MCP cursor-agent tools or agent -p) while the host AI only briefs, reviews, and reports. Invoke as /cursor-agent on|off|status. Also triggers on "cursor-agent on/off", "delegate to cursor-agent", "manager mode". When state is on, NEVER implement…

a2al/A2AL

Skill Claude CodeCodex

Gives the OpenClaw agent decentralized networking identity and peer discovery via the A2AL Tangled Network. Use when the user wants to make their OpenClaw instance discoverable to other AI agents worldwide, find and connect to remote AI agents by capability, send encrypted offline messages to other agents, or set up…

Verbalize-public/open-delegate

Skill Claude CodeCodex

Delegate a task to a background OpenCode agent session via the open-delegate MCP server (odedelegate/odeawait/odetranscript/odecancel/odediagnostics). Use when a task should run on a cheaper OpenCode model, run unattended in the background, or needs its own isolated OpenCode session instead of the native subagent tool.

shofer-dev/claude-code-slang-orchestrator

Plugin Claude Code

Bundles 4 commands, 1 MCP server · 54 tokens together

Run deterministic, .slang-driven multi-agent workflows inside Claude Code. A non-LLM state machine in an MCP server coordinates agents (via the Agent SDK); the top-level session triggers and observes runs.

Johnny-Z13/proofslip

MCP server Claude CodeCodexCursor +2

Receipt-based verification for AI agent workflows — create, verify, and poll ephemeral proof objects. Runs locally from the @proofslip/mcp-server npm package. Needs 2 environment variables to run.

hivemindunit/llmintel-mcp

MCP server Claude CodeCodexCursor +2

One of 2 in server.json

Check whether an LLM model id is deprecated, retiring, or retired, and what to migrate to. Runs locally from the @llmintel/mcp npm package. Needs 2 environment variables to run.

marchward/marchward

MCP server Claude CodeCodexCursor +2

Runtime authority for AI agents: credential mediation, spend cap, approval gates, audit log. Runs locally from the @marchward/mcp-server npm package. Needs 2 environment variables to run.

bobuilds/nexustoken-sdk

MCP server Claude CodeCodexCursor +2

Python SDK + MCP server for NexusToken — an agent-to-agent capability network. Runs locally from the nexustoken-sdk Python package. Needs 2 environment variables to run.

kit18/6ducklearn-mcp

MCP server Claude CodeCodexCursor +2

Connect agents to 6DuckLearn memory, approvals, and runtime control. Remote server at 6ducklearn.com.

vaizcom/vaiz-mcp

MCP server Claude CodeCodexCursor +2

Connect AI assistants to your Vaiz workspace: tasks, projects, boards, documents and milestones. Runs locally from the vaiz-mcp npm package. Needs 3 environment variables to run.

Tulimoa/tulimoa-mcp

Skill Claude CodeCodex

Connect an agent to the Tulimoa MCP gateway — one EU-hosted endpoint that federates your connected SaaS tools and carries a persistent memory layer, so context (facts, IDs, goals, plans) survives across turns and sessions and the agent stops re-fetching and re-asking.