Agentled
MCP server for AgentLed workflow automation with long-term memory and 100+ integrations
Agentled is a freemium MCP server for productivity. It runs locally on your machine and is started by your AI client.
- Pricing
- Freemium
- Platforms
- CLI, API
- Runs
- Locally
- Version
- 0.20.1
- Listing updated
Similar MCP servers
Install
Run in a terminal
claude mcp add mcp-server --env AGENTLED_API_KEY='<AGENTLED_API_KEY>' -- npx -y @agentled/mcp-serverAdd to claude_desktop_config.json
{
"mcpServers": {
"mcp-server": {
"command": "npx",
"args": [
"-y",
"@agentled/mcp-server"
],
"env": {
"AGENTLED_API_KEY": "<AGENTLED_API_KEY>"
}
}
}
}Add to ~/.cursor/mcp.json
{
"mcpServers": {
"mcp-server": {
"command": "npx",
"args": [
"-y",
"@agentled/mcp-server"
],
"env": {
"AGENTLED_API_KEY": "<AGENTLED_API_KEY>"
}
}
}
}Add to .vscode/mcp.json
{
"servers": {
"mcp-server": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@agentled/mcp-server"
],
"env": {
"AGENTLED_API_KEY": "<AGENTLED_API_KEY>"
}
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"mcp-server": {
"command": "npx",
"args": [
"-y",
"@agentled/mcp-server"
],
"env": {
"AGENTLED_API_KEY": "<AGENTLED_API_KEY>"
}
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"mcp-server": {
"command": "npx",
"args": [
"-y",
"@agentled/mcp-server"
],
"env": {
"AGENTLED_API_KEY": "<AGENTLED_API_KEY>"
}
}
}
}Using several servers? Build one config file with the MCP config generator.
Configuration
AGENTLED_API_KEYYour AgentLed workspace API key (generate in Workspace Settings > Developer)Required
About Agentled
AgentLed is positioned as an automation engine for AI agents. This server gives Claude, Codex, Cursor, Windsurf and other clients access to its workflows through one API key and one credit system, rather than separate accounts for LinkedIn, email finding, scraping, AI models or video generation. The README's example turns a single prompt about outbound to European fintech CTOs into three workflows: prospect research, signal detection and personalised outreach, scheduled every 48 hours.
A built-in Knowledge Graph stores results across runs, so scoring workflows can reuse earlier outcomes and feedback. Credit costs are tabulated, for instance 50 credits for LinkedIn company enrichment and 5 for email finding. It runs over stdio with an AGENTLED_API_KEY created in workspace settings, and is also offered as a Claude Code and Codex plugin that bundles a workflow-authoring skill. The README lists Claude, GPT-4, Gemini, Mistral, DeepSeek and Moonshot as supported models.
Tools this server provides (1)
Taken from the project documentation; the running server may differ.
- submit_feedback_to_agentled
- Capture product feedback when the user asks.
What it does
- Workflow orchestration
- Builds multi-step workflows where AI reasons at each step.
- Knowledge Graph memory
- Stores results and feedback across runs.
- Unified credits
- One key and credit system for many services.
- Lead research
- LinkedIn and email enrichment with ICP scoring.
- Plugin install
- Claude Code and Codex plugins bundle a workflow skill.
- Multi-model support
- Works with Claude, GPT-4, Gemini, Mistral, DeepSeek and Moonshot.
Good for
- Build an outbound prospecting campaign from one prompt
- Score and track leads across repeated runs
- Sync enriched contacts to a CRM
- Schedule recurring research workflows
Pricing
Freemium
Credit-based; plan prices not published here
Agentled FAQ
What do I need to use Agentled?
An AgentLed workspace and an API key from Workspace Settings > Developer.
How are services billed?
Through one credit system; the README lists credit costs per capability.
How do I add Agentled to Claude Code?
Use claude mcp add with AGENTLED_API_KEY and npx -y @agentled/mcp-server, or install the plugin.
Does Agentled remember past runs?
Yes, through a Knowledge Graph.
Is Agentled free?
Agentled has a free plan, with paid plans for more usage or features.
What are the best alternatives to Agentled?
The closest alternatives to Agentled are Cofounder, OfficeGen AI, LiveContext, APIANT and Odoo MCP Pro.
Where this comes from
- Description: written from the project's README.
- Install steps: from the official MCP Registry entry.