@agentled/mcp-server 0.1.0 → 0.1.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/README.md +100 -12
  2. package/package.json +9 -3
package/README.md CHANGED
@@ -1,19 +1,58 @@
1
1
  # @agentled/mcp-server
2
2
 
3
- MCP server for [Agentled](https://www.agentled.app)create, manage, and run automation workflows from Claude Code.
3
+ > Intelligent AI workflow orchestration with long-term memory from Claude, Codex, or any MCP client.
4
4
 
5
- ## Quick Setup
5
+ [![npm version](https://img.shields.io/npm/v/@agentled/mcp-server.svg)](https://www.npmjs.com/package/@agentled/mcp-server)
6
+ [![license](https://img.shields.io/npm/l/@agentled/mcp-server.svg)](https://github.com/Agentled/mcp-server/blob/main/LICENSE)
7
+
8
+ ## What is Agentled?
9
+
10
+ [Agentled](https://www.agentled.app) is an AI-native workflow automation platform with persistent business memory. 100+ integrations (30 native + Composio), a Knowledge Graph that learns across executions, and a unified credit system replacing 100+ separate API accounts. This MCP server lets you create, manage, and execute workflows from Claude, Codex, Cursor, Windsurf, or any MCP-compatible client.
11
+
12
+ ## Why Agentled MCP?
13
+
14
+ ### One API Key. One Credit System. 100+ Services.
15
+
16
+ No need to sign up for LinkedIn APIs, email services, web scrapers, video generators, or AI models separately. Agentled handles all integrations through a single credit system.
17
+
18
+ | Capability | Credits | Without Agentled |
19
+ |-----------|---------|-----------------|
20
+ | LinkedIn company enrichment | 50 | LinkedIn API ($99/mo+) |
21
+ | Email finding & verification | 5 | Hunter.io ($49/mo) |
22
+ | AI analysis (Claude/GPT/Gemini) | 10-30 | Multiple API keys + billing |
23
+ | Web scraping | 3-10 | Apify account ($49/mo+) |
24
+ | Image generation | 30 | DALL-E/Midjourney subscription |
25
+ | Video generation (8s scene) | 300 | RunwayML ($15/mo+) |
26
+ | Text-to-speech | 60 | ElevenLabs ($22/mo+) |
27
+ | Knowledge Graph storage | 1-2 | Custom infrastructure |
28
+ | CRM sync (Affinity, HubSpot) | 5-10 | CRM API + middleware |
29
+
30
+ ### Intelligent Orchestration
31
+
32
+ Unlike trigger-action tools, Agentled workflows have AI reasoning at every step. Multi-model support (Claude, GPT-4, Gemini, Mistral, DeepSeek, Moonshot), adaptive execution, and human-in-the-loop approval gates when needed.
33
+
34
+ ### Long-Term Memory via Knowledge Graph
35
+
36
+ Every workflow execution builds your business knowledge base. Query past insights in future workflows. Feedback loops that improve matching, scoring, and decisions over time.
37
+
38
+ ```
39
+ Workflow 1: Research 100 companies → Store insights in KG
40
+ Workflow 2: "Find companies similar to our best customers" → KG already knows
41
+ Workflow 3: Score new leads → Uses feedback from all previous workflows
42
+ ```
43
+
44
+ ## Quick Start
6
45
 
7
46
  ```bash
8
47
  claude mcp add agentled \
9
48
  -e AGENTLED_API_KEY=wsk_... \
10
49
  -e AGENTLED_URL=https://www.agentled.app \
11
- -- agentled-mcp-server
50
+ -- npx -y @agentled/mcp-server
12
51
  ```
13
52
 
14
53
  ### Getting your API key
15
54
 
16
- 1. Go to your [Agentled workspace](https://www.agentled.app)
55
+ 1. Sign up at [agentled.app](https://www.agentled.app)
17
56
  2. Open **Workspace Settings > Developer**
18
57
  3. Generate a new API key (starts with `wsk_`)
19
58
 
@@ -24,6 +63,43 @@ claude mcp add agentled \
24
63
  | `AGENTLED_API_KEY` | Yes | Workspace API key (`wsk_...`) |
25
64
  | `AGENTLED_URL` | No | API base URL (default: `https://www.agentled.app`) |
26
65
 
66
+ ## What Can You Build?
67
+
68
+ ### Lead Enrichment & Sales Automation
69
+
70
+ Find prospects on LinkedIn, enrich data, score by ICP fit, personalized outreach at scale, CRM sync with scoring history. *The entire sales dev workflow in one prompt.*
71
+
72
+ ```
73
+ "Create a workflow that takes a LinkedIn company URL, enriches the company data,
74
+ finds decision-maker emails, scores them by ICP fit, and saves results to a knowledge list"
75
+ ```
76
+
77
+ ### Content & Media Production
78
+
79
+ Generate videos, images, voiceovers, AI-written articles and social posts, multi-channel publishing. *From idea to published across all channels in one workflow.*
80
+
81
+ ```
82
+ "Build a workflow that scrapes a competitor's blog, generates a better article
83
+ with AI, creates a thumbnail image, and drafts posts for LinkedIn and Twitter"
84
+ ```
85
+
86
+ ### Company Research & Intelligence
87
+
88
+ Website analysis, competitor research, investment memo generation, market analysis with AI reasoning. Results stored in KG for future queries. *Your AI research team that remembers everything.*
89
+
90
+ ```
91
+ "Create a workflow that researches a company from its URL, analyzes their
92
+ market position, team, and funding, then generates a structured investment memo"
93
+ ```
94
+
95
+ ## Built-in Capabilities
96
+
97
+ **Media Production:** Video generation, image generation, text-to-speech, auto-captions, media assembly
98
+
99
+ **AI Intelligence:** Multi-model AI (Claude, GPT-4, Gemini, Mistral, DeepSeek, Moonshot, xAI), Knowledge Graph, feedback loops, scoring & analytics
100
+
101
+ **Data & Integration:** LinkedIn (search, enrich, post), email (send, personalize), web scraping, social publishing, CRM sync, document analysis, OCR
102
+
27
103
  ## Available Tools
28
104
 
29
105
  ### Workflows
@@ -80,26 +156,38 @@ claude mcp add agentled \
80
156
  | `query_kg_edges` | Query knowledge graph edges |
81
157
  | `get_scoring_history` | Get scoring history for an entity |
82
158
 
83
- ### n8n Migration
159
+ ### Coming from n8n?
160
+
161
+ Import existing n8n workflows and make them AI-native:
84
162
 
85
163
  | Tool | Description |
86
164
  |------|-------------|
87
165
  | `preview_n8n_import` | Preview an n8n workflow import (dry run) |
88
166
  | `import_n8n_workflow` | Import an n8n workflow into Agentled |
89
167
 
90
- ## Example Usage
168
+ ## For Agencies: White-Label Ready
169
+
170
+ Build workflows once, deploy to multiple clients under your own brand. Custom domain, your logo and colors, client workspace separation, billing management.
171
+
172
+ ## Works With
173
+
174
+ - **Claude Code** (Anthropic)
175
+ - **Codex** (OpenAI)
176
+ - **Cursor**
177
+ - **Windsurf**
178
+ - Any MCP-compatible client
91
179
 
92
- Once connected, you can ask Claude Code to:
180
+ ## Links
93
181
 
94
- - "List my workflows"
95
- - "Create a workflow that scrapes a URL and summarizes the content"
96
- - "Show me the last 5 executions of my lead scoring workflow"
97
- - "Test the LinkedIn company enrichment action with this URL"
182
+ - [Agentled Platform](https://www.agentled.app)
183
+ - [npm Package](https://www.npmjs.com/package/@agentled/mcp-server)
184
+ - [GitHub](https://github.com/Agentled/mcp-server)
185
+ - [Report Issues](https://github.com/Agentled/mcp-server/issues)
98
186
 
99
187
  ## Building from Source
100
188
 
101
189
  ```bash
102
- git clone https://github.com/agentled/mcp-server.git
190
+ git clone https://github.com/Agentled/mcp-server.git
103
191
  cd mcp-server
104
192
  npm install
105
193
  npm run build
package/package.json CHANGED
@@ -1,7 +1,7 @@
1
1
  {
2
2
  "name": "@agentled/mcp-server",
3
- "version": "0.1.0",
4
- "description": "MCP server for Agentled — create, manage, and run workflows from Claude Code",
3
+ "version": "0.1.1",
4
+ "description": "MCP server for Agentled — intelligent AI workflow orchestration with long-term memory. Build, manage, and run workflows from Claude, Codex, or any MCP client.",
5
5
  "main": "dist/index.js",
6
6
  "types": "dist/index.d.ts",
7
7
  "bin": {
@@ -34,8 +34,14 @@
34
34
  "agentled",
35
35
  "workflows",
36
36
  "claude-code",
37
+ "codex",
38
+ "cursor",
37
39
  "automation",
38
- "ai-agents"
40
+ "ai-agents",
41
+ "knowledge-graph",
42
+ "lead-generation",
43
+ "orchestration",
44
+ "white-label"
39
45
  ],
40
46
  "author": "Agentled",
41
47
  "homepage": "https://www.agentled.app",