Server data from the Official MCP Registry
Intelligent AI workflow orchestration with long-term memory, 100+ integrations, and unified credits.
Intelligent AI workflow orchestration with long-term memory, 100+ integrations, and unified credits.
Valid MCP server (2 strong, 2 medium validity signals). 3 known CVEs in dependencies (0 critical, 3 high severity) Package registry verified. Imported from the Official MCP Registry.
4 files analyzed ยท 4 issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
This plugin requests these system permissions. Most are normal for its category.
Set these up before or after installing:
Environment variable: AGENTLED_API_KEY
Add this to your MCP configuration file:
{
"mcpServers": {
"io-github-agentled-mcp-server": {
"env": {
"AGENTLED_API_KEY": "your-agentled-api-key-here"
},
"args": [
"-y",
"@agentled/mcp-server"
],
"command": "npx"
}
}
}From the project's GitHub README.
The automation engine built for AI agents. Intelligent AI workflow orchestration with long-term memory, 100+ integrations, and unified credits.
Agentled is the automation engine built for AI agents. It gives Claude, Codex, Cursor, Windsurf, and any MCP-compatible client direct access to intelligent workflow orchestration, long-term memory, and 100+ integrations.
Three things make it different:
๐ง Long-Term Memory โ A built-in Knowledge Graph stores insights across workflow executions. Your agents get smarter over time โ they remember past research, lead scores, content performance, and business context.
โก Unified Credits โ One API key, one credit system, 100+ services. No need to sign up for LinkedIn, email, scraping, AI models, or video generation separately. Connect once, use everything.
๐ฏ Intelligent Orchestration โ AI reasons at every step. Workflows aren't just "if this then that" โ they understand context, make decisions, and adapt to results.
$ agentled create "Outbound to fintech CTOs in Europe"
Loading workspace context from Knowledge Graph...
โฆ ICP loaded โฆ 3 prior campaigns โฆ 847 contacts in KG
Creating campaign with 3 workflows...
โโ Workflow 1: Prospect Research linkedin ยท hunter ยท clearbit
โ LinkedIn: CTO + fintech + EU โ 189 profiles
โ Enriched via Hunter + Clearbit โ 156 matched
โ ICP scoring โ 43 high-intent leads
โโ Workflow 2: Signal Detection web-scraper ยท crunchbase
โ Job postings โ 12 hiring devops
โ Crunchbase โ 8 recently funded
โ Cross-match: hiring + funded โ 5 hot leads
โโ Workflow 3: Outreach email ยท linkedin ยท kg
โ Personalized emails from context
โ LinkedIn requests with custom notes
โ 43 leads saved to Knowledge Graph
Campaign saved. Scheduled: every 48h
Credits used: 720
โ https://www.agentled.app/your-team/fintech-cto-outbound
One prompt. Three workflows. LinkedIn enrichment, email finding, AI scoring, multi-channel outreach โ all orchestrated, all stored in the Knowledge Graph for the next run.
claude mcp add agentled \
-e AGENTLED_API_KEY=wsk_... \
-- npx -y @agentled/mcp-server
Use the local built entrypoint when you want to test unpublished changes against a
local app. npx -y @agentled/mcp-server always uses the latest published npm package.
cd agentled-mcp-server
npm run build
claude mcp add --transport stdio agentled_local \
--env AGENTLED_API_KEY=wsk_... \
--env AGENTLED_URL=http://localhost:8080 \
-- node /absolute/path/to/agentsled-front/agentled-mcp-server/dist/index.js
wsk_)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.
| Capability | Credits | Without Agentled |
|---|---|---|
| LinkedIn company enrichment | 50 | LinkedIn API ($99/mo+) |
| Email finding & verification | 5 | Hunter.io ($49/mo) |
| AI analysis (Claude/GPT/Gemini) | 10-30 | Multiple API keys + billing |
| Web scraping | 3-10 | Apify account ($49/mo+) |
| Image generation | 30 | DALL-E/Midjourney subscription |
| Video generation (8s scene) | 300 | RunwayML ($15/mo+) |
| Text-to-speech | 60 | ElevenLabs ($22/mo+) |
| Knowledge Graph storage | 1-2 | Custom infrastructure |
| CRM sync (Affinity, HubSpot) | 5-10 | CRM API + middleware |
Other automation tools start from zero every run. Agentled's Knowledge Graph remembers across executions โ what worked, what didn't, what humans corrected. Scoring workflows can use compact row-level scoring_profile summaries and bounded scoring-memory retrieval so every run compounds on the last without dumping raw history into prompts.
Run 1: Investor scoring โ 62% accuracy (cold start)
Run 5: โ 78% (learning from IC feedback)
Run 12: โ 89% (compound learning from outcomes, zero manual tuning)
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.
Agent Teams let you run multiple AI specialists in a single workflow step. Pick a preset and describe what you need โ the team handles coordination, delegation, and synthesis.
"Add an Agent Team step that researches the company and produces an investment memo"
Six built-in presets cover the most common patterns:
| Preset | What it does |
|---|---|
research-and-summarize | Specialists gather information, one synthesizes a summary |
analyze-and-recommend | Multiple analysts evaluate options, produce a ranked recommendation |
generate-then-review | A generator drafts content, reviewers critique and refine |
compare-options | Specialists argue for competing options, coordinator arbitrates |
investigate-in-parallel | Independent specialists explore different angles simultaneously |
review-and-improve | Reviewers find issues, an editor applies improvements |
When creating Agent Team steps via MCP, include preset metadata so the step opens correctly in the builder:
{
"id": "analyze",
"type": "agentOrchestrator",
"name": "Agent Team",
"orchestratorConfig": {
"pattern": "supervisor",
"workers": [
{ "id": "researcher", "name": "Researcher", "systemPrompt": "Research {{input.company_url}} โ team, funding, market position" },
{ "id": "analyst", "name": "Analyst", "systemPrompt": "Analyse the research. Identify risks and growth signals." }
]
},
"metadata": {
"agentTeamPreset": "research-and-summarize",
"agentTeamMode": "simple",
"agentTeamUxVersion": 1
},
"next": { "stepId": "milestone" }
}
Existing steps created with raw orchestratorConfig and no metadata continue to work โ they open in advanced mode in the builder without errors.
"Find fintech CTOs in Europe, enrich via LinkedIn + Hunter, score by ICP fit,
draft personalized outreach, save everything to the Knowledge Graph"
"Scrape trending topics in our niche, generate 5 LinkedIn posts with AI,
create thumbnail images, schedule publishing for the week"
"Research this company from its URL โ team, funding, market position, competitors.
Generate an investment memo. Store in KG for future reference."
"Match this startup against our 2,000+ investor database. Score by sector focus,
stage preference, check size, and portfolio synergy. Compare with last round's outcomes."
3,000+ profiles processed. IC-ready reports. Prediction vs outcome learning โ accuracy went from 62% to 89% over 12 runs with zero manual tuning.
Media Production: Video generation, image generation, text-to-speech, auto-captions, media assembly
AI Intelligence: Multi-model AI (Claude, GPT-4, Gemini, Mistral, DeepSeek, Moonshot, xAI), Knowledge Graph, feedback loops, scoring & analytics
Data & Integration: LinkedIn (search, enrich, post), email (send, personalize), web scraping, social publishing, CRM sync, document analysis, OCR
| Tool | Description |
|---|---|
list_workflows | List all workflows in the workspace |
get_workflow | Get full workflow definition by ID |
create_workflow | Create a new workflow from pipeline JSON |
update_workflow | Update an existing workflow |
add_step | Add a step with automatic positioning and next-pointer rewiring |
update_step | Deep-merge updates into a single step by ID |
remove_step | Remove a step with automatic next-pointer rewiring |
delete_workflow | Permanently delete a workflow |
validate_workflow | Validate pipeline structure, returns errors per step |
publish_workflow | Change workflow status (draft, live, paused, archived) |
export_workflow | Export a workflow as portable JSON |
import_workflow | Import a workflow from exported JSON |
| Tool | Description |
|---|---|
get_draft | Get the current draft version of a workflow |
promote_draft | Promote a draft to the live version |
discard_draft | Discard the current draft |
create_snapshot | Create a manual config snapshot |
delete_snapshot | Delete a specific config snapshot |
list_snapshots | List version snapshots for a workflow |
restore_snapshot | Restore a workflow to a previous snapshot |
| Tool | Description |
|---|---|
start_workflow | Start a workflow execution with input. Pass useMocks: false to force a real (credit-consuming) run that ignores per-step mock data; defaults to honoring the workflow's configured mocks. |
list_executions | List executions for a workflow (paginated via nextToken) |
get_execution | Get execution details with step results |
list_timelines | List step execution records (timelines) for an execution (paginated via nextToken) |
get_timeline | Get a single timeline by ID with full step output |
stop_execution | Stop a running execution |
retry_execution | Retry a failed step โ auto-detects the most recent failure if no timeline ID provided |
| Tool | Description |
|---|---|
list_apps | List available apps and integrations |
get_app_actions | Get action schemas for an app |
test_app_action | Test an app action without creating a workflow |
test_ai_action | Test an AI prompt without creating a workflow |
test_code_action | Test JavaScript code in the same sandboxed VM as production |
get_step_schema | Get allowed PipelineStep fields grouped by category |
| Tool | Description |
|---|---|
get_workspace | Get workspace info and settings |
get_workspace_company_profile | Get the editable workspace company profile and offerings |
update_workspace_company_profile | Update top-level company profile fields like name, URLs, logo, industry, size, and additional information |
upsert_workspace_company_offerings | Create new offerings or update existing offerings in the workspace company profile |
list_knowledge_lists | List knowledge lists in the workspace |
get_knowledge_rows | Get rows from a knowledge list (paginated, max 50) |
get_knowledge_rows_by_ids | Fetch specific rows by ID (max 200) โ use after query_kg_edges |
get_knowledge_text | Get text content from a knowledge entry |
create_knowledge_list | Create a new knowledge list with a typed schema (idempotent on key collision) |
update_knowledge_list_schema | Add or remove fields on an existing list schema |
delete_knowledge_list | Permanently delete a list and all its rows |
upsert_knowledge_rows | Insert or update rows in a list (max 500/call, per-row error reporting) |
delete_knowledge_rows | Delete rows by ID |
upsert_knowledge_text | Create or update a text knowledge entry |
delete_knowledge_text | Delete a text knowledge entry by key |
query_kg_edges | Query knowledge graph edges |
get_scoring_history | Get scoring history for an entity |
| Tool | Description |
|---|---|
get_branding | Get the workspace's whitelabel branding config (displayName, logo, colors, favicon, badge) |
update_branding | Update branding โ set displayName, logoUrl, tagline, primaryColor, primaryColorDark, faviconUrl, hideBadge |
| Tool | Description |
|---|---|
chat | Send a message to the AgentLed AI agent. Build workflows through natural language โ no JSON required. Supports multi-turn conversations via session_id. |
| Tool | Description |
|---|---|
do | Natural language intent router โ describe what you want and it auto-selects and executes the right tool |
Import existing n8n workflows and make them AI-native:
| Tool | Description |
|---|---|
preview_n8n_import | Preview an n8n workflow import (dry run) |
import_n8n_workflow | Import an n8n workflow into Agentled |
When you need all records related to a specific entity, use the two-tool chain instead of paginating get_knowledge_rows:
Example 1 โ all deals scored by an investor:
1. query_kg_edges({ entityName: "Investor Name", relationshipType: "SCORED" })
โ returns edges with targetNodeIds
2. get_knowledge_rows_by_ids({ rowIds: <targetNodeIds from step 1> })
โ returns full row data for each matched deal
Example 2 โ all leads sourced from a campaign:
1. query_kg_edges({ entityName: "Campaign Name", relationshipType: "SOURCED" })
โ returns edges with targetNodeIds
2. get_knowledge_rows_by_ids({ rowIds: <targetNodeIds from step 1> })
โ returns full contact/lead rows
Why this matters: get_knowledge_rows is limited to 50 rows per call. At 3k rows that means 60 round trips; at 10k it means 200. The KG-edge path is O(edges for that entity) โ independent of total list size โ so it stays fast regardless of how large the list grows.
Node ID convention: source_node_id and target_node_id values from query_kg_edges are knowledge row IDs. Rows outside the authenticated workspace are silently excluded.
Build workflows once, deploy to multiple clients under your own brand. Configure branding directly from the MCP server:
"Set my workspace branding: displayName 'Acme AI', primaryColor '#6366f1', tagline 'Powered by Acme'"
Use get_branding and update_branding to manage displayName, logo, colors, favicon, tagline, and badge visibility. Client portal appearance updates instantly.
Memories let workflows learn across executions. Store what worked, recall it next time.
"Store a memory: key 'icp_criteria', value { industry: 'fintech', minEmployees: 50, region: 'EU' },
category 'preference', scope 'workspace'"
"Recall memory 'icp_criteria' at workspace scope โ use it to score this batch of leads"
"Search memories for 'conversion rate' in the 'outcome' category"
"Store memory: key 'total_leads_processed', value 43, merge 'increment', scope 'workspace'"
Each subsequent call with merge: 'increment' adds to the existing value โ no read-modify-write needed.
Proactive agents are background monitors that autonomously trigger workflows when conditions are met.
"Create a proactive agent named 'New Lead Watcher' that checks the 'incoming-leads' knowledge list
every 5 minutes. When new rows appear, start the 'lead-enrichment' workflow with the new rows as input.
Limit to 10 actions per day."
Config structure:
{
"monitorInterval": "5m",
"evaluation": { "mode": "rules" },
"monitors": [{
"type": "kg_list",
"listKey": "incoming-leads",
"condition": "new_rows"
}],
"actions": [{
"type": "start_workflow",
"workflowId": "wf_abc123",
"inputMapping": { "leads": "{{monitor.newRows}}" }
}],
"maxActionsPerDay": 10,
"cooldownMs": 300000
}
"Create a proactive agent that checks execution history every hour.
Use AI evaluation to decide if the failure rate is abnormal, then notify me via email."
{
"monitorInterval": "1h",
"evaluation": { "mode": "ai", "modelTier": "mini", "maxCreditsPerDay": 50 },
"monitors": [{
"type": "execution_history",
"condition": "consecutive_failures",
"threshold": 3
}],
"actions": [{
"type": "notify",
"channel": "email",
"message": "{{monitor.summary}}"
}],
"maxActionsPerDay": 5
}
"Pause proactive agent pa_xyz789"
"Resume proactive agent pa_xyz789"
git clone https://github.com/Agentled/mcp-server.git
cd mcp-server
npm install
npm run build
MIT
Be the first to review this server!
by Modelcontextprotocol ยท Developer Tools
Read, search, and manipulate Git repositories programmatically
by Toleno ยท Developer Tools
Toleno Network MCP Server โ Manage your Toleno mining account with Claude AI using natural language.
by mcp-marketplace ยท Developer Tools
Create, build, and publish Python MCP servers to PyPI โ conversationally.
by Microsoft ยท Content & Media
Convert files (PDF, Word, Excel, images, audio) to Markdown for LLM consumption
by mcp-marketplace ยท Developer Tools
Scaffold, build, and publish TypeScript MCP servers to npm โ conversationally
by mcp-marketplace ยท Finance
Free stock data and market news for any MCP-compatible AI assistant.