Agentled MCP Server

@agentled/mcp-server

The automation engine built for AI agents. Intelligent AI workflow orchestration with long-term memory, 100+ integrations, and unified credits.

What is Agentled?

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:

🧠 Long-Term Memory — A built-in Knowledge Graph stores insights across workflow executions. Your agents get smarter over time — they remember past research, lead scores, content performance, and business context.

⚡ Unified Credits — 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.

🎯 Intelligent Orchestration — AI reasons at every step. Workflows aren't just "if this then that" — they understand context, make decisions, and adapt to results.

See it in action

$ agentled create "Outbound to fintech CTOs in Europe"

Loading workspace context from Knowledge Graph...
✦ ICP loaded  ✦ 3 prior campaigns  ✦ 847 contacts in KG

Creating campaign with 3 workflows...

━━ Workflow 1: Prospect Research  linkedin · hunter · clearbit
  ✓ LinkedIn: CTO + fintech + EU → 189 profiles
  ✓ Enriched via Hunter + Clearbit → 156 matched
  ✓ ICP scoring → 43 high-intent leads

━━ Workflow 2: Signal Detection  web-scraper · crunchbase
  ✓ Job postings → 12 hiring devops
  ✓ Crunchbase → 8 recently funded
  ✓ Cross-match: hiring + funded → 5 hot leads

━━ Workflow 3: Outreach  email · linkedin · kg
  ✓ Personalized emails from context
  ✓ LinkedIn requests with custom notes
  ✓ 43 leads saved to Knowledge Graph

Campaign saved. Scheduled: every 48h
Credits used: 720
→ https://www.agentled.app/your-team/fintech-cto-outbound

One prompt. Three workflows. LinkedIn enrichment, email finding, AI scoring, multi-channel outreach — all orchestrated, all stored in the Knowledge Graph for the next run.

Quick Start

claude mcp add --transport stdio --scope user agentled \
  -e AGENTLED_API_KEY=wsk_... \
  -- npx -y @agentled/mcp-server

--scope user registers the server in your user MCP config so it loads in every project (not only the repo where you ran the command). Use a distinct server name (e.g. agentled_my_workspace) if you add multiple workspaces. For team-shared config in git, use --scope project and .mcp.json instead (Claude Code MCP scopes).

Claude Code plugin (one-step install)

Prefer the plugin if you want the MCP server and the Agentled skill installed together. In Claude Code:

/plugin marketplace add Agentled/mcp-server
/plugin install agentled@agentled

Then set your API key in the shell Claude Code runs from:

export AGENTLED_API_KEY=wsk_...

Codex plugin (one-step install)

The same repository is a Codex marketplace. Install the Agentled plugin with:

codex plugin marketplace add Agentled/mcp-server
codex plugin add agentled@agentled

Then set AGENTLED_API_KEY=wsk_... in the shell that launches Codex and start a new task. The plugin bundles the Agentled skills, starts the MCP server through npx -y @agentled/mcp-server, and loads its lifecycle hooks from the standard hooks/hooks.json path.

The plugin bundles the agentled skill (workflow-authoring guidance, namespaced agentled:agentled) and auto-starts the MCP server via npx -y @agentled/mcp-server. The same plugin directory carries both Claude Code and Codex manifests — one bundle, both hosts.

For Codex, the hook pack acts as in-session guidance around the CLI/MCP loop: session start explains the Agentled/Codex business-loop split, prompt/tool hooks add turn-level guidance when client needs, priorities, failures, or product gaps appear, and stop hooks nudge implementation handoffs to include readiness, validation, side effects, and next decision. Hooks do not store feedback, call Agentled APIs, run automations, spend credits, or perform customer/workspace writes. In Codex, run /hooks after installing or changing the plugin so the local hook definitions are reviewed and trusted before they run.

Use Codex automations for outside-workspace FDE cadence such as Outlook/client email follow-up, vendor replies, repo/build checks, and weekly operator reviews. Use Agentled routines for Agentled workspace/runtime checks such as workflow health, routine health, execution review, workspace summaries, and managed-agent operations. Use submit_feedback_to_agentled or agentled feedback submit when the user explicitly wants product feedback captured.

Pick one install path, not both. If you previously ran claude mcp add agentled ... or --setup-skills, remove those before (or instead of) installing the plugin — otherwise you get two identical MCP server processes and the skill registered twice. Cleanup: claude mcp remove agentled and delete .claude/skills/agentled/ (or ~/.claude/skills/agentled/). --setup-skills now detects an installed plugin and refuses to double-register unless you pass --force.

To develop the plugin locally:

claude --plugin-dir ./plugins/agentled     # load from source
claude plugin validate ./plugins/agentled  # check manifest + structure

plugins/agentled/skills/ is a generated mirror of skills/ (synced by publish.sh) — edit skills/agentled/SKILL.md, never the mirror.

Local development

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

Getting your API key

1. Sign up at agentled.app
2. Open Workspace Settings > Developer
3. Generate a new API key (starts with wsk_)

Why Agentled MCP?

One API Key. One Credit System. 100+ Services.

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.

Workflows That Learn

Other automation tools start from zero every run. Agentled's Knowledge Graph remembers across executions — 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 → 62% accuracy (cold start)
Run 5:  → 78% (learning from IC feedback)
Run 12: → 89% (compound learning from outcomes, zero manual tuning)

Intelligent Orchestration

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

Agent Teams let you run multiple AI specialists in a single workflow step. Pick a preset and describe what you need — 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:

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}} — 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 — they open in advanced mode in the builder without errors.

Analytics vs ROI semantics

When describing workflow outcomes, keep these terms separate:

• pipeline.analyticsConfig = business metrics (execution outcome stats shown in Business Metrics cards/charts).
• pipeline.metadata.roi = ROI assumptions/rollups (time saved and cost-value estimates).

If you update one without the other, name exactly what changed (e.g. "business metrics configured" vs "ROI assumptions configured").

CLI parity guard

The repository includes an automated parity guard so MCP tool additions do not silently drift from the CLI surface.

• Test: __tests__/cli/cli-mcp-parity.test.ts
• Docs: docs/CLI_MCP_PARITY.md

Run it with:

yarn test:node -- cli-mcp-parity.test.ts

What Can You Build?

Lead Enrichment & Sales Automation

"Find fintech CTOs in Europe, enrich via LinkedIn + Hunter, score by ICP fit,
draft personalized outreach, save everything to the Knowledge Graph"

Content & Media Production

"Scrape trending topics in our niche, generate 5 LinkedIn posts with AI,
create thumbnail images, schedule publishing for the week"

Company Research & Intelligence

"Research this company from its URL — team, funding, market position, competitors.
Generate an investment memo. Store in KG for future reference."

VC Investor Matching (real case study)

"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 — accuracy went from 62% to 89% over 12 runs with zero manual tuning.

Built-in Skills And Integrations

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

Available Tools

Use-case operating guides

When work starts from an existing workflow ID, call get_workflow first and inspect useCaseContext. Then call get_use_case with the returned key or workflow graph ID, and read any operatingGuides before answering workflow-specific questions, running backfills, or editing live config. Missing guide warnings mean the operating README is not attached yet and the context is incomplete.

When work starts from a user's business goal rather than an existing workflow, use How to Build Use Cases From User Goals. It covers the external-agent lifecycle from bounded chat result to KG text/list state, WorkspaceUseCase, workflows, approval queues, and home summary updates.

Workflows

Public Form Links

Public form links are the external intake surface for workflows with context.executionInputConfig fields. Use them when people outside the workspace need to submit a workflow form without signing in: inbound lead forms, pitch deck submissions, referral forms, support intake, assessment questionnaires, or any workflow whose first step is a manual/input trigger.

Do not use a public form link for internal child workflows. Child workflows should use context.executionInputConfig.internal: true and be called from another workflow with agentled.call-workflow.

Deletion is intentionally not exposed via the external API or MCP. To revoke a public form link, call update_public_form_link with enabled: false. Permanent deletion requires an authenticated workspace member acting through the UI — destructive ops on the form-link surface are not granted to the public API key.

Typical agent flow:

1. get_workflow({ workflowId })
2. Confirm context.executionInputConfig exists and is not internal.
3. list_public_form_links({ workflowId })
4. If none exists, create_public_form_link({ workflowId, enabled: true })
5. Return the publicUrl to the user.

The public URL is /en/forms/{formLinkId}. On submit, Agentled validates the form link, starts the workflow with the submitted input, records a PublicFormSubmission, and increments submissionCount. Optional settings:

• enabled: disable without deleting the link.
• expiresAt: ISO datetime expiry.
• submissionLimit: maximum accepted submissions.
• autoShare: when true, the public form status page can show generated results after completion. Use this only when the workflow output is safe for the submitter to see.
• shareExpiresInDays: expiry for auto-shared result links.
• successMessage: custom thank-you message after submission.

Internal-only Workflows

Mark a workflow as a child / sub-workflow that is only run via agentled.call-workflow from an orchestrator by setting context.executionInputConfig.internal: true. The UI then hides the Run button and replaces the manual run form with an info banner. Inputs are still validated and passed by orchestrators via executionInputData exactly as before — this is a UI guard, not a runtime restriction.

Use it for any workflow whose goal/description starts with "Internal sub-workflow", that ends in a return step, or that you only intend to invoke from another workflow.

{
  "context": {
    "executionInputConfig": {
      "title": "Save Sourced Candidates",
      "internal": true,
      "fields": [{ "name": "candidates", "label": "Candidates", "type": "text", "required": true }]
    }
  }
}

Flip the flag via update_workflow_context — fetch first, merge locally, replace at the parent level (the merge-order trap from update_step applies here too — see docs/MCP_STEP_EDITING.md):

// 1. get_workflow → read context.executionInputConfig
// 2. local: { ...executionInputConfig, internal: true }
// 3.
{
  "updates": { "context": { "executionInputConfig": {...full merged value...} } },
  "replace": ["context.executionInputConfig"]
}

Editing existing workflows: merge model

Prefer the surgical path tools for common single-path edits — they call get_step when needed and map to the same merge contract:

• replace_step_dictionary — dictionary key merges (fieldUpdates, responseStructure, fieldMapping)
• replace_step_path — nested path sets that must preserve siblings
• unset_step_path — delete one path
• append_step_array_item / remove_step_array_item — array mutations

Keep raw update_step for complex multi-path edits. It accepts three explicit operations on the same call; at least one must be non-empty.

• updates — partial step patch, deep-merged ONE LEVEL deep. Top-level scalars are replaced; nested objects (pipelineStepPrompt, stepInputData, etc.) get their direct keys merged with the stored value's keys. Keys nested two levels deep are overwritten as a unit, not merged.
• replace: string[] — dot-paths whose values from updates are assigned wholesale, skipping the deep-merge. Use this for dictionary-shaped fields where keys are user data (not config) — patching one inner key with updates alone silently wipes the others.
• unset: string[] — dot-paths to delete. Each path must currently exist on the step (validated against the original).

Read before editing dictionary fields. Prefer replace_step_dictionary. With raw update_step, call get_step({ workflowId, stepId }) (~1KB), modify locally, send the full new object back via replace[].

Diff in the response. Every update_step / surgical-tool call returns diff: { addedPaths, changedPaths, removedPaths } and warnings[]. If the merge silently removed ≥6 fields without an explicit unset, a warning fires.

What to use where:

Executive summaries for workflow groups. When a user asks to save a summary for a workflow, workflow group, cluster, or home card, write it to metadata.executiveSummary with update_workflow_context. Do not store it as Knowledge text unless the user explicitly asks for a reusable note. For a group, write exactly once to the owner pipeline: prefer metadata.workflowGraph.role === "orchestrator", otherwise use the lowest metadata.workflowGraph.order pipeline. Keep the body to 1-2 short sentences, include concrete counts/rates and the reporting period when available, and set author to the active workspace agent, not the external tool/coding agent.

{
  "workflowId": "2e1cdd60-2fcf-441a-856f-583ae76b38a5",
  "updates": {
    "metadata": {
      "executiveSummary": {
        "body": "Startup Outreach sent 46 founder emails for the reporting period, with 28 opens and 9 clicks: a 60.9% open rate, 19.6% click rate, and 32.1% click-to-open rate.",
        "bullets": ["Clicks: 6 UTM Pitch Night, 2 plain Pitch Night, 1 calendar."],
        "generatedAt": "2026-06-03T00:00:00.000Z",
        "author": "AngelHive Assistant"
      }
    }
  }
}

Type changes. step.type is technically mutable but stale type-specific fields (pipelineStepPrompt, app, tools, orchestratorConfig) persist unless you unset them. For clean conversions, prefer remove_step + add_step.

Live workflows. Edits are routed to a draft snapshot. Response includes editingDraft: true. Inspect via get_draft, ship via promote_draft, throw away via discard_draft. For high-stakes edits, create_snapshot first as a manual checkpoint.

Draft staleness. When a draft exists, every update_step and get_step response includes a draft summary with exists, draftCreatedAt, liveUpdatedAt, stale, modifiedStepIds, and modifiedFields. If draft.stale === true, the live workflow advanced after the draft was created — promoting will land the draft's older values for fields you didn't touch. update_step also emits a staleness warning. Recovery: discard_draft and re-apply.

⚠ discard_draft only reverts pending context (and step) changes — NOT metadata. Metadata writes via update_workflow_context bypass the draft and apply immediately to the live Pipeline row. If you need a single rollback point covering metadata too, create_snapshot before the edit. See docs/MCP_STEP_EDITING.md for the full atomicity contract.

Never send a full steps[] array via update_workflow. Use surgical path tools, update_step, add_step, remove_step instead.

For the deep reference (StepMergeError codes, dot-path validation rules, full diff semantics) see docs/MCP_STEP_EDITING.md.

Drafts & Snapshots

Executions

Run deep links use /<locale>/<workspace>/<workflowPathname>/runs?runId=<executionId>&step=<stepId>. The step query param is optional only for run-level handoffs. When a response points to a specific approval card, output, failure, or current step, include &step=<stepId> and do not ask the human to open the step manually after a run-only URL. When present, the app expands that workflow step and scrolls to it. stepId is the workflow step id, not the timeline id. Inside the app chat/navigation tool surface, navigateToExecutionPage accepts the same stepId.

Knowledge row deep links use /<locale>/<workspace>/knowledge-and-data/<listKey>?rowId=<rowId>. The app opens the Knowledge & Data list page and opens the row editor sheet for that row. The backwards-compatible route /<locale>/<workspace>/knowledge-and-data/<listKey>/row/<rowId> redirects to the canonical query-param URL.

Knowledge text deep links use /<locale>/<workspace>/knowledge-and-data/<key>. The backwards-compatible route /<locale>/<workspace>/knowledge-and-data/text/<key> redirects to the canonical item URL.

Apps & Testing

AI step types: aiAction vs aiActionWithTools

Pick the right type — validate_workflow will reject the wrong one:

aiActionWithTools requires at least one tool — placed under step.tools or step.agent.tools (both are merged at runtime). If you omit tools from both locations, validate_workflow returns a blocker AI_STEP_TOOLS_REQUIRED. If the prompt says "search the web" / "recall memory" / "knowledge graph" without the matching tool attached, you get a warning AI_STEP_TOOL_PROMPT_MISMATCH: web-search prompts need web_search; memory prompts need workspace_memory; KG lookup prompts need kg_search or kg_traverse. fetch_website_content fetches a known URL and kg_write writes KG data, so neither satisfies those lookup/search prompts.

Valid builtinType values: web_search, file_search, code_interpreter, fetch_website_content, kg_search, kg_traverse, kg_nodes, kg_write, workspace_memory.

Prompt caching for repeated AI steps

Agentled enables provider prompt caching where supported. Caching reuses prompt processing for an identical prefix; it does not cache or replay the AI response. To benefit in bulk workflows, especially scoring/matching loops, write prompts with the stable material first:

[stable role and task]
[stable rubric / scoring dimensions]
[stable output JSON schema]
[stable examples or decision rules]

Runtime inputs:
{{currentItem}}
{{steps.previous.output}}
{{input.field}}

Do not start high-volume prompts with INPUTS, {{currentItem}}, {{steps.*}}, {{input.*}}, {{execution.id}}, {{now}}, or {{today}}. Keep changing payloads, dates, execution IDs, and per-item records at the end so OpenAI/Anthropic can cache the shared prefix.

// aiActionWithTools example
{
  "id": "research",
  "type": "aiActionWithTools",
  "name": "Research Company",
  "tools": [
    { "type": "builtin", "builtinType": "web_search", "name": "Web Search" }
  ],
  "pipelineStepPrompt": {
    "template": "Search the web for the founder of {{input.company}} and return their name.",
    "responseStructure": { "firstName": "string", "lastName": "string" }
  },
  "creditCost": 10,
  "next": { "stepId": "find-email" }
}

Knowledge & Data

Credits and Cost Drivers

Credit reporting tools are opt-in for cost-driver detail so existing balance checks stay compact. Every credit total is ledger-derived and returned with a period object containing label, display, start, and end; always show that period label next to totals.

For a human/operator UI check, open the workspace credit usage page:

https://www.agentled.app/en/{workspace}/account/billing/credits-usage

Example: https://www.agentled.app/en/inovexus/account/billing/credits-usage.

Supported periods:

• rolling-30-days: moving 30-day window ending at request time.
• rolling-7-days: moving 7-day window ending at request time.
• current-month / month-to-date: UTC calendar month-to-date, not the billing renewal period.
• previous-month: prior UTC calendar month.
• all-time: full ledger before the request time; use intentionally because it can scan more rows.

Examples:

// Compact balance/burn-rate check
{ "tool": "get_workspace_credits", "arguments": { "period": "rolling-30-days" } }

// Workspace cost drivers for a calendar month-to-date window
{ "tool": "get_workspace_credit_cost_drivers", "arguments": { "period": "current-month", "limit": 5 } }

// Workflow cost drivers
{ "tool": "get_workflow_credits", "arguments": { "workflowId": "wf_abc123", "period": "rolling-30-days", "includeCostDrivers": true } }

External API equivalents:

GET /api/external/workspace/credits?period=rolling-30-days&include=costDrivers&limit=5
GET /api/external/workflows/{workflowId}/credits?period=current-month&include=costDrivers

Billing-period reporting is separate from calendar-month reporting and should not be implied unless a future API adds an explicit billing-period label.

Branding (Whitelabel)

Agents

First-class workspace AI Agents with identity, instructions, tools, config files, and assigned workflows. All agents are conversational by default. For scheduled/autonomous work, attach routines via create_routine to create an AI Agent with routines. SOUL.md and TOOLS.md live in configFiles; reflection context (JOURNAL.md, OBJECTIVES.md, PEOPLE.md) lives as linked AgentFiles and is auto-seeded for active AI Agents using reflection. Agents decide what durable signal belongs in those files; AgentLed only provides scoped storage and scheduled Reflection. An agent created entirely via MCP renders identically to one built in the Agent Wizard.

Slug convention: slug is the short role ID used in URLs and email addresses. Keep Agent in the display name when useful, but do not append -agent to the slug just because the display name includes it; for example, Deal Sourcing Agent should use deal-sourcing@{workspace}.agentled.ai, not deal-sourcing-agent@{workspace}.agentled.ai.

Built-in app result cache

Separate from prompt caching: many app actions reuse prior results via workspace KnowledgeRow defaults. See the Agentled skill section Built-in app result cache (skills/agentled/SKILL.md). MCP rerun tools default forceWithoutCache: true.

Agent Files

Documentation truncated — see the full README on GitHub.