Agentled MCP Server

Agentled is the automation engine built for AI agents. Its 40 documented tools cover workflow, step, snapshot, form. It runs locally over stdio via the published package.

People connecting memory tools to Claude, Cursor, VS Code, or another MCP client. The project is written in TypeScript.

VERIFIED ACTIVE

LAST COMMIT 2026-08-22 · ★ 3 · #73 OF 259 MAINTAINED MEMORY · VERIFIED 2026-08-25

MIT · TypeScript servers · how we verify → /methodology

01 · Install Agentled MCP Server

before you install - you'll need

Set AGENTLED_API_KEY, AGENTLED_URL before connecting.

Claude Code

claude mcp add agentled-mcp-server -- npx -y @agentled/mcp-server

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "agentled-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@agentled/mcp-server"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license MIT - declared in the repository

npm package @agentled/mcp-server - published under the repo owner's npm scope (@agentled)

registry namespace io.github.Agentled is GitHub-verified and matches the repo owner

03 · What Agentled MCP Server can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

What you can build

With this server connected, an agent can list all workflows in the workspace, get full workflow definition by ID, including useCaseContext when linked, get ledger-derived, period-labelled workflow credit usage, and create a new workflow from pipeline JSON.

Capability map

Tools grouped from the project's README - what Agentled MCP Server lets an agent do.

Workflow

11 tools - e.g. Get full workflow definition by ID, including useCaseContext when linked; Get ledger-derived, period-labelled workflow credit usage; opt in to cost drivers with includeCostDrivers; Create a new workflow…

get_workflow · get_workflow_credits · create_workflow · update_workflow · update_workflow_context · delete_workflow…

read & search

9 tools - e.g. List all workflows in the workspace; Get the current draft version of a workflow; List version snapshots for a workflow

list_workflows · get_draft · list_snapshots · list_executions · list_timelines · get_timeline…

Step

4 tools - e.g. Add a step with automatic positioning and next-pointer rewiring; Deep-merge updates into a single step by ID; Remove a step with automatic next-pointer rewiring

add_step · update_step · remove_step · get_step_schema

Snapshot

4 tools - e.g. Create a manual config snapshot; Delete a specific config snapshot; Read a snapshot's full config (steps, context, etc.) without restoring it

create_snapshot · delete_snapshot · get_snapshot_content · restore_snapshot

Form

3 tools - e.g. List existing public form links for a workflow; Create and enable a public form link; Enable/disable a link or update limits, expiry, auto-share, and thank-you copy. To revoke external access, set…

list_public_form_links · create_public_form_link · update_public_form_link

Execution

3 tools - e.g. Get execution details with step results. Requires the real executionId, not executionInputId; if needed, call list_executions and match pipelineExecutionInputId; Stop a running execution; Retry a failed…

get_execution · stop_execution · retry_execution

Test

3 tools - e.g. Test an app action without creating a workflow; Test an AI prompt without creating a workflow; Test JavaScript code in the same sandboxed VM as production

test_app_action · test_ai_action · test_code_action

Promote

1 tool - e.g. Promote a draft to the live version

promote_draft

04 · Who maintains Agentled MCP Server

mcp-server is maintained by agentled. It's the only MCP server we track from this author; the repo dates to Mar 2026.

05 · Facts

category
memory - ranked #73 of 259 actively-maintained memory servers as of 2026-08-25.
registry
io.github.Agentled/mcp-server (active, first published 2026-03-23 · 20 versions)
packages
npm:@agentled/mcp-server

06 · Agentled MCP Server FAQ

Is Agentled MCP Server still maintained?

Yes - as of 2026-08-25, its last commit was 2026-08-22. We re-verify nightly.

What can Agentled MCP Server do?

With this server connected, an agent can list all workflows in the workspace, get full workflow definition by ID, including useCaseContext when linked, get ledger-derived, period-labelled workflow credit usage, and create a new workflow from pipeline JSON.

How do I install Agentled MCP Server?

Run `npx -y @agentled/mcp-server`. The README documents 2 environment variables (AGENTLED_API_KEY, AGENTLED_URL) to set first. Set AGENTLED_API_KEY, AGENTLED_URL before connecting. You can also paste the ready-made client config above.

Does Agentled MCP Server run locally?

Yes - it's a stdio server: it runs on your machine (via npx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Agentled MCP Server

Pairs well with

Servers that cover what Agentled MCP Server doesn't - only shown when the pairing reason fits the companion.

  1. Server Filesystem → filesystem companion filesystem · ★ 38,704
  2. X402 List MCP → filesystem companion filesystem · ★ 58